← Mistral Large 3

Mistral Large 3 675B-INSTRUCT-2512

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.

unsloth/Mistral-Large-3-675B-Instruct-2512-GGUF:IQ1_Sllamacpp · IQ1_S · 177.7 GiB · quantizer (unsloth)
unsloth/Mistral-Large-3-675B-Instruct-2512-GGUF:IQ2_XXSllamacpp · IQ2_XXS · 209.4 GiB · quantizer (unsloth)
hf.co/mradermacher/Mistral-Large-3-675B-Instruct-2512-GGUF:Q2_Kollama · Q2_K · 228.0 GiB · quantizer (mradermacher)
unsloth/Mistral-Large-3-675B-Instruct-2512-GGUF:IQ3_XXSllamacpp · IQ3_XXS · 260.0 GiB · quantizer (unsloth)
hf.co/mradermacher/Mistral-Large-3-675B-Instruct-2512-GGUF:Q3_K_Sollama · Q3_K_S · 270.1 GiB · quantizer (mradermacher)
hf.co/mradermacher/Mistral-Large-3-675B-Instruct-2512-GGUF:Q3_K_Lollama · Q3_K_L · 324.6 GiB · quantizer (mradermacher)
hf.co/mradermacher/Mistral-Large-3-675B-Instruct-2512-GGUF:Q4_K_Sollama · Q4_K_S · 355.1 GiB · quantizer (mradermacher)
unsloth/Mistral-Large-3-675B-Instruct-2512-GGUF:Q4_0llamacpp · Q4_0 · 355.5 GiB · quantizer (unsloth)
hf.co/mradermacher/Mistral-Large-3-675B-Instruct-2512-GGUF:Q4_K_Mollama · Q4_K_M · 377.9 GiB · quantizer (mradermacher)
unsloth/Mistral-Large-3-675B-Instruct-2512-GGUF:Q4_K_Mllamacpp · Q4_K_M · 379.0 GiB · quantizer (unsloth)
unsloth/Mistral-Large-3-675B-Instruct-2512-GGUF:Q8_0llamacpp · Q8_0 · 666.5 GiB · quantizer (unsloth)
unsloth/Mistral-Large-3-675B-Instruct-2512-GGUF:BF16llamacpp · BF16 · 1254.5 GiB · quantizer (unsloth)
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.

Mistral-Large-3-675B-Instruct-2512-i1-GGUFnot measured