Benchmark result

unsloth/Qwen3.8-Flash-Next-GGUF on 2× AMD Radeon RX 7900 XTX — 27.1 tok/s

Measured with Unsloth Studio on September 22, 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

unsloth/Qwen3.8-Flash-Next-GGUF on other hardware

Reproduce this run

toolUnsloth Studio

modelunsloth/Qwen3.8-Flash-Next-GGUF (UD-IQ3_XXS)

context16,384

kv cacheq8_0 (assumed default)

effortxhigh (model default)

think limitnone

samplingtemperature 0.7 · top_p 0.8 · top_k 20 · min_p 0 · presence_penalty 1.5

clientv0.4.80+98

Set those in Unsloth Studio, then:

llm-benchmark benchmark --model "unsloth/Qwen3.8-Flash-Next-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.