Baltor Get started

Models

North Mini Code (free)

By Cohere. 30.5 billion parameters, a context window of 500,000 tokens and the licence apache-2.0.

Facts

Released
2026-06-05 the day the repository was first published on Hugging Face Hugging Face, read
Licence
apache-2.0 the licence the model card declares Hugging Face, read
Open weights
Yes the weights are published in this Hugging Face repository Hugging Face, read
Parameters
30.5 billion counted from the safetensors weight files Hugging Face, read
Active parameters
3.3 billion estimate estimated from the expert counts and sizes in the configuration model configuration, read
Knowledge cutoff
Unknown
Context window
  • 500,000 tokens the maximum position embeddings in the model configuration model configuration, read
  • 256,000 tokens the context length OpenRouter lists OpenRouter, read
Longest output
  • 64,000 tokens the largest output OpenRouter's first provider allows OpenRouter, read
Tool calling
  • Yes OpenRouter lists tools among the supported parameters OpenRouter, read
Structured output
  • No OpenRouter lists no structured output parameter OpenRouter, read
Reasoning controls
  • Yes OpenRouter lists reasoning controls OpenRouter, read
Inputs and outputs
text in, text out Hugging Face, read
Good for
  • Coding: the maker's name for the model marks it for code Hugging Face, read
  • Reasoning: OpenRouter lists reasoning controls for it OpenRouter, read

Prices

No source lists a price for this model. It may only run on your own hardware.

Run it on your own hardware

Weights are the sizes of the files a source lists, or an estimate from the parameter count where none does. Memory is an estimate: weights plus KV cache plus 512 MiB and 5 percent of the weights for runtime buffers. Check it against your hardware.

QuantizationWeightsMemory at 8,192 tokensMemory at 32,768 tokens
UD-IQ1_M8.7 GiB10.4 GiB12.7 GiB
UD-IQ2_XXS9.1 GiB10.8 GiB13.1 GiB
UD-IQ2_M9.2 GiB10.9 GiB13.2 GiB
UD-Q2_K_XL9.8 GiB11.5 GiB13.8 GiB
UD-IQ3_XXS10.9 GiB12.7 GiB15.0 GiB
UD-IQ3_S11.9 GiB13.7 GiB16.0 GiB
UD-Q3_K_M13.2 GiB15.2 GiB17.5 GiB
UD-Q3_K_XL13.4 GiB15.3 GiB17.6 GiB
UD-IQ4_XS14.2 GiB16.2 GiB18.5 GiB
UD-IQ4_NL14.5 GiB16.5 GiB18.8 GiB
UD-Q4_K_S16.8 GiB18.9 GiB21.2 GiB
MXFP4_MOE17.4 GiB19.5 GiB21.8 GiB
UD-Q4_K_M17.9 GiB20.0 GiB22.3 GiB
UD-Q4_K_XL17.9 GiB20.1 GiB22.4 GiB
UD-Q5_K_S20.1 GiB22.4 GiB24.7 GiB
UD-Q5_K_M21.4 GiB23.7 GiB26.0 GiB
UD-Q5_K_XL21.4 GiB23.8 GiB26.1 GiB
UD-Q6_K23.8 GiB26.2 GiB28.5 GiB
UD-Q6_K_XL25.9 GiB28.5 GiB30.8 GiB
Q8_030.2 GiB33.0 GiB35.3 GiB
UD-Q8_K_XL30.9 GiB33.7 GiB36.0 GiB
BF1656.8 GiB60.9 GiB63.2 GiB

Start it with a local runtime

  • Ollama
    ollama run hf.co/unsloth/North-Mini-Code-1.0-GGUF:UD-IQ1_M
  • LM Studio
    lms get unsloth/North-Mini-Code-1.0-GGUF
lms server start
  • llama.cpp server
    llama-server -hf unsloth/North-Mini-Code-1.0-GGUF:UD-IQ1_M --jinja
  • vLLM
    vllm serve CohereLabs/North-Mini-Code-1.0
  • SGLang
    sglang serve --model-path CohereLabs/North-Mini-Code-1.0 --port 30000

Use it from your harness

No endpoint in this directory serves this model yet.

Published results

These are results other people published. Baltor did not run them and does not rank models by them.