BestLLMfor Your hardware. Your LLM. Your call.
The Local Copilot Kit APIOpen data Find my LLM
Model fiche

North Mini Code 1.0

By Cohere · United States

Updated 2026-08-31

chat code reasoning
Parameters
30.5B
License
Apache 2.0
Context
476k
VRAM (Q4)
18 GB
Released
5 June 2026

Overview

Cohere's 30.5B dense model tuned for agentic coding and reasoning, with an unusually long 488K context window under Apache 2.0 licensing.

When to pick this model

  • Long-context codebase analysis or multi-file agentic coding tasks
  • You need Apache 2.0 licensing for unrestricted commercial deployment
  • Reasoning-heavy coding workflows where context length matters more than general chat versatility
  • Local deployment on a single 24GB-class GPU (Q4)

VRAM requirements by quantization

VRAM REQUIRED (GB)81216243248Q4_K_M18 GBQ5_K_M22 GBQ8_033 GBFP1661 GB
QuantizationVRAM required
Q4_K_M (recommended)18 GB
Q5_K_M22 GB
Q8_033 GB
FP16 (no quantization)61 GB

VRAM figures include model weights plus a typical 8k KV cache and ~600 MB runtime overhead (Ollama / llama.cpp baseline). Add headroom for higher context lengths.

In practice, North Mini Code 1.0 wants a 24 GB card at Q4_K_M (18 GB). Stepping up to Q8_0 nearly doubles the footprint to 33 GB, and unquantized FP16 weights take 61 GB — plan your GPU around the Q4 or Q5 figure unless you specifically need the higher fidelity.

Without a GPU, North Mini Code 1.0 needs roughly 40 GB of system RAM to run on CPU via llama.cpp or Ollama — workable for background jobs, but far slower than GPU inference. Throughput estimates from our compatibility engine: around 9 tokens/sec on entry-level GPUs, on the order of 14 tokens/sec on a mid-range card, and up to 22 tokens/sec on high-end hardware — assuming the chosen quantization fully fits in VRAM.

What hardware do you need

The table below matches North Mini Code 1.0 to common GPU memory tiers, using the highest-fidelity quantization that fully fits each card class. Spilling layers to system RAM works but costs most of the speed, so size your card to the quantization you actually want to run.

GPU memoryExample cardsBest fit for North Mini Code 1.0
8 GBRTX 5070 Laptop, RTX 5060, RTX 5060 Ti 8GBDoes not fit — needs 18 GB at Q4_K_M
12 GBRTX 5070, RTX 5070 Ti Laptop, RTX 4080 LaptopDoes not fit — needs 18 GB at Q4_K_M
16 GBRTX 5080, RTX 4080 Super, Radeon RX 9070 XTDoes not fit — needs 18 GB at Q4_K_M
24 GBRTX 4090, Radeon RX 7900 XTX, RTX 5090 LaptopQ5_K_M (22 GB used)
32 GBRTX 5090Q5_K_M (22 GB used)

Which hardware should you buy to run North Mini Code 1.0?

To run North Mini Code 1.0 locally at Q4, you need ~18 GB of VRAM. The best value for this today is a GMKtec EVO-X2 64GB (Ryzen AI Max+ 395 mini PC) (64 GB unified memory, half the price of an RTX 5090).

Check GMKtec EVO-X2 64GB (Ryzen AI Max+ 395 mini PC) price on Amazon →

As an Amazon Associate, BestLLMfor earns from qualifying purchases, at no extra cost to you. It does not influence our independent rankings.

Strengths

  • 488K context window, among the longest available at this size
  • Apache 2.0 license with no commercial restrictions
  • Purpose-built for agentic coding and reasoning
  • Runs at ~18GB VRAM in Q4, accessible on a single high-end consumer GPU

Limitations

  • Coding-focused; less well-rounded for general chat
  • Inference throughput is moderate, not class-leading

Typical workloads

In our catalog grid, North Mini Code 1.0 is filed under Agentic Coding, Reasoning, Long Context — the use cases where its size/quality trade-off makes the most sense. Its tags translate to concrete workloads: code generation and review (pair it with an editor integration like Continue.dev or Cline); multi-step reasoning and math-flavoured tasks.

The 476k-token context window is large enough to hold entire codebases' worth of files or long reports in a single prompt, which is what makes local RAG and document analysis practical. The Apache 2.0 license is permissive, so shipping it inside a commercial product raises no special legal questions.

Architecture & training

Architecture: Dense 30.5B · 488K context

Training: Cohere's North line, focused on agentic coding and reasoning. Apache 2.0 license.

Verdict

The pick when you need very long-context agentic coding under a fully permissive license.

Quick start

ollama run north-mini-code-1.0

Or use the open-source MCP server to query this model from Claude Desktop, Cursor, or any MCP-compatible client.

Similar models worth comparing

Frequently asked questions

How much VRAM does North Mini Code 1.0 need?

At the recommended Q4_K_M quantization, North Mini Code 1.0 needs about 18 GB of VRAM. Q8_0 takes 33 GB, and unquantized FP16 weights take 61 GB.

Can North Mini Code 1.0 run without a GPU?

Yes — with roughly 40 GB of system RAM it runs CPU-only through llama.cpp or Ollama. Expect a fraction of GPU speed, which is fine for background or batch jobs but slow for interactive chat.

What context window does North Mini Code 1.0 support?

North Mini Code 1.0 supports a 476k-token context window (488,000 tokens).

Can I use North Mini Code 1.0 commercially?

Yes. North Mini Code 1.0 is released under Apache 2.0, a permissive open-source license that allows commercial use, modification and redistribution.

How fast is North Mini Code 1.0 on consumer hardware?

Our compatibility engine estimates on the order of 14 tokens/sec on a mid-range GPU and up to 22 tokens/sec on high-end cards, assuming the quantization fully fits in VRAM.

Which quantization of North Mini Code 1.0 should I download first?

Start with Q4_K_M (18 GB) — the standard size/quality sweet spot. Step up to Q5_K_M or Q8_0 only if you have VRAM headroom. On a 24 GB card you can run up to Q5_K_M.

Tools

Is North Mini Code 1.0 the right pick for you?

Compute self-hosted ROI → Back to catalog