Benchmark result
empero-ai/Qwen3.8-35B-A3B-Distill-GGUF on 2× AMD Radeon RX 7900 XT/7900 XTX/7900M — 95.3 tok/s
Measured with Unsloth Studio on September 30, 2026.
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.
How this run compares
2nd fastest of 2 runs of this model on 2× AMD Radeon RX 7900 XT/7900 XTX/7900M · Multi-GPU · median 107.4 tok/s.
sort
- 1119.6tok/s84.0Unsloth Studio · Q6_K · KV f16
- 295.3tok/s83.3Unsloth Studio · Q6_K · KV f16this run
Reproduce this run
toolUnsloth Studio
modelempero-ai/Qwen3.8-35B-A3B-Distill-GGUF (Q6_K)
context131,072
kv cachef16 (assumed default)
samplingtemperature 0.7 · top_p 0.8 · top_k 20 · min_p 0 · presence_penalty 1.5
clientv0.4.82+98
Set those in Unsloth Studio, then:
llm-benchmark benchmark --model "empero-ai/Qwen3.8-35B-A3B-Distill-GGUF" --tool "Unsloth 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.