commonllama benchmark · run
Run 0032b87abd93
One run of Qwen3.5 4B on one machine class. This page is the durable record a submission receipt points to.
Pre-release: these numbers come from commonllama harness 0.0.0, a build not yet released. They are real measurements, not estimates; released-harness numbers will replace them.
Identity
What this record is.
| Run id | 0032b87abd93fc80043405e31d6d3577 |
|---|---|
| Harness run id | run-74ck890kms |
| Content digest | a76c8ebb004d91e6d78a8d60c8eb6cf20bc5ca9cfcff03496640ff119b15a0c2 canonical, from the committed envelope |
| Raw byte digest | d300a15a9e1f4842d1c3d752eda18f5756080c54ff673032900b95f7665723df sha256 over the file bytes |
| Provenance | migration |
| Report status | complete |
Setting
Where the measurement ran.
| Hardware class | goldspier-rtx5090 |
|---|---|
| System RAM | unavailable bucket, taxonomy v1 |
| Backend | vulkan |
| Storage medium | ssd |
| Model | Qwen3.5 4B c6f6972469c7 |
Qualified to at least 131,072 tokens of context, an observed lower bound, not a maximum.
Ladder
Every rung, every repetition.
Policy mode backend_default, ladder taxonomy v1. A cell that carries no time carries its typed reason instead.
| Context | Rep | Outcome | Actual tokens | Cook | Reload | Reason |
|---|---|---|---|---|---|---|
| 4,096 | 1 | ok | 4,096 | 757.0 ms | 9.79 s | |
| 8,192 | 1 | ok | 8,192 | 1.31 s | 10.54 s | |
| 16,384 | 1 | ok | 16,384 | 2.37 s | 11.41 s | |
| 32,768 | 1 | ok | 32,768 | 5.37 s | 14.17 s | |
| 65,536 | 1 | ok | 65,536 | 12.90 s | 20.02 s | |
| 131,072 | 1 | ok | 131,072 | 35.27 s | 31.67 s |
Saved context
Byte facts as recorded.
| Metric | Context | KV types | Availability | Bytes | Bytes per token | Source |
|---|---|---|---|---|---|---|
artifact-density | 4,096 | not recorded | available | unavailable | goldspier-f-checkpoint-vulkan-four | |
artifact-density | 4,096 | not recorded | available | goldspier-f-resident | ||
artifact-density | 8,192 | not recorded | available | unavailable | goldspier-f-checkpoint-vulkan-four | |
artifact-density | 8,192 | not recorded | available | goldspier-f-resident | ||
artifact-density | 16,384 | not recorded | available | unavailable | goldspier-f-checkpoint-vulkan-four | |
artifact-density | 16,384 | not recorded | available | goldspier-f-resident | ||
artifact-density | 32,768 | not recorded | available | unavailable | goldspier-f-checkpoint-vulkan-four | |
artifact-density | 32,768 | not recorded | available | goldspier-f-resident | ||
artifact-density | 65,536 | not recorded | available | unavailable | goldspier-f-checkpoint-vulkan-four | |
artifact-density | 65,536 | not recorded | available | goldspier-f-resident | ||
artifact-density | 131,072 | not recorded | available | unavailable | goldspier-f-checkpoint-vulkan-four | |
artifact-density | 131,072 | not recorded | available | goldspier-f-resident |
Runtime binding
The configuration the run bound to.
| Requested digest | not recorded |
|---|---|
| Effective digest | unavailable no reason recorded. |
Digests are stored as the harness emitted them, over the recursively key sorted public tuple. The site never recomputes one.
Software identities
The software behind the numbers.
These identities accompany every result so a stale row is visibly stale rather than quietly comparable.
| Harness | 0.0.0 |
|---|---|
| Source commit | 50dbc6c5512c87c9fbd0592628db07527b486e5a |
| Engine | llama.cpp |
| Addon | bf1b8c52dd6bde456aac056911a196a8fe75bb7518432613f8e3016d1b9852dc |
| Backend build | vulkan |
| Upstream | 082b326fc76f6e9bbb835b3920a3022bfdb6691c |
| Patchset | f0b3859395701d3d2b258de4e89ccff407e7c62e983f0636e6097a7b363e599b |
| Schema | commonllama.website-benchmark.v1 |
| Measurement contract | not recorded |
commonllama benchmark records are dedicated to the public domain under CC0 1.0. Use them for anything.