model family

Gemma 4

Published by Google. 10 members have been measured on real machines. 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
image + text → texttext → 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.

10 of 53 builds measured · 43 still open
what each build proved
e2b · Q4_K_M · ollama · Tool calling — provede2b · Q4_K_M · ollama · Tool loop finished — provede2b · Q4_K_M · ollama · Faithful to tool results — provede2b · Q4_K_M · ollama · Chained tool calls — provede2b · Q4_K_M · ollama · Structured output — provede2b · Q4_K_M · ollama · Sustained output — provede2b · Q4_K_M · ollama · Extended thinking — provede2b · Q4_K_M · ollama · Vision — provede2b · Q4_K_M · ollama · Counts in images — provede2b · Q4_K_M · ollama · Multiple images at once — provede2b · Q4_K_M · ollama · Spatial reasoning — provede2b · Q4_K_M · ollama · Writes code — provede2b · Q4_K_M · ollama · Reasons about code — provede2b · Q4_K_M · ollama · Synthesises sources — provede2b · Q4_K_M · ollama · Follows instructions — provede2b · Q3_K_M · Tool calling — provede2b · Q3_K_M · Tool loop finished — provede2b · Q3_K_M · Faithful to tool results — provede2b · Q3_K_M · Chained tool calls — provede2b · Q3_K_M · Structured output — provede2b · Q3_K_M · Sustained output — provede2b · Q3_K_M · Extended thinking — provede2b · Q3_K_M · Vision — provede2b · Q3_K_M · Counts in images — provede2b · Q3_K_M · Multiple images at once — provede2b · Q3_K_M · Spatial reasoning — provede2b · Q3_K_M · Writes code — provede2b · Q3_K_M · Reasons about code — provede2b · Q3_K_M · Synthesises sources — provede2b · Q3_K_M · Follows instructions — provede2b · Q4_K_M · unsloth · Tool calling — provede2b · Q4_K_M · unsloth · Tool loop finished — provede2b · Q4_K_M · unsloth · Faithful to tool results — provede2b · Q4_K_M · unsloth · Chained tool calls — provede2b · Q4_K_M · unsloth · Structured output — provede2b · Q4_K_M · unsloth · Sustained output — provede2b · Q4_K_M · unsloth · Extended thinking — provede2b · Q4_K_M · unsloth · Vision — provede2b · Q4_K_M · unsloth · Counts in images — provede2b · Q4_K_M · unsloth · Multiple images at once — provede2b · Q4_K_M · unsloth · Spatial reasoning — provede2b · Q4_K_M · unsloth · Writes code — provede2b · Q4_K_M · unsloth · Reasons about code — provede2b · Q4_K_M · unsloth · Synthesises sources — provede2b · Q4_K_M · unsloth · Follows instructions — provede2b · IQ4_NL · Tool calling — provede2b · IQ4_NL · Tool loop finished — provede2b · IQ4_NL · Faithful to tool results — provede2b · IQ4_NL · Chained tool calls — provede2b · IQ4_NL · Structured output — provede2b · IQ4_NL · Sustained output — provede2b · IQ4_NL · Extended thinking — provede2b · IQ4_NL · Vision — provede2b · IQ4_NL · Counts in images — provede2b · IQ4_NL · Multiple images at once — provede2b · IQ4_NL · Spatial reasoning — provede2b · IQ4_NL · Writes code — provede2b · IQ4_NL · Reasons about code — provede2b · IQ4_NL · Synthesises sources — provede2b · IQ4_NL · Follows instructions — provede2b · Q4_0 · Tool calling — provede2b · Q4_0 · Tool loop finished — provede2b · Q4_0 · Faithful to tool results — provede2b · Q4_0 · Chained tool calls — provede2b · Q4_0 · Structured output — provede2b · Q4_0 · Sustained output — provede2b · Q4_0 · Extended thinking — provede2b · Q4_0 · Vision — provede2b · Q4_0 · Counts in images — provede2b · Q4_0 · Multiple images at once — provede2b · Q4_0 · Spatial reasoning — provede2b · Q4_0 · Writes code — provede2b · Q4_0 · Reasons about code — provede2b · Q4_0 · Synthesises sources — provede2b · Q4_0 · Follows instructions — provede2b · Q3_K_S · Tool calling — provede2b · Q3_K_S · Tool loop finished — asked, failede2b · Q3_K_S · Faithful to tool results — provede2b · Q3_K_S · Chained tool calls — provede2b · Q3_K_S · Structured output — provede2b · Q3_K_S · Sustained output — provede2b · Q3_K_S · Extended thinking — provede2b · Q3_K_S · Vision — provede2b · Q3_K_S · Counts in images — provede2b · Q3_K_S · Multiple images at once — provede2b · Q3_K_S · Spatial reasoning — provede2b · Q3_K_S · Writes code — provede2b · Q3_K_S · Reasons about code — provede2b · Q3_K_S · Synthesises sources — provede2b · Q3_K_S · Follows instructions — provede4b · Q3_K_M · Tool calling — provede4b · Q3_K_M · Tool loop finished — provede4b · Q3_K_M · Faithful to tool results — provede4b · Q3_K_M · Chained tool calls — provede4b · Q3_K_M · Structured output — provede4b · Q3_K_M · Sustained output — provede4b · Q3_K_M · Extended thinking — provede4b · Q3_K_M · Vision — provede4b · Q3_K_M · Counts in images — provede4b · Q3_K_M · Multiple images at once — provede4b · Q3_K_M · Spatial reasoning — provede4b · Q3_K_M · Writes code — provede4b · Q3_K_M · Reasons about code — provede4b · Q3_K_M · Synthesises sources — provede4b · Q3_K_M · Follows instructions — provede2b · e2b-it-qat · Tool calling — never askede2b · e2b-it-qat · Tool loop finished — never askede2b · e2b-it-qat · Faithful to tool results — never askede2b · e2b-it-qat · Chained tool calls — never askede2b · e2b-it-qat · Structured output — never askede2b · e2b-it-qat · Sustained output — never askede2b · e2b-it-qat · Extended thinking — never askede2b · e2b-it-qat · Vision — never askede2b · e2b-it-qat · Counts in images — never askede2b · e2b-it-qat · Multiple images at once — never askede2b · e2b-it-qat · Spatial reasoning — never askede2b · e2b-it-qat · Writes code — never askede2b · e2b-it-qat · Reasons about code — never askede2b · e2b-it-qat · Synthesises sources — never askede2b · e2b-it-qat · Follows instructions — never askede4b · e4b-it-qat · Tool calling — never askede4b · e4b-it-qat · Tool loop finished — never askede4b · e4b-it-qat · Faithful to tool results — never askede4b · e4b-it-qat · Chained tool calls — never askede4b · e4b-it-qat · Structured output — never askede4b · e4b-it-qat · Sustained output — never askede4b · e4b-it-qat · Extended thinking — never askede4b · e4b-it-qat · Vision — never askede4b · e4b-it-qat · Counts in images — never askede4b · e4b-it-qat · Multiple images at once — never askede4b · e4b-it-qat · Spatial reasoning — never askede4b · e4b-it-qat · Writes code — never askede4b · e4b-it-qat · Reasons about code — never askede4b · e4b-it-qat · Synthesises sources — never askede4b · e4b-it-qat · Follows instructions — never askede2b · Tool calling — never askede2b · Tool loop finished — never askede2b · Faithful to tool results — never askede2b · Chained tool calls — never askede2b · Structured output — never askede2b · Sustained output — never askede2b · Extended thinking — never askede2b · Vision — never askede2b · Counts in images — never askede2b · Multiple images at once — never askede2b · Spatial reasoning — never askede2b · Writes code — never askede2b · Reasons about code — never askede2b · Synthesises sources — never askede2b · Follows instructions — never asked
Tool calling
Tool loop finished
Faithful to tool results
Chained tool calls
Structured output
Sustained output
Extended thinking
Vision
Counts in images
Multiple images at once
Spatial reasoning
Writes code
Reasons about code
Synthesises sources
Follows instructions
gemma4:e2be2b · Q4_K_M · 5 machines · 5.1B
8,192recalled
32,768served
45.1best tok/s
43.3 tok/s · unnamed machine19.3 tok/s · unnamed machine8.9 tok/s · x86 · CPU · Hyderabad7.7 tok/s · unnamed machine4.1 tok/s · unnamed machine
4.143.3 tok/s across 5 machines · ×10.7 spreadunnamed machinex86 · CPU
recalled 8k▲ served 32k⌐ declared 128k · unsignedadvertises 16× what it proved
hf.co/unsloth/gemma-4-E2B-it-GGUF:Q3_K_Me2b · Q3_K_M · 3 machines · 4.65B
8,192recalled
served
38.4best tok/s
38.4 tok/s · unnamed machine14.2 tok/s · unnamed machine2.8 tok/s · unnamed machine
2.838.4 tok/s across 3 machines · ×13.8 spreadunnamed machine
recalled 8k⌐ declared 128k · unsignedadvertises 16× what it proved
hf.co/unsloth/gemma-4-E2B-it-GGUF:Q4_K_Me2b · Q4_K_M · 3 machines · 4.65B
8,192recalled
8,192served
164.7best tok/s
97.9 tok/s · NVIDIA · Bhubaneswar6.4 tok/s · unnamed machine3.9 tok/s · unnamed machine
3.997.9 tok/s across 3 machines · ×25.4 spreadNVIDIAunnamed machine
recalled 8k⌐ declared 128k · unsignedadvertises 16× what it proved
hf.co/unsloth/gemma-4-E2B-it-GGUF:IQ4_NLe2b · IQ4_NL · 2 machines · 4.65B
8,192recalled
served
54.9best tok/s
54.9 tok/s · unnamed machine10.0 tok/s · unnamed machine
10.054.9 tok/s across 2 machines · ×5.5 spreadunnamed machine
recalled 8k⌐ declared 128k · unsignedadvertises 16× what it proved
hf.co/unsloth/gemma-4-E2B-it-GGUF:Q4_0e2b · Q4_0 · 2 machines · 4.65B
4,096recalled
served
57.6best tok/s
57.6 tok/s · unnamed machine9.1 tok/s · unnamed machine
9.157.6 tok/s across 2 machines · ×6.3 spreadunnamed machine
recalled 4k⌐ declared 128k · unsignedadvertises 32× what it proved

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

36 of 53 builds fit a 16 GB machine — budgeting 70% of it, or 11.2 GiB, because the cache and the runtime want the rest. 2 of them use a signed resident size a machine actually held; the rest are declared file sizes.

  • hf.co/unsloth/gemma-4-E2B-it-GGUF:IQ2_MIQ2_Mollamaquantized by unsloth
    2.1 GiB
  • hf.co/unsloth/gemma-4-E2B-it-GGUF:IQ3_XXSIQ3_XXSollamaquantized by unsloth
    2.2 GiB
  • hf.co/unsloth/gemma-4-E2B-it-GGUF:IQ4_XSIQ4_XSollamaquantized by unsloth
    2.8 GiB
  • mlx-community/gemma-4-E2B-it-4bit4bitmlxquantized by mlx-community
    2.8 GiB
  • hf.co/unsloth/gemma-4-E2B-it-GGUF:Q4_0Q4_0ollamameasured herequantized by unsloth
    2.8 GiB
  • hf.co/unsloth/gemma-4-E4B-it-qat-GGUF:Q2_K_XLQ2_K_XLollamaquantized by unsloth
    3.0 GiB
  • unsloth/gemma-4-E2B-it-GGUF:gemma-4-E2B-it-Q4_K_M.ggufQ4_K_Mllamacppquantized by unsloth
    3.8 GiB
  • lmstudio-community/gemma-4-E2B-it-MLX-4bit4BITmlxquantized by lmstudio-community
    4.0 GiB
  • hf.co/ggml-org/gemma-4-E4B-it-GGUF:Q4_0Q4_0ollamaquantized by ggml-org
    4.3 GiB
  • mlx-community/gemma-4-E4B-it-4bit4bitmlxquantized by mlx-community
    4.5 GiB
  • hf.co/unsloth/gemma-4-E2B-it-GGUF:Q8_0Q8_0ollamaquantized by unsloth
    4.7 GiB
  • lmstudio-community/gemma-4-E2B-it-MLX-6bit6BITmlxquantized by lmstudio-community
    4.8 GiB
  • hf.co/lmstudio-community/gemma-4-E4B-it-GGUF:Q4_K_MQ4_K_Mollamaquantized by lmstudio-community
    5.0 GiB
  • hf.co/unsloth/gemma-4-E2B-it-GGUF:Q4_K_MQ4_K_Mollamaresident · signedquantized by unsloth
    5.0 GiB
  • lmstudio-community/gemma-4-E2B-it-MLX-8bit8BITmlxquantized by lmstudio-community
    5.5 GiB
  • hf.co/yuxinlu1/gemma-4-12B-agentic-fable5-composer2.5-v2-3.5x-tau2-GGUF:Q3_K_MQ3_K_Mollamaderived by yuxinlu1
    5.7 GiB
  • lmstudio-community/gemma-4-12B-it-MLX-4bit4BITmlxquantized by lmstudio-community
    6.3 GiB
  • lmstudio-community/gemma-4-E4B-it-MLX-4bit4BITmlxquantized by lmstudio-community
    6.4 GiB
  • hf.co/google/gemma-4-12B-it-qat-q4_0-gguf:Q4_0Q4_0ollamapublished by google
    6.5 GiB
  • mlx-community/gemma-4-12b-it-4bit4bitmlxquantized by mlx-community
    6.8 GiB
  • lmstudio-community/gemma-4-E4B-it-MLX-5bit5BITmlxquantized by lmstudio-community
    6.9 GiB
  • hf.co/yuxinlu1/gemma-4-12B-agentic-fable5-composer2.5-v2-3.5x-tau2-GGUF:Q4_K_MQ4_K_Mollamaderived by yuxinlu1
    6.9 GiB
  • hf.co/unsloth/gemma-4-12B-it-qat-GGUF:Q4_K_MQ4_K_Mollamaquantized by unsloth
    7.2 GiB
  • hf.co/ggml-org/gemma-4-E4B-it-GGUF:Q8_0Q8_0ollamaquantized by ggml-org
    7.5 GiB
  • google/gemma-4-E2B-it-qat-w4a16-ctW4A16vllmpublished by google
    7.8 GiB
  • lmstudio-community/gemma-4-E4B-it-MLX-8bit8BITmlxquantized by lmstudio-community
    8.3 GiB
  • hf.co/unsloth/gemma-4-E2B-it-GGUF:BF16BF16ollamaquantized by unsloth
    8.7 GiB
  • lmstudio-community/gemma-4-12B-it-MLX-6bit6BITmlxquantized by lmstudio-community
    9.1 GiB
  • hf.co/yuxinlu1/gemma-4-12B-agentic-fable5-composer2.5-v2-3.5x-tau2-GGUF:Q6_KQ6_Kollamaderived by yuxinlu1
    9.1 GiB
  • hf.co/unsloth/gemma-4-26B-A4B-it-GGUF:IQ2_XXSIQ2_XXSollamaquantized by unsloth
    9.2 GiB
  • hf.co/unsloth/gemma-4-26B-A4B-it-GGUF:IQ2_MIQ2_Mollamaquantized by unsloth
    9.3 GiB
  • google/gemma-4-E2B-itBF16vllmpublished by google
    9.5 GiB
  • google/gemma-4-12B-it-qat-w4a16-ctW4A16vllmpublished by google
    9.6 GiB
  • gemma4:e2bQ4_K_Mollamaresident · signedpublished by google
    10.2 GiB
  • hf.co/unsloth/gemma-4-26B-A4B-it-GGUF:IQ3_XXSIQ3_XXSollamaquantized by unsloth
    10.6 GiB
  • gemma4:e4bQ4_K_Mollamapublished by google
    10.7 GiB
  • hf.co/yuxinlu1/gemma-4-12B-agentic-fable5-composer2.5-v2-3.5x-tau2-GGUF:Q8_0Q8_0ollamaderived by yuxinlu1
    11.8 GiB
  • lmstudio-community/gemma-4-12B-it-MLX-8bit8BITmlxquantized by lmstudio-community
    11.8 GiB
  • hf.co/unsloth/gemma-4-26B-A4B-it-qat-GGUF:Q4_K_XLQ4_K_XLollamaquantized by unsloth
    13.3 GiB
  • hf.co/ggml-org/gemma-4-E4B-it-GGUF:BF16BF16ollamaquantized by ggml-org
    14.0 GiB
  • lmstudio-community/gemma-4-26B-A4B-it-QAT-MLX-4bit4BITmlxquantized by lmstudio-community
    14.5 GiB
  • google/gemma-4-E4B-itBF16vllmpublished by google
    14.9 GiB
  • hf.co/unsloth/gemma-4-26B-A4B-it-GGUF:Q4_K_MQ4_K_Mollamaquantized by unsloth
    15.8 GiB
  • cyankiwi/gemma-4-26B-A4B-it-AWQ-4bitW4A16vllmquantized by cyankiwi
    16.0 GiB
  • hf.co/unsloth/gemma-4-31B-it-qat-GGUF:Q4_K_XLQ4_K_XLollamaquantized by unsloth
    16.1 GiB
  • nvidia/Gemma-4-26B-A4B-NVFP4NVFP4vllmquantized by nvidia
    17.5 GiB
  • google/gemma-4-31B-it-qat-w4a16-ctW4A16vllmpublished by google
    21.7 GiB
  • google/gemma-4-12B-itBF16vllmpublished by google
    22.3 GiB
  • hf.co/unsloth/gemma-4-26B-A4B-it-GGUF:Q8_0Q8_0ollamaquantized by unsloth
    25.0 GiB
  • RedHatAI/gemma-4-26B-A4B-it-FP8-dynamicFP8vllmquantized by RedHatAI
    26.7 GiB
  • nvidia/Gemma-4-31B-IT-NVFP4NVFP4vllmquantized by nvidia
    30.4 GiB
  • google/gemma-4-26B-A4B-itBF16vllmpublished by google
    48.1 GiB
  • google/gemma-4-31B-itBF16vllmpublished by google
    58.3 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
Gemma 4 12B12B
lmstudio-community/gemma-4-12B-it-MLX-4bit4BITmlx6.3 GiB on diskquantized by lmstudio-community
hf.co/google/gemma-4-12B-it-qat-q4_0-gguf:Q4_0Q4_0ollama6.5 GiB on diskpublished by google
mlx-community/gemma-4-12b-it-4bit4bitmlx6.8 GiB on diskquantized by mlx-community
hf.co/unsloth/gemma-4-12B-it-qat-GGUF:Q4_K_MQ4_K_Mollama7.2 GiB on diskquantized by unsloth
lmstudio-community/gemma-4-12B-it-MLX-6bit6BITmlx9.1 GiB on diskquantized by lmstudio-community
google/gemma-4-12B-it-qat-w4a16-ctW4A16vllm9.6 GiB on diskpublished by google
lmstudio-community/gemma-4-12B-it-MLX-8bit8BITmlx11.8 GiB on diskquantized by lmstudio-community
google/gemma-4-12B-itBF16vllm22.3 GiB on diskpublished by google
Gemma 4 12B · yuxinlu1
hf.co/yuxinlu1/gemma-4-12B-agentic-fable5-composer2.5-v2-3.5x-tau2-GGUF:Q3_K_MQ3_K_Mollama5.7 GiB on diskderived by yuxinlu1
hf.co/yuxinlu1/gemma-4-12B-agentic-fable5-composer2.5-v2-3.5x-tau2-GGUF:Q4_K_MQ4_K_Mollama6.9 GiB on diskderived by yuxinlu1
hf.co/yuxinlu1/gemma-4-12B-agentic-fable5-composer2.5-v2-3.5x-tau2-GGUF:Q6_KQ6_Kollama9.1 GiB on diskderived by yuxinlu1
hf.co/yuxinlu1/gemma-4-12B-agentic-fable5-composer2.5-v2-3.5x-tau2-GGUF:Q8_0Q8_0ollama11.8 GiB on diskderived by yuxinlu1
Gemma 4 26B-A4B
hf.co/unsloth/gemma-4-26B-A4B-it-GGUF:IQ2_XXSIQ2_XXSollama9.2 GiB on diskquantized by unsloth
hf.co/unsloth/gemma-4-26B-A4B-it-GGUF:IQ2_MIQ2_Mollama9.3 GiB on diskquantized by unsloth
hf.co/unsloth/gemma-4-26B-A4B-it-GGUF:IQ3_XXSIQ3_XXSollama10.6 GiB on diskquantized by unsloth
hf.co/unsloth/gemma-4-26B-A4B-it-qat-GGUF:Q4_K_XLQ4_K_XLollama13.3 GiB on diskquantized by unsloth
lmstudio-community/gemma-4-26B-A4B-it-QAT-MLX-4bit4BITmlx14.5 GiB on diskquantized by lmstudio-community
hf.co/unsloth/gemma-4-26B-A4B-it-GGUF:Q4_K_MQ4_K_Mollama15.8 GiB on diskquantized by unsloth
cyankiwi/gemma-4-26B-A4B-it-AWQ-4bitW4A16vllm16.0 GiB on diskquantized by cyankiwi
nvidia/Gemma-4-26B-A4B-NVFP4NVFP4vllm17.5 GiB on diskquantized by nvidia
hf.co/unsloth/gemma-4-26B-A4B-it-GGUF:Q8_0Q8_0ollama25.0 GiB on diskquantized by unsloth
RedHatAI/gemma-4-26B-A4B-it-FP8-dynamicFP8vllm26.7 GiB on diskquantized by RedHatAI
google/gemma-4-26B-A4B-itBF16vllm48.1 GiB on diskpublished by google
Gemma 4 31B
hf.co/unsloth/gemma-4-31B-it-qat-GGUF:Q4_K_XLQ4_K_XLollama16.1 GiB on diskquantized by unsloth
google/gemma-4-31B-it-qat-w4a16-ctW4A16vllm21.7 GiB on diskpublished by google
nvidia/Gemma-4-31B-IT-NVFP4NVFP4vllm30.4 GiB on diskquantized by nvidia
google/gemma-4-31B-itBF16vllm58.3 GiB on diskpublished by google
Gemma 4 E2B5.1B
hf.co/unsloth/gemma-4-E2B-it-GGUF:IQ2_MIQ2_Mollama2.1 GiB on diskquantized by unsloth
hf.co/unsloth/gemma-4-E2B-it-GGUF:IQ3_XXSIQ3_XXSollama2.2 GiB on diskquantized by unsloth
hf.co/unsloth/gemma-4-E2B-it-GGUF:IQ4_XSIQ4_XSollama2.8 GiB on diskquantized by unsloth
mlx-community/gemma-4-E2B-it-4bit4bitmlx2.8 GiB on diskquantized by mlx-community
hf.co/unsloth/gemma-4-E2B-it-GGUF:Q4_0Q4_0ollama2.8 GiB on diskquantized by unsloth
hf.co/unsloth/gemma-4-E2B-it-GGUF:Q4_K_MQ4_K_Mollama3.8 GiB on diskquantized by unsloth
unsloth/gemma-4-E2B-it-GGUF:gemma-4-E2B-it-Q4_K_M.ggufQ4_K_Mllamacpp3.8 GiB on diskquantized by unsloth
lmstudio-community/gemma-4-E2B-it-MLX-4bit4BITmlx4.0 GiB on diskquantized by lmstudio-community
hf.co/unsloth/gemma-4-E2B-it-GGUF:Q8_0Q8_0ollama4.7 GiB on diskquantized by unsloth
lmstudio-community/gemma-4-E2B-it-MLX-6bit6BITmlx4.8 GiB on diskquantized by lmstudio-community
lmstudio-community/gemma-4-E2B-it-MLX-8bit8BITmlx5.5 GiB on diskquantized by lmstudio-community
gemma4:e2bQ4_K_Mollama7.0 GiB on diskpublished by google
google/gemma-4-E2B-it-qat-w4a16-ctW4A16vllm7.8 GiB on diskpublished by google
hf.co/unsloth/gemma-4-E2B-it-GGUF:BF16BF16ollama8.7 GiB on diskquantized by unsloth
google/gemma-4-E2B-itBF16vllm9.5 GiB on diskpublished by google
Gemma 4 E4B8B
hf.co/unsloth/gemma-4-E4B-it-qat-GGUF:Q2_K_XLQ2_K_XLollama3.0 GiB on diskquantized by unsloth
hf.co/ggml-org/gemma-4-E4B-it-GGUF:Q4_0Q4_0ollama4.3 GiB on diskquantized by ggml-org
mlx-community/gemma-4-E4B-it-4bit4bitmlx4.5 GiB on diskquantized by mlx-community
hf.co/lmstudio-community/gemma-4-E4B-it-GGUF:Q4_K_MQ4_K_Mollama5.0 GiB on diskquantized by lmstudio-community
lmstudio-community/gemma-4-E4B-it-MLX-4bit4BITmlx6.4 GiB on diskquantized by lmstudio-community
lmstudio-community/gemma-4-E4B-it-MLX-5bit5BITmlx6.9 GiB on diskquantized by lmstudio-community
hf.co/ggml-org/gemma-4-E4B-it-GGUF:Q8_0Q8_0ollama7.5 GiB on diskquantized by ggml-org
lmstudio-community/gemma-4-E4B-it-MLX-8bit8BITmlx8.3 GiB on diskquantized by lmstudio-community
gemma4:e4bQ4_K_Mollama10.7 GiB on diskpublished by google
hf.co/ggml-org/gemma-4-E4B-it-GGUF:BF16BF16ollama14.0 GiB on diskquantized by ggml-org
google/gemma-4-E4B-itBF16vllm14.9 GiB on diskpublished by google
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 Gemma 4 family (epn.family.gemma-4), and can my gram run any of it? See /inferences/gemma-4

open a gramx with this ask →epn.family.gemma-4