model family

Llama 3.2

Published by meta-llama. 4 members measured on real machines, across 24 builds. Every number below was signed by the machine that produced it — none of it is from a model card.

what it takes, what it returns
text → text

Declared by the network’s catalog, not measured — a signature says what this family would be asked. Whether it answered is the signed capability flags on each member.

24 of 51 builds measured · 27 still open
what each build proved
3b · F16
3b · IQ3_M
3b · Q3_K_L
3b · Q4_K_M · bartowski
3b · Q8_0 · bartowski
1b · Q8_0 · ollama
1b · Q4_K_M · bartowski
3b · BF16
3b~chuanli11-llama-3-2-uncensored · IQ3_XS
1b · IQ3_XS
1b · Q8_0 · bartowski
1b · IQ1_S
1b · F16
1b · Q4_K_M · MaziyarPanahi
3b · IQ1_S · unsloth
1b · IQ3_M
1b · Q3_K_L
1b~hugging-quants-llama-3-2-k-m · Q4_K_M
3b · IQ1_S · MaziyarPanahi
3b · IQ2_XXS
3b · IQ3_XXS
3b · Q4_0
3b · Q4_K_M · unsloth
3b · Q8_0 · unsloth
3b · F16 · Tool calling — proved3b · F16 · Tool loop finished — proved3b · F16 · Faithful to tool results — proved3b · F16 · Structured output — proved3b · F16 · Sustained output — proved3b · F16 · Writes code — proved3b · F16 · Reasons about code — asked, failed3b · F16 · Synthesises sources — asked, failed3b · F16 · Follows instructions — proved3b · IQ3_M · Tool calling — proved3b · IQ3_M · Tool loop finished — proved3b · IQ3_M · Faithful to tool results — proved3b · IQ3_M · Structured output — proved3b · IQ3_M · Sustained output — proved3b · IQ3_M · Writes code — proved3b · IQ3_M · Reasons about code — asked, failed3b · IQ3_M · Synthesises sources — proved3b · IQ3_M · Follows instructions — proved3b · Q3_K_L · Tool calling — proved3b · Q3_K_L · Tool loop finished — proved3b · Q3_K_L · Faithful to tool results — proved3b · Q3_K_L · Structured output — proved3b · Q3_K_L · Sustained output — proved3b · Q3_K_L · Writes code — proved3b · Q3_K_L · Reasons about code — proved3b · Q3_K_L · Synthesises sources — proved3b · Q3_K_L · Follows instructions — asked, failed3b · Q4_K_M · bartowski · Tool calling — proved3b · Q4_K_M · bartowski · Tool loop finished — proved3b · Q4_K_M · bartowski · Faithful to tool results — proved3b · Q4_K_M · bartowski · Structured output — proved3b · Q4_K_M · bartowski · Sustained output — proved3b · Q4_K_M · bartowski · Writes code — proved3b · Q4_K_M · bartowski · Reasons about code — asked, failed3b · Q4_K_M · bartowski · Synthesises sources — proved3b · Q4_K_M · bartowski · Follows instructions — asked, failed3b · Q8_0 · bartowski · Tool calling — proved3b · Q8_0 · bartowski · Tool loop finished — proved3b · Q8_0 · bartowski · Faithful to tool results — proved3b · Q8_0 · bartowski · Structured output — proved3b · Q8_0 · bartowski · Sustained output — proved3b · Q8_0 · bartowski · Writes code — proved3b · Q8_0 · bartowski · Reasons about code — asked, failed3b · Q8_0 · bartowski · Synthesises sources — asked, failed3b · Q8_0 · bartowski · Follows instructions — asked, failed1b · Q8_0 · ollama · Tool calling — proved1b · Q8_0 · ollama · Tool loop finished — proved1b · Q8_0 · ollama · Faithful to tool results — proved1b · Q8_0 · ollama · Structured output — proved1b · Q8_0 · ollama · Sustained output — proved1b · Q8_0 · ollama · Writes code — proved1b · Q8_0 · ollama · Reasons about code — asked, failed1b · Q8_0 · ollama · Synthesises sources — proved1b · Q8_0 · ollama · Follows instructions — proved1b · Q4_K_M · bartowski · Tool calling — proved1b · Q4_K_M · bartowski · Tool loop finished — proved1b · Q4_K_M · bartowski · Faithful to tool results — proved1b · Q4_K_M · bartowski · Structured output — proved1b · Q4_K_M · bartowski · Sustained output — proved1b · Q4_K_M · bartowski · Writes code — proved1b · Q4_K_M · bartowski · Reasons about code — asked, failed1b · Q4_K_M · bartowski · Synthesises sources — proved1b · Q4_K_M · bartowski · Follows instructions — proved3b · BF16 · Tool calling — proved3b · BF16 · Tool loop finished — proved3b · BF16 · Faithful to tool results — proved3b · BF16 · Structured output — proved3b · BF16 · Sustained output — proved3b · BF16 · Writes code — proved3b · BF16 · Reasons about code — asked, failed3b · BF16 · Synthesises sources — asked, failed3b · BF16 · Follows instructions — proved3b~chuanli11-llama-3-2-uncensored · IQ3_XS · Tool calling — proved3b~chuanli11-llama-3-2-uncensored · IQ3_XS · Tool loop finished — proved3b~chuanli11-llama-3-2-uncensored · IQ3_XS · Faithful to tool results — asked, failed3b~chuanli11-llama-3-2-uncensored · IQ3_XS · Structured output — proved3b~chuanli11-llama-3-2-uncensored · IQ3_XS · Sustained output — proved3b~chuanli11-llama-3-2-uncensored · IQ3_XS · Writes code — proved3b~chuanli11-llama-3-2-uncensored · IQ3_XS · Reasons about code — asked, failed3b~chuanli11-llama-3-2-uncensored · IQ3_XS · Synthesises sources — asked, failed3b~chuanli11-llama-3-2-uncensored · IQ3_XS · Follows instructions — proved1b · IQ3_XS · Tool calling — proved1b · IQ3_XS · Tool loop finished — proved1b · IQ3_XS · Faithful to tool results — proved1b · IQ3_XS · Structured output — proved1b · IQ3_XS · Sustained output — proved1b · IQ3_XS · Writes code — proved1b · IQ3_XS · Reasons about code — asked, failed1b · IQ3_XS · Synthesises sources — asked, failed1b · IQ3_XS · Follows instructions — proved1b · Q8_0 · bartowski · Tool calling — proved1b · Q8_0 · bartowski · Tool loop finished — proved1b · Q8_0 · bartowski · Faithful to tool results — proved1b · Q8_0 · bartowski · Structured output — proved1b · Q8_0 · bartowski · Sustained output — proved1b · Q8_0 · bartowski · Writes code — proved1b · Q8_0 · bartowski · Reasons about code — asked, failed1b · Q8_0 · bartowski · Synthesises sources — asked, failed1b · Q8_0 · bartowski · Follows instructions — proved1b · IQ1_S · Tool calling — asked, failed1b · IQ1_S · Tool loop finished — never asked1b · IQ1_S · Faithful to tool results — never asked1b · IQ1_S · Structured output — asked, failed1b · IQ1_S · Sustained output — asked, failed1b · IQ1_S · Writes code — asked, failed1b · IQ1_S · Reasons about code — asked, failed1b · IQ1_S · Synthesises sources — asked, failed1b · IQ1_S · Follows instructions — asked, failed1b · F16 · Tool calling — proved1b · F16 · Tool loop finished — proved1b · F16 · Faithful to tool results — proved1b · F16 · Structured output — proved1b · F16 · Sustained output — proved1b · F16 · Writes code — proved1b · F16 · Reasons about code — asked, failed1b · F16 · Synthesises sources — asked, failed1b · F16 · Follows instructions — proved1b · Q4_K_M · MaziyarPanahi · Tool calling — proved1b · Q4_K_M · MaziyarPanahi · Tool loop finished — proved1b · Q4_K_M · MaziyarPanahi · Faithful to tool results — proved1b · Q4_K_M · MaziyarPanahi · Structured output — proved1b · Q4_K_M · MaziyarPanahi · Sustained output — proved1b · Q4_K_M · MaziyarPanahi · Writes code — proved1b · Q4_K_M · MaziyarPanahi · Reasons about code — asked, failed1b · Q4_K_M · MaziyarPanahi · Synthesises sources — asked, failed1b · Q4_K_M · MaziyarPanahi · Follows instructions — proved3b · IQ1_S · unsloth · Tool calling — asked, failed3b · IQ1_S · unsloth · Tool loop finished — never asked3b · IQ1_S · unsloth · Faithful to tool results — never asked3b · IQ1_S · unsloth · Structured output — asked, failed3b · IQ1_S · unsloth · Sustained output — asked, failed3b · IQ1_S · unsloth · Writes code — asked, failed3b · IQ1_S · unsloth · Reasons about code — asked, failed3b · IQ1_S · unsloth · Synthesises sources — asked, failed3b · IQ1_S · unsloth · Follows instructions — asked, failed1b · IQ3_M · Tool calling — proved1b · IQ3_M · Tool loop finished — proved1b · IQ3_M · Faithful to tool results — proved1b · IQ3_M · Structured output — proved1b · IQ3_M · Sustained output — proved1b · IQ3_M · Writes code — proved1b · IQ3_M · Reasons about code — asked, failed1b · IQ3_M · Synthesises sources — asked, failed1b · IQ3_M · Follows instructions — proved1b · Q3_K_L · Tool calling — proved1b · Q3_K_L · Tool loop finished — proved1b · Q3_K_L · Faithful to tool results — asked, failed1b · Q3_K_L · Structured output — proved1b · Q3_K_L · Sustained output — proved1b · Q3_K_L · Writes code — proved1b · Q3_K_L · Reasons about code — asked, failed1b · Q3_K_L · Synthesises sources — asked, failed1b · Q3_K_L · Follows instructions — proved1b~hugging-quants-llama-3-2-k-m · Q4_K_M · Tool calling — asked, failed1b~hugging-quants-llama-3-2-k-m · Q4_K_M · Tool loop finished — never asked1b~hugging-quants-llama-3-2-k-m · Q4_K_M · Faithful to tool results — never asked1b~hugging-quants-llama-3-2-k-m · Q4_K_M · Structured output — proved1b~hugging-quants-llama-3-2-k-m · Q4_K_M · Sustained output — proved1b~hugging-quants-llama-3-2-k-m · Q4_K_M · Writes code — asked, failed1b~hugging-quants-llama-3-2-k-m · Q4_K_M · Reasons about code — asked, failed1b~hugging-quants-llama-3-2-k-m · Q4_K_M · Synthesises sources — asked, failed1b~hugging-quants-llama-3-2-k-m · Q4_K_M · Follows instructions — asked, failed3b · IQ1_S · MaziyarPanahi · Tool calling — asked, failed3b · IQ1_S · MaziyarPanahi · Tool loop finished — never asked3b · IQ1_S · MaziyarPanahi · Faithful to tool results — never asked3b · IQ1_S · MaziyarPanahi · Structured output — proved3b · IQ1_S · MaziyarPanahi · Sustained output — proved3b · IQ1_S · MaziyarPanahi · Writes code — asked, failed3b · IQ1_S · MaziyarPanahi · Reasons about code — asked, failed3b · IQ1_S · MaziyarPanahi · Synthesises sources — asked, failed3b · IQ1_S · MaziyarPanahi · Follows instructions — asked, failed3b · IQ2_XXS · Tool calling — asked, failed3b · IQ2_XXS · Tool loop finished — never asked3b · IQ2_XXS · Faithful to tool results — never asked3b · IQ2_XXS · Structured output — proved3b · IQ2_XXS · Sustained output — proved3b · IQ2_XXS · Writes code — asked, failed3b · IQ2_XXS · Reasons about code — proved3b · IQ2_XXS · Synthesises sources — asked, failed3b · IQ2_XXS · Follows instructions — proved3b · IQ3_XXS · Tool calling — proved3b · IQ3_XXS · Tool loop finished — proved3b · IQ3_XXS · Faithful to tool results — proved3b · IQ3_XXS · Structured output — proved3b · IQ3_XXS · Sustained output — proved3b · IQ3_XXS · Writes code — proved3b · IQ3_XXS · Reasons about code — asked, failed3b · IQ3_XXS · Synthesises sources — asked, failed3b · IQ3_XXS · Follows instructions — proved3b · Q4_0 · Tool calling — proved3b · Q4_0 · Tool loop finished — proved3b · Q4_0 · Faithful to tool results — proved3b · Q4_0 · Structured output — proved3b · Q4_0 · Sustained output — proved3b · Q4_0 · Writes code — proved3b · Q4_0 · Reasons about code — asked, failed3b · Q4_0 · Synthesises sources — asked, failed3b · Q4_0 · Follows instructions — asked, failed3b · Q4_K_M · unsloth · Tool calling — proved3b · Q4_K_M · unsloth · Tool loop finished — proved3b · Q4_K_M · unsloth · Faithful to tool results — proved3b · Q4_K_M · unsloth · Structured output — proved3b · Q4_K_M · unsloth · Sustained output — proved3b · Q4_K_M · unsloth · Writes code — proved3b · Q4_K_M · unsloth · Reasons about code — proved3b · Q4_K_M · unsloth · Synthesises sources — asked, failed3b · Q4_K_M · unsloth · Follows instructions — proved3b · Q8_0 · unsloth · Tool calling — proved3b · Q8_0 · unsloth · Tool loop finished — proved3b · Q8_0 · unsloth · Faithful to tool results — proved3b · Q8_0 · unsloth · Structured output — proved3b · Q8_0 · unsloth · Sustained output — proved3b · Q8_0 · unsloth · Writes code — proved3b · Q8_0 · unsloth · Reasons about code — asked, failed3b · Q8_0 · unsloth · Synthesises sources — proved3b · Q8_0 · unsloth · Follows instructions — proved
Tool calling
Tool loop finished
Faithful to tool results
Structured output
Sustained output
Writes code
Reasons about code
Synthesises sources
Follows instructions
Llama 3.2 3B13 builds measured →
hf.co/bartowski/Llama-3.2-3B-Instruct-GGUF:F163b · F16 · bartowski · ollama · 1 machine · 3.21B
1,31,072recalled
—served
38.3best tok/s
recalled 128k⌐ declared 128k · unsigned
hf.co/bartowski/Llama-3.2-3B-Instruct-GGUF:IQ3_M3b · IQ3_M · bartowski · ollama · 1 machine · 3.21B
1,31,072recalled
—served
72.0best tok/s
recalled 128k⌐ declared 128k · unsigned
hf.co/bartowski/Llama-3.2-3B-Instruct-GGUF:Q3_K_L3b · Q3_K_L · bartowski · ollama · 1 machine · 3.21B
1,31,072recalled
—served
78.8best tok/s
recalled 128k⌐ declared 128k · unsigned
hf.co/bartowski/Llama-3.2-3B-Instruct-GGUF:Q4_K_M3b · Q4_K_M · bartowski · ollama · 1 machine · 3.21B
1,31,072recalled
—served
86.9best tok/s
recalled 128k⌐ declared 128k · unsigned
hf.co/bartowski/Llama-3.2-3B-Instruct-GGUF:Q8_03b · Q8_0 · bartowski · ollama · 1 machine · 3.21B
1,31,072recalled
—served
62.8best tok/s
recalled 128k⌐ declared 128k · unsigned
hf.co/unsloth/Llama-3.2-3B-Instruct-GGUF:F163b · BF16 · unsloth · ollama · 1 machine · 3.21B
16,384recalled
—served
94.9best tok/s
recalled 16k⌐ declared 128k · unsignedadvertises 8× what it proved
hf.co/unsloth/Llama-3.2-3B-Instruct-GGUF:IQ1_S3b · IQ1_S · unsloth · ollama · 2 machines · 3.21B
—recalled
—served
225.2best tok/s
225.2 tok/s · unnamed machine94.5 tok/s · unnamed machine
94.5 → 225.2 tok/s across 2 machines · ×2.4 spreadunnamed machine
hf.co/MaziyarPanahi/Llama-3.2-3B-Instruct-GGUF:IQ1_S3b · IQ1_S · maziyarpanahi · ollama · 1 machine
—recalled
—served
45.7best tok/s
hf.co/unsloth/Llama-3.2-3B-Instruct-GGUF:IQ2_XXS3b · IQ2_XXS · unsloth · ollama · 1 machine
—recalled
—served
124.2best tok/s
hf.co/unsloth/Llama-3.2-3B-Instruct-GGUF:IQ3_XXS3b · IQ3_XXS · unsloth · ollama · 1 machine
—recalled
—served
199.5best tok/s
hf.co/unsloth/Llama-3.2-3B-Instruct-GGUF:Q4_03b · Q4_0 · unsloth · ollama · 1 machine
—recalled
—served
205.1best tok/s
hf.co/unsloth/Llama-3.2-3B-Instruct-GGUF:Q4_K_M3b · Q4_K_M · unsloth · ollama · 1 machine
—recalled
—served
203.9best tok/s
hf.co/unsloth/Llama-3.2-3B-Instruct-GGUF:Q8_03b · Q8_0 · unsloth · ollama · 1 machine
—recalled
—served
72.8best tok/s
Llama 3.2 1B9 builds measured →
llama3.2:1b1b · Q8_0 · ollama · ollama · 10 machines · 1.2B
32,768recalled
—served
49.9best tok/s
29.1 tok/s · unnamed machine20.4 tok/s · unnamed machine13.1 tok/s · unnamed machine11.4 tok/s · x86 · CPU · North Charleston11.0 tok/s · unnamed machine10.7 tok/s · unnamed machine9.7 tok/s · unnamed machine7.7 tok/s · unnamed machine3.4 tok/s · unnamed machine0.8 tok/s · unnamed machine
0.8 → 29.1 tok/s across 10 machines · ×36.1 spreadunnamed machinex86 · CPU
recalled 32k⌐ declared 128k · unsignedadvertises 4× what it proved
hf.co/bartowski/Llama-3.2-1B-Instruct-GGUF:Q4_K_M1b · Q4_K_M · bartowski · ollama · 4 machines · 1.24B
16,384recalled
—served
103.9best tok/s
103.9 tok/s · unnamed machine12.2 tok/s · unnamed machine11.6 tok/s · unnamed machine4.7 tok/s · unnamed machine
4.7 → 103.9 tok/s across 4 machines · ×22.0 spreadunnamed machine
recalled 16k⌐ declared 128k · unsignedadvertises 8× what it proved
hf.co/MaziyarPanahi/Llama-3.2-1B-Instruct-GGUF:IQ3_XS1b · IQ3_XS · MaziyarPanahi · ollama · 3 machines · 1.24B
4,096recalled
—served
107.5best tok/s
107.5 tok/s · unnamed machine17.7 tok/s · unnamed machine1.5 tok/s · unnamed machine
1.5 → 107.5 tok/s across 3 machines · ×72.9 spreadunnamed machine
recalled 4k⌐ declared 128k · unsignedadvertises 32× what it proved
hf.co/bartowski/Llama-3.2-1B-Instruct-GGUF:Q8_01b · Q8_0 · bartowski · ollama · 1 machine · 1.24B
4,096recalled
—served
8.7best tok/s
recalled 4k⌐ declared 128k · unsignedadvertises 32× what it proved
hf.co/MaziyarPanahi/Llama-3.2-1B-Instruct-GGUF:IQ1_S1b · IQ1_S · MaziyarPanahi · ollama · 4 machines · 1.24B
—recalled
—served
105.0best tok/s
105.0 tok/s · unnamed machine10.7 tok/s · unnamed machine6.6 tok/s · unnamed machine3.3 tok/s · unnamed machine
3.3 → 105.0 tok/s across 4 machines · ×32.2 spreadunnamed machine
hf.co/bartowski/Llama-3.2-1B-Instruct-GGUF:F161b · F16 · bartowski · ollama · 2 machines · 1.24B
—recalled
—served
8.0best tok/s
6.7 tok/s · unnamed machine4.3 tok/s · unnamed machine
4.3 → 6.7 tok/s across 2 machines · ×1.6 spreadunnamed machine
hf.co/MaziyarPanahi/Llama-3.2-1B-Instruct-GGUF:Q4_K_M1b · Q4_K_M · MaziyarPanahi · ollama · 2 machines · 1.24B
—recalled
—served
113.3best tok/s
113.3 tok/s · unnamed machine8.9 tok/s · unnamed machine
8.9 → 113.3 tok/s across 2 machines · ×12.8 spreadunnamed machine
hf.co/bartowski/Llama-3.2-1B-Instruct-GGUF:IQ3_M1b · IQ3_M · bartowski · ollama · 1 machine · 1.24B
—recalled
—served
5.3best tok/s
hf.co/bartowski/Llama-3.2-1B-Instruct-GGUF:Q3_K_L1b · Q3_K_L · bartowski · ollama · 1 machine · 1.24B
—recalled
—served
10.4best tok/s
Llama-3.2-3B-Instruct-uncensored1 build measured →
hf.co/bartowski/Llama-3.2-3B-Instruct-uncensored-GGUF:IQ3_XS3b~chuanli11-llama-3-2-uncensored · IQ3_XS · bartowski · ollama · 1 machine
8,192recalled
—served
46.8best tok/s
Llama-3.2-1B-Instruct-Q4_K_M-GGUF1 build measured →
hf.co/hugging-quants/Llama-3.2-1B-Instruct-Q4_K_M-GGUF:Q4_K_M1b~hugging-quants-llama-3-2-k-m · Q4_K_M · hugging-quants · ollama · 1 machine · 1.24B
—recalled
—served
11.3best tok/s

Builds this network knows of

Declared, not measured — this is what the catalog says exists and what it would cost a machine to hold. Nothing here is signed, and none of it claims the build works.

how much memory does your machine have

48 of 51 builds fit a 16 GB machine — budgeting 70% of it, or 11.2 GiB, because the cache and the runtime want the rest.

  • hf.co/MaziyarPanahi/Llama-3.2-1B-Instruct-GGUF:IQ1_SIQ1_Sollamameasured herequantized by MaziyarPanahi
    0.4 GiB
  • hf.co/bartowski/Llama-3.2-1B-Instruct-GGUF:IQ3_MIQ3_Mollamameasured herequantized by bartowski
    0.6 GiB
  • mlx-community/Llama-3.2-1B-Instruct-4bit4BITmlxderived by mlx-community
    0.6 GiB
  • hf.co/bartowski/Llama-3.2-1B-Instruct-GGUF:Q3_K_LQ3_K_Lollamameasured herequantized by bartowski
    0.7 GiB
  • hf.co/bartowski/Llama-3.2-1B-Instruct-GGUF:Q4_0_8_8Q4_0_8_8ollamaquantized by bartowski
    0.7 GiB
  • hf.co/bartowski/Llama-3.2-1B-Instruct-GGUF:Q4_0_4_4Q4_0_4_4ollamaquantized by bartowski
    0.7 GiB
  • hf.co/bartowski/Llama-3.2-1B-Instruct-GGUF:Q4_K_MQ4_K_Mollamameasured herequantized by bartowski
    0.8 GiB
  • hf.co/hugging-quants/Llama-3.2-1B-Instruct-Q4_K_M-GGUF:Q4_K_MQ4_K_Mollamameasured herederived by hugging-quants
    0.8 GiB
  • hf.co/unsloth/Llama-3.2-3B-Instruct-GGUF:IQ1_SIQ1_Sollamameasured herequantized by unsloth
    0.8 GiB
  • mobilint/Llama-3.2-1B-InstructBF16vllmquantized by mobilint
    1.0 GiB
  • unsloth/Llama-3.2-1B-Instruct-unsloth-bnb-4bitBITSANDBYTESvllmderived by unsloth
    1.0 GiB
  • hf.co/bartowski/Llama-3.2-1B-Instruct-GGUF:Q8_0Q8_0ollamameasured herequantized by bartowski
    1.2 GiB
  • hf.co/QuantFactory/Llama-3.2-3B-Instruct-abliterated-GGUF:Q2_KQ2_Kollamaderived by QuantFactory
    1.3 GiB
  • hf.co/bartowski/Llama-3.2-3B-Instruct-uncensored-GGUF:Q2_KQ2_Kollamaderived by bartowski
    1.4 GiB
  • hf.co/QuantFactory/Llama-3.2-3B-Instruct-abliterated-GGUF:Q3_K_SQ3_K_Sollamaderived by QuantFactory
    1.4 GiB
  • hf.co/bartowski/Llama-3.2-3B-Instruct-GGUF:IQ3_MIQ3_Mollamameasured herequantized by bartowski
    1.5 GiB
  • hf.co/bartowski/Llama-3.2-3B-Instruct-uncensored-GGUF:IQ3_XSIQ3_XSollamameasured herederived by bartowski
    1.5 GiB
  • mlx-community/Llama-3.2-3B-Instruct-4bit4BITmlxderived by mlx-community
    1.7 GiB
  • hf.co/bartowski/Llama-3.2-3B-Instruct-GGUF:Q3_K_LQ3_K_Lollamameasured herequantized by bartowski
    1.7 GiB
  • hf.co/QuantFactory/Llama-3.2-3B-Instruct-abliterated-GGUF:Q3_K_LQ3_K_Lollamaderived by QuantFactory
    1.7 GiB
  • hf.co/bartowski/Llama-3.2-3B-Instruct-GGUF:Q4_0_4_4Q4_0_4_4ollamaquantized by bartowski
    1.8 GiB
  • hf.co/bartowski/Llama-3.2-3B-Instruct-GGUF:Q4_0_8_8Q4_0_8_8ollamaquantized by bartowski
    1.8 GiB
  • hf.co/QuantFactory/Llama-3.2-3B-Instruct-abliterated-GGUF:Q4_0Q4_0ollamaderived by QuantFactory
    1.8 GiB
  • hf.co/bartowski/Llama-3.2-3B-Instruct-uncensored-GGUF:Q3_K_LQ3_K_Lollamaderived by bartowski
    1.8 GiB
  • hf.co/bartowski/Llama-3.2-3B-Instruct-GGUF:Q4_K_MQ4_K_Mollamameasured herequantized by bartowski
    1.9 GiB
  • hf.co/hugging-quants/Llama-3.2-3B-Instruct-Q4_K_M-GGUF:Q4_K_MQ4_K_Mollamaderived by hugging-quants
    1.9 GiB
  • hf.co/QuantFactory/Llama-3.2-3B-Instruct-abliterated-GGUF:Q4_K_MQ4_K_Mollamaderived by QuantFactory
    1.9 GiB
  • RedHatAI/Llama-3.2-1B-Instruct-FP8-dynamicFP8vllmquantized by RedHatAI
    1.9 GiB
  • hf.co/bartowski/Llama-3.2-3B-Instruct-uncensored-GGUF:Q4_0_4_8Q4_0_4_8ollamaderived by bartowski
    2.0 GiB
  • hf.co/bartowski/Llama-3.2-3B-Instruct-uncensored-GGUF:Q4_0_8_8Q4_0_8_8ollamaderived by bartowski
    2.0 GiB
  • hf.co/bartowski/Llama-3.2-3B-Instruct-uncensored-GGUF:Q4_K_MQ4_K_Mollamaderived by bartowski
    2.1 GiB
  • unsloth/Llama-3.2-3B-Instruct-unsloth-bnb-4bitBITSANDBYTESvllmderived by unsloth
    2.2 GiB
  • mlx-community/Llama-3.2-1B-Instruct-bf16BF16mlxderived by mlx-community
    2.3 GiB
  • THGLab/Llama-3.2-1B-Instruct-LinkLlama-Cap50BF16vllmderived by THGLab
    2.3 GiB
  • unsloth/Llama-3.2-1B-InstructBF16vllmderived by unsloth
    2.3 GiB
  • hf.co/bartowski/Llama-3.2-1B-Instruct-GGUF:F16F16ollamameasured herequantized by bartowski
    2.3 GiB
  • mlx-community/Llama-3.2-3B-Instruct-uncensored-6bit6BITmlxderived by mlx-community
    2.4 GiB
  • mlx-community/Llama-3.2-3B-Instruct-8bitBF16mlxderived by mlx-community
    3.2 GiB
  • hf.co/bartowski/Llama-3.2-3B-Instruct-GGUF:Q8_0Q8_0ollamameasured herequantized by bartowski
    3.2 GiB
  • hf.co/QuantFactory/Llama-3.2-3B-Instruct-abliterated-GGUF:Q8_0Q8_0ollamaderived by QuantFactory
    3.2 GiB
  • hf.co/bartowski/Llama-3.2-3B-Instruct-uncensored-GGUF:Q8_0Q8_0ollamaderived by bartowski
    3.6 GiB
  • RedHatAI/Llama-3.2-3B-Instruct-FP8-dynamicFP8vllmquantized by RedHatAI
    4.1 GiB
  • hf.co/leafspark/Llama-3.2-11B-Vision-Instruct-GGUF:Q4_K_MQ4_K_Mollamaquantized by leafspark
    5.6 GiB
  • unsloth/Llama-3.2-3B-InstructBF16vllmderived by unsloth
    6.0 GiB
  • hf.co/bartowski/Llama-3.2-3B-Instruct-GGUF:F16F16ollamameasured herequantized by bartowski
    6.0 GiB
  • hf.co/bartowski/Llama-3.2-3B-Instruct-uncensored-GGUF:F16F16ollamaderived by bartowski
    6.7 GiB
  • hf.co/leafspark/Llama-3.2-11B-Vision-Instruct-GGUF:Q8_0Q8_0ollamaquantized by leafspark
    9.7 GiB
  • mlx-community/Llama-3.2-11B-Vision-Instruct-8bitBF16mlxderived by mlx-community
    10.6 GiB
  • hf.co/leafspark/Llama-3.2-11B-Vision-Instruct-GGUF:F16F16ollamaquantized by leafspark
    18.2 GiB
  • mlx-community/Llama-3.2-11B-Vision-Instruct-abliteratedBF16mlxderived by mlx-community
    19.9 GiB
  • mlx-community/Llama-3.2-90B-Vision-Instruct-4bitBF16mlxderived by mlx-community
    46.4 GiB

Sizes are what the catalog declares, not what a machine measured — fitting on disk is necessary and not sufficient. Nobody here has run these on your machine, and this narrows the candidates rather than certifying one.

the same builds, by member
Llama 3.2 1B1.2B
hf.co/MaziyarPanahi/Llama-3.2-1B-Instruct-GGUF:IQ1_SIQ1_Sollama375 MiB on diskquantized by MaziyarPanahi
hf.co/bartowski/Llama-3.2-1B-Instruct-GGUF:IQ3_MIQ3_Mollama626 MiB on diskquantized by bartowski
hf.co/bartowski/Llama-3.2-1B-Instruct-GGUF:Q3_K_LQ3_K_Lollama698 MiB on diskquantized by bartowski
hf.co/bartowski/Llama-3.2-1B-Instruct-GGUF:Q4_0_8_8Q4_0_8_8ollama735 MiB on diskquantized by bartowski
hf.co/bartowski/Llama-3.2-1B-Instruct-GGUF:Q4_0_4_4Q4_0_4_4ollama735 MiB on diskquantized by bartowski
hf.co/bartowski/Llama-3.2-1B-Instruct-GGUF:Q4_K_MQ4_K_Mollama770 MiB on diskquantized by bartowski
mobilint/Llama-3.2-1B-InstructBF16vllm1002 MiB on diskquantized by mobilint
hf.co/bartowski/Llama-3.2-1B-Instruct-GGUF:Q8_0Q8_0ollama1.2 GiB on diskquantized by bartowski
RedHatAI/Llama-3.2-1B-Instruct-FP8-dynamicFP8vllm1.9 GiB on diskquantized by RedHatAI
hf.co/bartowski/Llama-3.2-1B-Instruct-GGUF:F16F16ollama2.3 GiB on diskquantized by bartowski
Llama-3.2-1B-Instruct-Q4_K_M-GGUF
hf.co/hugging-quants/Llama-3.2-1B-Instruct-Q4_K_M-GGUF:Q4_K_MQ4_K_Mollama770 MiB on diskderived by hugging-quants
Llama-3.2-1B-Instruct-bf16
mlx-community/Llama-3.2-1B-Instruct-4bit4BITmlx663 MiB on diskderived by mlx-community
mlx-community/Llama-3.2-1B-Instruct-bf16BF16mlx2.3 GiB on diskderived by mlx-community
Llama-3.2-1B-Instruct-LinkLlama-Cap50
THGLab/Llama-3.2-1B-Instruct-LinkLlama-Cap50BF16vllm2.3 GiB on diskderived by THGLab
Llama-3.2-1B-Instruct
unsloth/Llama-3.2-1B-Instruct-unsloth-bnb-4bitBITSANDBYTESvllm1.0 GiB on diskderived by unsloth
unsloth/Llama-3.2-1B-InstructBF16vllm2.3 GiB on diskderived by unsloth
Llama 3.2 3B3.2B
hf.co/unsloth/Llama-3.2-3B-Instruct-GGUF:IQ1_SIQ1_Sollama870 MiB on diskquantized by unsloth
hf.co/bartowski/Llama-3.2-3B-Instruct-GGUF:IQ3_MIQ3_Mollama1.5 GiB on diskquantized by bartowski
hf.co/bartowski/Llama-3.2-3B-Instruct-GGUF:Q3_K_LQ3_K_Lollama1.7 GiB on diskquantized by bartowski
hf.co/bartowski/Llama-3.2-3B-Instruct-GGUF:Q4_0_4_4Q4_0_4_4ollama1.8 GiB on diskquantized by bartowski
hf.co/bartowski/Llama-3.2-3B-Instruct-GGUF:Q4_0_8_8Q4_0_8_8ollama1.8 GiB on diskquantized by bartowski
hf.co/bartowski/Llama-3.2-3B-Instruct-GGUF:Q4_K_MQ4_K_Mollama1.9 GiB on diskquantized by bartowski
hf.co/bartowski/Llama-3.2-3B-Instruct-GGUF:Q8_0Q8_0ollama3.2 GiB on diskquantized by bartowski
RedHatAI/Llama-3.2-3B-Instruct-FP8-dynamicFP8vllm4.1 GiB on diskquantized by RedHatAI
hf.co/bartowski/Llama-3.2-3B-Instruct-GGUF:F16F16ollama6.0 GiB on diskquantized by bartowski
Llama-3.2-3B-Instruct-uncensored
hf.co/bartowski/Llama-3.2-3B-Instruct-uncensored-GGUF:Q2_KQ2_Kollama1.4 GiB on diskderived by bartowski
hf.co/bartowski/Llama-3.2-3B-Instruct-uncensored-GGUF:IQ3_XSIQ3_XSollama1.5 GiB on diskderived by bartowski
hf.co/bartowski/Llama-3.2-3B-Instruct-uncensored-GGUF:Q3_K_LQ3_K_Lollama1.8 GiB on diskderived by bartowski
hf.co/bartowski/Llama-3.2-3B-Instruct-uncensored-GGUF:Q4_0_4_8Q4_0_4_8ollama2.0 GiB on diskderived by bartowski
hf.co/bartowski/Llama-3.2-3B-Instruct-uncensored-GGUF:Q4_0_8_8Q4_0_8_8ollama2.0 GiB on diskderived by bartowski
hf.co/bartowski/Llama-3.2-3B-Instruct-uncensored-GGUF:Q4_K_MQ4_K_Mollama2.1 GiB on diskderived by bartowski
mlx-community/Llama-3.2-3B-Instruct-uncensored-6bit6BITmlx2.4 GiB on diskderived by mlx-community
hf.co/bartowski/Llama-3.2-3B-Instruct-uncensored-GGUF:Q8_0Q8_0ollama3.6 GiB on diskderived by bartowski
hf.co/bartowski/Llama-3.2-3B-Instruct-uncensored-GGUF:F16F16ollama6.7 GiB on diskderived by bartowski
Llama-3.2-3B-Instruct-Q4_K_M-GGUF
hf.co/hugging-quants/Llama-3.2-3B-Instruct-Q4_K_M-GGUF:Q4_K_MQ4_K_Mollama1.9 GiB on diskderived by hugging-quants
Llama-3.2-3B-Instruct
mlx-community/Llama-3.2-3B-Instruct-4bit4BITmlx1.7 GiB on diskderived by mlx-community
mlx-community/Llama-3.2-3B-Instruct-8bitBF16mlx3.2 GiB on diskderived by mlx-community
Llama-3.2-3B-Instruct-abliterated-GGUF
hf.co/QuantFactory/Llama-3.2-3B-Instruct-abliterated-GGUF:Q2_KQ2_Kollama1.3 GiB on diskderived by QuantFactory
hf.co/QuantFactory/Llama-3.2-3B-Instruct-abliterated-GGUF:Q3_K_SQ3_K_Sollama1.4 GiB on diskderived by QuantFactory
hf.co/QuantFactory/Llama-3.2-3B-Instruct-abliterated-GGUF:Q3_K_LQ3_K_Lollama1.7 GiB on diskderived by QuantFactory
hf.co/QuantFactory/Llama-3.2-3B-Instruct-abliterated-GGUF:Q4_0Q4_0ollama1.8 GiB on diskderived by QuantFactory
hf.co/QuantFactory/Llama-3.2-3B-Instruct-abliterated-GGUF:Q4_K_MQ4_K_Mollama1.9 GiB on diskderived by QuantFactory
hf.co/QuantFactory/Llama-3.2-3B-Instruct-abliterated-GGUF:Q8_0Q8_0ollama3.2 GiB on diskderived by QuantFactory
Llama-3.2-3B-Instruct
unsloth/Llama-3.2-3B-Instruct-unsloth-bnb-4bitBITSANDBYTESvllm2.2 GiB on diskderived by unsloth
unsloth/Llama-3.2-3B-InstructBF16vllm6.0 GiB on diskderived by unsloth
Llama 3.2 VISION-11B
hf.co/leafspark/Llama-3.2-11B-Vision-Instruct-GGUF:Q4_K_MQ4_K_Mollama5.6 GiB on diskquantized by leafspark
hf.co/leafspark/Llama-3.2-11B-Vision-Instruct-GGUF:Q8_0Q8_0ollama9.7 GiB on diskquantized by leafspark
hf.co/leafspark/Llama-3.2-11B-Vision-Instruct-GGUF:F16F16ollama18.2 GiB on diskquantized by leafspark
Llama-3.2-11B-Vision-Instruct-8bit
mlx-community/Llama-3.2-11B-Vision-Instruct-8bitBF16mlx10.6 GiB on diskderived by mlx-community
Llama-3.2-11B-Vision-Instruct-abliterated
mlx-community/Llama-3.2-11B-Vision-Instruct-abliteratedBF16mlx19.9 GiB on diskderived by mlx-community
Llama-3.2-90B-Vision-Instruct-4bit
mlx-community/Llama-3.2-90B-Vision-Instruct-4bitBF16mlx46.4 GiB on diskderived by mlx-community
ask your own gram

Your concierge can answer this from the network rather than from this page. The ask carries the operator id, so it resolves to a capability and an engine — not to a name somebody has to recognise.

What has this network measured about the Llama 3.2 family (epn.family.llama-3-2), and can my gram run any of it? See /inferences/llama-3-2

open a gramx with this ask →epn.family.llama-3-2