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-2-123B-Instruct-2512-GGUF:IQ1_Sollama · IQ1_S · 26.5 GiB · quantizer (unsloth)
hf.co/unsloth/Devstral-2-123B-Instruct-2512-GGUF:IQ2_XXSollama · IQ2_XXS · 32.0 GiB · quantizer (unsloth)
DevQuasar/mistralai.Devstral-2-123B-Instruct-2512-GGUF:Q2_Kllamacpp · Q2_K · 43.4 GiB · quantizer (DevQuasar)
hf.co/unsloth/Devstral-2-123B-Instruct-2512-GGUF:IQ3_XXSollama · IQ3_XXS · 45.6 GiB · quantizer (unsloth)
unsloth/Devstral-2-123B-Instruct-2512-GGUF:Q3_K_Sllamacpp · Q3_K_S · 50.6 GiB · quantizer (unsloth)
unsloth/Devstral-2-123B-Instruct-2512-GGUF:IQ4_XSllamacpp · IQ4_XS · 62.5 GiB · quantizer (unsloth)
mlx-community/Devstral-2-123B-Instruct-2512-4bitmlx · 4BIT · 65.5 GiB · quantizer (mlx-community)
unsloth/Devstral-2-123B-Instruct-2512-GGUF:Q4_0llamacpp · Q4_0 · 66.1 GiB · quantizer (unsloth)
unsloth/Devstral-2-123B-Instruct-2512-GGUF:Q4_K_Mllamacpp · Q4_K_M · 69.8 GiB · quantizer (unsloth)
mlx-community/Devstral-2-123B-Instruct-2512-5bitmlx · 5BIT · 80.1 GiB · quantizer (mlx-community)
mlx-community/Devstral-2-123B-Instruct-2512-8bitmlx · 8BIT · 123.7 GiB · quantizer (mlx-community)
unsloth/Devstral-2-123B-Instruct-2512-GGUF:Q8_0llamacpp · Q8_0 · 123.7 GiB · quantizer (unsloth)
hf.co/ggml-org/Devstral-2-123B-Instruct-2512-GGUF:Q8_0ollama · Q8_0 · 123.7 GiB · quantizer (ggml-org)
cyankiwi/Devstral-2-123B-Instruct-2512-AWQ-4bitvllm · W4A16 · 139.6 GiB · quantizer (cyankiwi)
unsloth/Devstral-2-123B-Instruct-2512-GGUF:BF16llamacpp · BF16 · 232.9 GiB · quantizer (unsloth)
mistralai/Devstral-2-123B-Instruct-2512vllm · FP8 · 238.9 GiB · vendor (mistralai)