Registry evidence
← Back to results

Registry run record

deepseek-ai/DeepSeek-R1-Distill-Qwen-14B on 1× AMD Radeon RX 9070 · 15.92 GB each

This record is included in this website build. Inspect its measurements, declared setup and evidence metadata below. Inclusion in a local preview alone does not establish community review.

Compare this setup ↗

Execution device

GPU

Profile

chat-small-v2

Framework

lmstudio LM Studio 0.4.28 (build 2)

Quantization

Q4_K_M

Transport

Windows–WSL bridge

Run started

11/13/2026, 11:28:36 AM

Performance summary

Time to first token, p50
643.72 ms
Time to first token, p95
730.12 ms
Inter-token latency, p50
16.4 ms
Inter-token latency, p95
16.47 ms
Output tokens per second
52.99
Total tokens per second
266.34
Requests per second
0.21
Error rate
0%

Reproducibility record

Model revision
sha256-manifest:39e40f3bbefbfb4786d38b9a59d5beff6043eaf0ee92a2539bedea5fe724e6d5
Runtime
lmstudio LM Studio 0.4.28 (build 2)
Runtime arguments
None recorded
GuideLLM
0.7.3
CPU / RAM
AMD Ryzen 7 5800X3D 8-Core Processor · 31.92 GB
Operating system
Microsoft Windows 11 Pro Insider Preview 10.0.26220
Driver version
Not reported
Configuration fingerprint
sha256:c200c6e833ca74a7a7925f930abfb1f95f9dd58f3c465263ea3b21ff17914b18
Source commit
Not recorded

What served this model

What this evidence says.

Reading a fact on a machine establishes what that machine reports about itself. None of this independently confirms that the hardware named here did the work, or that the weights were the ones named.

Measured through the Windows–WSL bridge. Its latency is inside every number here and has not been subtracted.

Where this ran

Arrangement
A Windows host served the model; a WSL2 runner measured itstated by the contributor
Serving operating system
Microsoft Windows 11 Pro Insider Preview 10.0.26220read on that machine
Serving processor
AMD Ryzen 7 5800X3D 8-Core Processorread on that machine
Serving CPU cores
8 physical cores · 16 threadsread on that machine
Serving memory
31.92 GBread on that machine
Installed memory
32 GBread on that machineThe modules fitted. Serving memory above is what the operating system could use.
Benchmark runner
Linux-6.18.58.1-microsoft-standard-WSL2-x86_64-with-glibc2.43 (wsl2)read on that machineThe machine that ran GuideLLM. On a bridged run this is the WSL2 distribution, and nothing it can see of its host is evidence about what served the model.

What ran the weights

Declared execution device
GPUstated by the contributorWhat the contributor says performed inference. OmoBench does not observe this and cannot confirm it.
Accelerator
1 × amd AMD Radeon RX 9070, 15.92 GB eachread on that machineperformed inference. Finding a device establishes the device, not that inference touched it.
Weight placement
GPU onlystated by the contributor

Which model, and which weights

Canonical model
deepseek-ai/DeepSeek-R1-Distill-Qwen-14Bstated by the contributorThe catalog identity this result is compared under.
Identifier the server answered to
deepseek-r1-distill-qwen-14bstated by the contributorA serving alias. It is not a claim about which weights were loaded.
Catalog status
Cataloguedstated by the contributor
Quantization
Q4_K_Mstated by the contributor
Weights
1 file(s), identified by their bytesstated by the contributorManifest sha256:39e40f3bbefbfb4786d38b9a59d5beff6043eaf0ee92a2539bedea5fe724e6d5. These weights have no public immutable revision, so the bytes themselves are the identity.

What made it publishable

Eligibility
Not recordednot recordedThis result is catalogued, so the catalog's own record of the licence and modality applies. It carries no separate eligibility block.

What served it

Framework
lmstudiostated by the contributor
Inference engine
llama.cpp LM Studio 0.4.28 (build 2)stated by the contributorWhat executed the weights.
Hosting application
LM Studio 0.4.23stated by the contributorThe program hosting the engine. Its release version is a different thing from the engine build above.
Serving setting · context_length
8192stated by the contributor
Startup arguments
Not recordednot recorded

What counted the tokens

Tokenizer source
deepseek-ai/DeepSeek-R1-Distill-Qwen-14Bstated by the contributor
Loaded before the run
Yes, in the runner's own interpreterread on that machine
Tokenizer revision
1df8507178afcc1bef68cd8c393f61a886323761read on that machineWhich bytes loaded: the cached snapshot's commit, or a hash of a local tokenizer file.
Tokenizer implementation
TokenizersBackendread on that machine
Vocabulary size
151643read on that machine
Matches the served weights
Not verifiable from this evidenceA tokenizer that loads is not thereby the one the served weights were trained with, and nothing available to OmoBench can establish that it is.

How the requests travelled

Transport
Through the Windows–WSL bridgeread on that machineBridge windows-stdio-http1-v1.
Protocol
HTTP/1.1, one request per connectionread on that machine
Transport latency
Inside every measurement, never subtractedread on that machineA relay sits inside every request this run made and its cost has not been separated out, so these numbers are comparable with other bridged runs rather than with direct ones.

Evidence bundle

Files retained with this result.

initial run · Xatiiv

result.json

Normalized summary used to render this registry record.

guidellm-benchmarks.json.gz

Raw GuideLLM output

sha256:3c7e369af278ea74d46dc3939727bf0c6099653c556efdbfe29ba16e71aa3a0d

guidellm.stdout.log

GuideLLM log

sha256:09128c7bce5134957de516f77470d96e77259b587cb42251ceee6f5c1b829557

environment.json

Environment snapshot

sha256:cb4b1d684e7b6f2a3260e673d46ee541c499c897abb92a487724b4d1be9acfc4

reproduce.md

Reproduction notes

sha256:65d10d32d7fff56e5a7e9a210238a6994b76aa4ba6f808a61c138de101730962