Benchmark result
unsloth/GLM-4.7-Flash-GGUF:UD-Q4_K_XL on AMD Radeon AI PRO R9700 — 117.7 tok/s
Measured with llama.cpp b11146-7fe450e19 on October 17, 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/GLM-4.7-Flash-GGUF:UD-Q4_K_XL on other hardware
Reproduce this run
toolllama.cpp b11146-7fe450e19
modelunsloth/GLM-4.7-Flash-GGUF:UD-Q4_K_XL (Q4_K)
context65,536
think limitnone
samplingtemperature 0.699999988079071 · top_p 1 · top_k 40 · min_p 0.009999999776482582 · presence_penalty 0 · repeat_penalty 1
clientv0.4.96+102
Set those in llama.cpp, then:
llm-benchmark benchmark --model "unsloth/GLM-4.7-Flash-GGUF:UD-Q4_K_XL" --tool "llama.cpp"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.