Run an AI model on your computer

1. Qwen3-4B-AWQ

   Qwen · 2 tested configurations

   • AWQ · 8K → 2K tokens · No cache reuse

     Output throughput · includes prefill · 1 request

     55.3tok/s

     Best measured · 4 concurrent requests

     109tok/s

     Observed GPU occupancy

     19.5GiB

     First token

     1.6 s

     Use this recipe · 4 concurrent requests ↗Evidence report and run availability ↗Same test on other GPUs
     Test details · 2 concurrency levels

     Total output tokens divided by the full request window, including prefill and queueing.

     Occupancy includes engine buffers and reserved KV cache. It is not the minimum VRAM required by the model.

     Reports combined counts reports, not inference requests. Request successes and failures are listed in each report.

     Engine

     vllm · vLLM 0.29.0

     Protocol

     wbench-fixed-http-v3

     Dataset

     migration-analysis-v1:sha256=68590c248e43f32c04dfd8062464fd1e4856917795fe307225e5c6112a54fe94:cache=isolated:repeats=3

     Workload

     8192in-2048out

     Concurrency	Mean throughput (tok/s)	P95	TTFT	Observed occupancy (GiB)	GPU power (W)	Reports combined	View report
     C1	55.3	37.17 s	1.6 s	19.54	71.9	1	9301a9ba ↗
     C4	109.43	78.88 s	3.1 s	19.55	71.9	1	9301a9ba ↗

   • 1 other test configurations on this GPU

     • AWQ · 8K → 2K tokens · Prefix cache reuse

       Output throughput · includes prefill · 1 request

       57.4tok/s

       Best measured · 4 concurrent requests

       175tok/s

       Observed GPU occupancy

       19.5GiB

       First token

       60 ms

       Use this recipe · 4 concurrent requests ↗Evidence report and run availability ↗Same test on other GPUs
       Test details · 2 concurrency levels

       Total output tokens divided by the full request window, including prefill and queueing.

       Occupancy includes engine buffers and reserved KV cache. It is not the minimum VRAM required by the model.

       Reports combined counts reports, not inference requests. Request successes and failures are listed in each report.

       Engine

       vllm · vLLM 0.29.0

       Protocol

       wbench-fixed-http-v3

       Dataset

       migration-analysis-v1:sha256=68590c248e43f32c04dfd8062464fd1e4856917795fe307225e5c6112a54fe94:cache=prefix-reuse:repeats=3

       Workload

       8192in-2048out

       Concurrency	Mean throughput (tok/s)	P95	TTFT	Observed occupancy (GiB)	GPU power (W)	Reports combined	View report
       C1	57.39	35.7 s	60 ms	19.55	71.8	1	7e2cbfda ↗
       C4	175.39	46.75 s	114 ms	19.55	71.9	1	7e2cbfda ↗

2. Qwen3.8-27B-UD-Q4_K_M.gguf

   unsloth/Qwen3.8-27B-GGUF · 2 tested configurations

   • Q4_K_M · 8K → 2K tokens

     Output throughput · includes prefill · 1 request

     14.1tok/s

     Observed GPU occupancy

     17GiB

     First token

     279 ms

     Evidence report and run availability ↗Same test on other GPUs
     Test details

     Total output tokens divided by the full request window, including prefill and queueing.

     Occupancy includes engine buffers and reserved KV cache. It is not the minimum VRAM required by the model.

     Reports combined counts reports, not inference requests. Request successes and failures are listed in each report.

     Engine

     llamacpp

     Protocol

     wbench-fixed-http-v1

     Dataset

     synthetic-tokenizer-v1:repeats=3

     Workload

     8192in-2048out

     Concurrency	Mean throughput (tok/s)	P95	TTFT	Observed occupancy (GiB)	GPU power (W)	Reports combined	View report
     C1	14.09	145.5 s	279 ms	17.05	71.9	1	4bc32a6c ↗

   • 1 other test configurations on this GPU

     • Q4_K_M · 32K → 2K tokens

       Output throughput · includes prefill · 1 request

       12.9tok/s

       Observed GPU occupancy

       17GiB

       First token

       371 ms

       Evidence report and run availability ↗Same test on other GPUs
       Test details

       Total output tokens divided by the full request window, including prefill and queueing.

       Occupancy includes engine buffers and reserved KV cache. It is not the minimum VRAM required by the model.

       Reports combined counts reports, not inference requests. Request successes and failures are listed in each report.

       Engine

       llamacpp

       Protocol

       wbench-fixed-http-v1

       Dataset

       synthetic-tokenizer-v1:repeats=3

       Workload

       32768in-2048out

       Concurrency	Mean throughput (tok/s)	P95	TTFT	Observed occupancy (GiB)	GPU power (W)	Reports combined	View report
       C1	12.94	158.32 s	371 ms	17.05	71.8	1	d8a4b66b ↗

Models shown: 2 / 2

Recipe availability is checked on each report against the published recipe executor.

Occupancy includes engine buffers and reserved KV cache. It is not the minimum VRAM required by the model.

LLM run scripts require Linux x86_64 and an NVIDIA GPU. API and benchmark availability are checked separately on the report.