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/North-Mini-Code-1.0-GGUF:IQ1_Mollama · IQ1_M · 8.7 GiB · quantizer (unsloth)
hf.co/unsloth/North-Mini-Code-1.0-GGUF:IQ2_XXSollama · IQ2_XXS · 9.1 GiB · quantizer (unsloth)
hf.co/unsloth/North-Mini-Code-1.0-GGUF:IQ3_XXSollama · IQ3_XXS · 10.9 GiB · quantizer (unsloth)
hf.co/unsloth/North-Mini-Code-1.0-GGUF:Q4_K_Sollama · Q4_K_S · 16.8 GiB · quantizer (unsloth)
mlx-community/North-Mini-Code-1.0-4bitmlx · 4BIT · 17.2 GiB · quantizer (mlx-community)
hf.co/unsloth/North-Mini-Code-1.0-GGUF:Q4_K_Mollama · Q4_K_M · 17.9 GiB · quantizer (unsloth)
CohereLabs/North-Mini-Code-1.0-w4a16vllm · W4A16 · 18.0 GiB · vendor (CohereLabs)
mlx-community/North-Mini-Code-1.0-6bitmlx · 6BIT · 24.1 GiB · quantizer (mlx-community)
CohereLabs/North-Mini-Code-1.0-fp8vllm · FP8 · 29.8 GiB · vendor (CohereLabs)
hf.co/unsloth/North-Mini-Code-1.0-GGUF:Q8_0ollama · Q8_0 · 30.2 GiB · quantizer (unsloth)
aaronmwelborn/North-Mini-Code-1.0-8bitmlx · 8BIT · 31.0 GiB · quantizer (aaronmwelborn)
hf.co/Fr4nkSt3in/North-Mini-Code-1.0-BF16-GGUF:BF16ollama · BF16 · 56.8 GiB · quantizer (Fr4nkSt3in)
unsloth/North-Mini-Code-1.0-GGUF:BF16llamacpp · BF16 · 56.8 GiB · quantizer (unsloth)