Benchmark result

qwen/qwen3.8-27b on NVIDIA GeForce RTX 3090 — 16.5 tok/s

Measured with LM Studio on October 21, 2026.

What the model built

The coding scenario asks for a playable game in a single HTML file. This is exactly what the model returned, unedited; the frame only adds a line that tells this page how tall it is.

How this run compares

12th fastest of 12 runs of this model on NVIDIA GeForce RTX 3090 · median 50.5 tok/s.

sort

194.9tok/s22.7vLLM
256.6tok/s88.2llama.cpp
354.0tok/s90.7Strata
453.5tok/s82.3llama.cpp
552.6tok/s79.7llama.cpp
650.9tok/s86.9llama.cpp
750.0tok/s88.3Strata
838.4tok/s90.9Strata
937.7tok/s88.0Strata
1037.3tok/s88.2llama.cpp
1136.9tok/s89.6llama.cpp
1216.5tok/s86.2LM Studio · Q4_K_Mthis run

Compare the nearest 5 →

qwen/qwen3.8-27b on other hardware

Reproduce this run

toolLM Studio

modelqwen/qwen3.8-27b (Q4_K_M)

context177,840

thinkingon

effortmedium

clientv0.4.96+102

Set those in LM Studio, then:

llm-benchmark benchmark --model "qwen/qwen3.8-27b" --tool "LM Studio"

The client prompts for context length and thinking mode, and for the KV cache dtype on Unsloth Studio. Sampling is left at the model default — the values above are what the tool reported using, not overrides the client sent.