Registry evidence
← Back to results

Registry run record

qwen/qwen3-vl-4b on 1× AMD Radeon RX 9070 · 16 GB each · text-only workload

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

11/11/2026, 4:16:01 PM

Performance summary

Time to first token, p50
242.89 ms
Time to first token, p95
258.98 ms
Inter-token latency, p50
6.05 ms
Inter-token latency, p95
6.09 ms
Output tokens per second
143.36
Total tokens per second
721.3
Requests per second
0.56
Error rate
0%

Reproducibility record

Model revision
D:\OmoBench\lmstudio-models
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:e2418912fc627a2c138eafcfc20a78efe6dc2627889f832272ee6f7abeabbe88
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.

This model is not catalogued and is not asking to be. It was accepted on the eligibility facts this bundle carries, which are listed below.

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 memory
31.92 GBread on that machine
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, 16 GB eachstated by the contributorperformed 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
qwen/qwen3-vl-4bstated by the contributorThe catalog identity this result is compared under.
Identifier the server answered to
qwen/qwen3-vl-4bstated by the contributorA serving alias. It is not a claim about which weights were loaded.
Catalog status
Not catalogued — published on its declared eligibilitystated by the contributorThis model is not in the catalog and is not asking to be. What made it publishable is the eligibility it declares, not a list it belongs to.
Quantization
Q4_K_Mstated by the contributor
Weights
D:\OmoBench\lmstudio-modelsstated by the contributorRecorded as a revision only. Which repository it is a revision of is not separately recorded.

What made it publishable

Licence
Apache-2.0stated by the contributorCopied from the publisher, not interpreted.
Licence text
https://huggingface.co/lmstudio-community/Qwen3-VL-4B-Instruct-GGUFstated by the contributor
Weights publicly downloadable
Yesstated by the contributorAccepting the publisher's terms counts; a gated repository still qualifies.
Modality
image-text-to-textstated by the contributorThe model's capability. This benchmark measures a text-only workload.
Publisher
Not recordednot recorded
Where the weights come from
https://lmstudio.ai/models/qwen/qwen3-vl-4bstated by the contributor
Family
Not recordednot recorded
Parameter class
Not recordednot recordedA label the publisher states, never a measurement, and never a claim about answers.
Base model
Not recordednot recorded

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
Qwen/Qwen3-VL-4B-Instructstated by the contributor
Loaded before the run
Not checked by OmoBench
Tokenizer implementation
Not recordednot recorded
Vocabulary size
Not recordednot recorded
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

sha256:20f9f5bfbb42b2e068c445687d0902ba0b11e0e99e886911e2b57e3a38d88f53

guidellm.stdout.log

GuideLLM log

sha256:ee6bade928092f5ab6d20f5e501300778a7ebfe047461913135dde43940d9479

environment.json

Environment snapshot

sha256:cb4b1d684e7b6f2a3260e673d46ee541c499c897abb92a487724b4d1be9acfc4

reproduce.md

Reproduction notes

sha256:6ba265e5280c9e9524377e0e416c99c4660bbb0f4714caf462478441585a95a8