/inference/hf.co-bartowski-krutrim-ai-labs_krutrim-2-instruct-gguf-q4_k_m

hf.co/bartowski/krutrim-ai-labs_Krutrim-2-instruct-GGUF:Q4_K_M

Measured by 2 nodes on hardware we do not own, and signed by each of them. What machines here actually proved — never what the card claims.

matrix built 20 Oct 2026 · every field verified against the signature of the node that produced it, and re-verifiable by you: each signed figure carries the exact bytes the node signed (signing_payload_b64) and the signature over them, and the ed25519 public key is embedded in node_did. effective_ctx is the context length a node PROVED by recall, never the length a model card advertises
context declared10,24,000what the runtime reported. A node attests it was told this; nobody attests it is true.
context proved by recall65,536the largest size at which a machine could still find tokens planted across the whole prompt — start, middle and end, all of which had to come back.
Advertises 15.6× the context any machine here could make it use.Not an accusation — it is what happened here, and it is signed.
recalled 64k⌐ declared 1000k · unsignedadvertises 16× what it proved
every machine that timed it
13.6 tok/s · unnamed machine3.7 tok/s · unnamed machine
3.7 → 13.6 tok/s across 2 machines · ×3.6 spreadunnamed machine

Languages, proved

BengaliEnglishGujaratiKannadaMalayalamMarathiPunjabiTamilTelugu

Each question was put entirely in its own language and script, and the answer had to be right. A model with no coverage cannot parse the question, so answering in English is a failure here, not a pass. 9 proved of 10 asked — a language absent from the probe set was never asked, and is not a claim either way.

Capabilities, measured

Reasons about codeprobed, and failed
Asked to predict exactly what a short program prints. This is the half of coding that matters for agent work and that writing valid syntax does not demonstrate: following state through control flow.
Writes codepassed
Asked for a specific function and checked with the Go compiler’s own parser. Nothing is executed — running model-written code to score a model would be a security hole opened for a metric — but syntactic validity is a fact rather than an opinion.
Embeddingsprobed, and failed
The engine was asked for an embedding of a short text and returned a real, non-zero vector.
Follows instructionspassed
Given a plain constraint on its output format and checked for exact obedience. This separates an instruct-tuned model from a base one — a base model answers fluently and ignores every instruction, which then looks like a dozen unrelated weaknesses instead of one.
Sustained outputpassed
Asked to produce a long structured answer and checked for length. A model that stops after a couple of hundred tokens cannot write a report, however capable it is otherwise.
Structured outputpassed
The ENGINE was asked to constrain decoding to a schema, and the answer conformed. This is stronger than politely asking for JSON and hoping: the grammar makes invalid output unreachable, which is what an operator actually builds on.
Extended thinkingprobed, and failed
The model emitted reasoning on the engine’s dedicated reasoning channel before answering. Read from that channel rather than by scanning the answer for tags, which is why models that reason are no longer reported as models that do not.
Synthesises sourcespassed
Given three documents with one fact split across them, and required to combine rather than quote. No single document contains the answer, so a model that retrieves without reasoning cannot pass.
Tool callingprobed, and failed
The node asked the model to call a function and checked that it called the RIGHT one with a well-formed argument — not merely that it emitted a tool name.
Visionprobed, and failed
A four-digit code was rendered into an image and the model had to read it back. A model that cannot see cannot guess four digits, and a model that can has no reason to fail — so this passes and fails for the right reason, which describing a picture never did.
Tool loop finishedprobed, and failed
Whether the conversation ENDED after the tool call, or the model kept calling until the turn budget ran out. Passing “tool calling” and failing this means the model will call a tool in production and never come back. A model chosen on the first flag alone is the reason an agent silently stops delivering work.
Audioprobed, and failed
Given audio and asked to transcribe it.
Faithful to tool resultsprobed, and failed
The model was handed a list through a tool and had to report every item back. Calling a tool and understanding its answer are different abilities: a model can produce a perfect call, receive nine items, and confidently report three.

The llama family

siblings measured on the same network — compare what each actually proved
hf.co/bartowski/Llama-3.2-3B-Instruct-GGUF:IQ3_M/inference/hf.co-bartowski-llama-3.2-3b-instruct-gguf-iq3_m
1,31,072 ctx proved1 node
hf.co/bartowski/Llama-3.2-3B-Instruct-GGUF:Q3_K_L/inference/hf.co-bartowski-llama-3.2-3b-instruct-gguf-q3_k_l
1,31,072 ctx proved1 node
hf.co/bartowski/Llama-3.2-3B-Instruct-GGUF:Q4_K_M/inference/hf.co-bartowski-llama-3.2-3b-instruct-gguf-q4_k_m
1,31,072 ctx proved1 node
llama3.2:1b/inference/llama3.2-1b
32,768 ctx proved7 nodes
hf.co/bartowski/Llama-3.2-1B-Instruct-GGUF:Q4_K_M/inference/hf.co-bartowski-llama-3.2-1b-instruct-gguf-q4_k_m
16,384 ctx proved3 nodes
hf.co/unsloth/Llama-3.2-3B-Instruct-GGUF:F16/inference/hf.co-unsloth-llama-3.2-3b-instruct-gguf-f16
16,384 ctx proved1 node
hf.co/bartowski/sarvam-1-GGUF:Q4_K_M/inference/hf.co-bartowski-sarvam-1-gguf-q4_k_m
8,192 ctx proved5 nodes
hf.co/MaziyarPanahi/Llama-3.2-1B-Instruct-GGUF:IQ3_XS/inference/hf.co-maziyarpanahi-llama-3.2-1b-instruct-gguf-iq3_xs
4,096 ctx proved3 nodes
hf.co/MaziyarPanahi/Llama-3.2-1B-Instruct-GGUF:IQ1_S/inference/hf.co-maziyarpanahi-llama-3.2-1b-instruct-gguf-iq1_s
ctx not probed3 nodes
hf.co/MaziyarPanahi/Llama-3.2-1B-Instruct-GGUF:Q4_K_M/inference/hf.co-maziyarpanahi-llama-3.2-1b-instruct-gguf-q4_k_m
ctx not probed2 nodes
hf.co/unsloth/Llama-3.2-3B-Instruct-GGUF:IQ1_S/inference/hf.co-unsloth-llama-3.2-3b-instruct-gguf-iq1_s
ctx not probed2 nodes
hf.co/bartowski/Llama-3.2-1B-Instruct-GGUF:F16/inference/hf.co-bartowski-llama-3.2-1b-instruct-gguf-f16
ctx not probed1 node
hf.co/mradermacher/Airavata-GGUF:Q4_K_M/inference/hf.co-mradermacher-airavata-gguf-q4_k_m
ctx not probed1 node
hf.co/QuantFactory/OpenHathi-7B-Hi-v0.1-Base-GGUF:Q4_K_M/inference/hf.co-quantfactory-openhathi-7b-hi-v0.1-base-gguf-q4_k_m
ctx not probed1 node
signed by this network

What machines here proved

context proved by recall65,536
peak throughput ever signed13.56 tok/s · did:epn:002408…a5be46
resident while loaded18.4 GiB (18.4 on card) · did:epn:002408…a5be46
machines that measured it2
samples behind those numbers2
regions it was proved in2
Every line traces to a node signature.
from the public record · unsigned

What the runtime says about it

context declared10,24,000
parameters12.2B
parameter count12,24,77,82,400
quantisationQ4_K_M
familyllama
formatgguf
ollama /api/show; the node attests that the runtime reported these, not that they are true. Attested by did:epn:002408…a5be46.The only unsigned block on this page. We attest we read these from the runtime — not that they are true. Nobody signs a model card.

Proven across regions

The Dalles, Oregon97058 · 1 node
Muzaffarpur, Bihar842001 · 1 node

Every machine that measured it

nothing is averaged — the machine is what you are choosing
did:epn:002408…a5be46The Dalles · 97058 · 0.40.6 · on host · 20 Oct 2026
65,536ctx provedthe model lost the needle at 128K
13.56tok/s now37 samples · 131s18.4 GiB resident · 18.4 GiB on card · 7.0 GiB on disk
✗ Reasons about code✓ Writes code✗ Embeddings✓ Follows instructions✓ Sustained output✓ Structured output✗ Extended thinking✓ Synthesises sources✗ Tool calling✗ Vision✗ Tool loop finished✗ Audio✗ Faithful to tool results✓ 9 languages
did:epn:002408…afbb8aMuzaffarpur · 842001 · 16 Oct 2026
—ctx proved
3.73tok/s nowpeak 10.27 · 1 Oct 202652 samples · 1,310s
no capability probed

Context ladders attempted: did:epn:002408…a5be46 4096,8192,16384,32768,65536,131072

Run this where your data already is

Tell us the workload, whose machines it should run on, and which jurisdiction it answers to.

Run a gramPut a machine on the network in this region; it signs its capacity into the room.Open a gramxStart your own room — an org, a community, a brand.Be invitedAccept a link from an admin to cross into the private room.