Magistral Small 2506

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/Magistral-Small-2506-GGUF:IQ2_XXSollama · IQ2_XXS · 6.3 GiB · quantizer (unsloth)

hf.co/unsloth/Magistral-Small-2506-GGUF:IQ2_Mollama · IQ2_M · 7.7 GiB · quantizer (unsloth)

hf.co/unsloth/Magistral-Small-2506-GGUF:IQ3_XXSollama · IQ3_XXS · 8.8 GiB · quantizer (unsloth)

lmstudio-community/Magistral-Small-2506-MLX-4bitmlx · 4BIT · 12.3 GiB · quantizer (lmstudio-community)

hf.co/unsloth/Magistral-Small-2506-GGUF:Q4_0ollama · Q4_0 · 12.6 GiB · quantizer (unsloth)

hf.co/unsloth/Magistral-Small-2506-GGUF:Q4_K_Mollama · Q4_K_M · 13.3 GiB · quantizer (unsloth)

hf.co/mistralai/Magistral-Small-2506_gguf:Q8_0ollama · Q8_0 · 23.3 GiB · vendor (mistralai)

hf.co/unsloth/Magistral-Small-2506-GGUF:BF16ollama · BF16 · 43.9 GiB · quantizer (unsloth)

mistralai/Magistral-Small-2506vllm · BF16 · 87.8 GiB · vendor (mistralai)

derivatives — somebody else's change to these weights

Fine-tunes, merges and abliterations of this member, each its own model with its own page. None of their numbers are counted above.

magistral-small-2506-mlx-bf16not measured Magistral-Small-2506-bf16not measured Magistral-Small-2506-i1-GGUFnot measured Magistral-Small-2506not measured