Benchmark result
unsloth/Qwen3.8-27B-GGUF:UD-Q4_K_XL on NVIDIA GeForce RTX 3080 +1 more — 61.5 tok/s
Measured with unsloth manual on November 14, 2026.
Support llm-bench.io
llm-bench.io is free. If it helped you, I'd appreciate your support to cover the infrastructure costs.
What the model built
Open full screen →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
unsloth/Qwen3.8-27B-GGUF:UD-Q4_K_XL on other hardware
- 41.5tok/s83.7Advanced Micro Devices, Inc. [AMD/ATI] Device 7551 · Q4_K
- 41.0tok/s69.3Advanced Micro Devices, Inc. [AMD/ATI] Device 7551 · Q4_K
- 31.2tok/s80.3Advanced Micro Devices, Inc. [AMD/ATI] Device 7551 · Q4_K
- 30.0tok/s85.1Advanced Micro Devices, Inc. [AMD/ATI] Device 7551 · Q4_K
- 29.4tok/s75.4Advanced Micro Devices, Inc. [AMD/ATI] Device 7551 · Q4_K
Reproduce this run
toolunsloth manual
modelunsloth/Qwen3.8-27B-GGUF:UD-Q4_K_XL (Q4_K)
context131,000
clientv0.4.98+102
Set those in unsloth, then:
llm-benchmark benchmark --model "unsloth/Qwen3.8-27B-GGUF:UD-Q4_K_XL" --tool "unsloth"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.