Benchmark result
bartowski/Mellum2.1-12B-A2.5B-Thinking-GGUF on Intel(R) Arc(TM) 140V GPU (16GB) — 30.7 tok/s
Measured with Unsloth Studio on October 23, 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; the frame only adds a line that tells this page how tall it is.
How this run compares
1st fastest of 2 runs of this model on Intel(R) Arc(TM) 140V GPU (16GB) · median 27.5 tok/s.
sort
- 130.7tok/s74.8Unsloth Studio · IQ4_NL · KV q4_0this run
- 224.4tok/s67.7Unsloth Studio · Q4_K_M · KV q4_0
bartowski/Mellum2.1-12B-A2.5B-Thinking-GGUF on other hardware
Reproduce this run
toolUnsloth Studio
modelbartowski/Mellum2.1-12B-A2.5B-Thinking-GGUF (IQ4_NL)
context262,144
kv cacheq4_0
thinkingon
think limitnone
samplingtemperature 0.7 · top_p 0.95 · top_k -1 · min_p 0.01 · presence_penalty 0
clientv0.4.97+102
Set those in Unsloth Studio, then:
llm-benchmark benchmark --model "bartowski/Mellum2.1-12B-A2.5B-Thinking-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.