/inferences/qwen-3-5/2b/unsloth-q4_k_m-ollama

hf.co/unsloth/Qwen3.5-2B-GGUF:Q4_K_M

unsloth · Q4_K_M · on ollama · quantizer build

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 26 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 declarednot declaredwhat the runtime reported. A node attests it was told this; nobody attests it is true.
context proved by recallnot probedthe 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.
Both numbers are needed to state a gap, and one of them is missing.
every machine that timed it
8.5 tok/s · unnamed machine7.0 tok/s · x86 · CPU · Kane
7.0 → 8.5 tok/s across 2 machines · ×1.2 spreadunnamed machinex86 · CPU

Other builds of Qwen 3.5 2B

every other build of this member measured on the network — compare what each actually proved
hf.co/unsloth/Qwen3.5-2B-GGUF:Q4_0unsloth · Q4_0 · ollama
ctx not probed1 node
hf.co/unsloth/Qwen3.5-2B-GGUF:Q8_0unsloth · Q8_0 · ollama
ctx not probed1 node
signed by this network

What machines here proved

peak throughput ever signed8.61 tok/s · did:epn:002408…acbe75
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

No runtime metadata was attested for this model.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

Taipei, Taipei110 · 1 node
Kane, Iowa51503 · 1 node

Every machine that measured it

nothing is averaged — the machine is what you are choosing
did:epn:002408…acbe75Taipei · 110 · 25 Oct 2026
—ctx proved
8.48tok/s now39 samples · 3,338s
no capability probed
did:epn:002408…e61d3bKane · 51503 · 26 Oct 2026x86_64 · none · 23.4 GiB pooled
—ctx proved
7.03tok/s now17 samples · 1,312s
no capability probed

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.