Benchmark result
unsloth/LFM2.5-VL-1.6B-GGUF on NVIDIA GeForce RTX 4070 — 439.8 tok/s
Measured with Unsloth Studio on September 26, 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
3rd fastest of 3 runs of this model on NVIDIA GeForce RTX 4070 · median 1,004.3 tok/s.
sort
- 11,101.6tok/s13.9llama.cpp
- 21,004.3tok/s23.0llama.cpp
- 3439.8tok/s24.8Unsloth Studio · Q4_K_M · KV f16this run
unsloth/LFM2.5-VL-1.6B-GGUF on other hardware
Reproduce this run
toolUnsloth Studio
modelunsloth/LFM2.5-VL-1.6B-GGUF (Q4_K_M)
context65,536
kv cachef16
think limitnone
samplingtemperature 0.7 · top_p 0.95 · top_k -1 · min_p 0.01 · presence_penalty 0
clientv0.4.80+98
Set those in Unsloth Studio, then:
llm-benchmark benchmark --model "unsloth/LFM2.5-VL-1.6B-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.