No machine on this network has measured this model yet. Everything below is what the catalog knows exists — where the weights come from, how large each build is, and whose work it is. Nothing here is a claim about what the model can do; that only appears once a machine has run it and signed the result.
hf.co/unsloth/Devstral-Small-2-24B-Instruct-2512-GGUF:IQ1_Sollama · IQ1_S · 5.2 GiB · quantizer (unsloth)
hf.co/unsloth/Devstral-Small-2-24B-Instruct-2512-GGUF:IQ2_XXSollama · IQ2_XXS · 6.3 GiB · quantizer (unsloth)
hf.co/unsloth/Devstral-Small-2-24B-Instruct-2512-GGUF:IQ3_XXSollama · IQ3_XXS · 8.8 GiB · quantizer (unsloth)
hf.co/unsloth/Devstral-Small-2-24B-Instruct-2512-GGUF:Q4_0ollama · Q4_0 · 12.6 GiB · quantizer (unsloth)
hf.co/unsloth/Devstral-Small-2-24B-Instruct-2512-GGUF:Q4_K_Mollama · Q4_K_M · 13.3 GiB · quantizer (unsloth)
mlx-community/Devstral-Small-2-24B-Instruct-2512-4bitmlx · 4BIT · 14.1 GiB · quantizer (mlx-community)
Firworks/Devstral-Small-2-24B-Instruct-2512-nvfp4vllm · W4A4 · 15.0 GiB · quantizer (Firworks)
hf.co/unsloth/Devstral-Small-2-24B-Instruct-2512-GGUF:Q8_0ollama · Q8_0 · 23.3 GiB · quantizer (unsloth)
mlx-community/mistralai_Devstral-Small-2-24B-Instruct-2512-MLX-8Bitmlx · 8BIT · 24.7 GiB · quantizer (mlx-community)
cyankiwi/Devstral-Small-2-24B-Instruct-2512-AWQ-4bitvllm · W4A16 · 29.9 GiB · quantizer (cyankiwi)
hf.co/unsloth/Devstral-Small-2-24B-Instruct-2512-GGUF:BF16ollama · BF16 · 43.9 GiB · quantizer (unsloth)
unsloth/Devstral-Small-2-24B-Instruct-2512vllm · FP8 · 48.0 GiB · quantizer (unsloth)