Text model · North

NO North Mini Code 1.0: RAM and VRAM requirements

North Mini Code 1.0 needs about 21.1 GB to run at Q4_K_M (the Q4_K_M GGUF file is ~19 GB to download; KV cache and overhead add the rest), or about 34.1 GB at Q8_0. The lightest hardware that runs it is Nvidia GeForce RTX 4090 (24GB).

North family · 30.5B params (Mixture-of-Experts: activates only 3B of 30.5B params per token, so generation is faster than the total size suggests) · released Jun 2026.

Shopping for hardware? See what runs North Mini Code 1.0 →

License Apache-2.0 · Commercial OK ↓ 14.8K/mo ♥ 546 on HuggingFace

Q4_K_M GGUF

19 GB

Q8_0 GGUF

32 GB

Memory @ Q4 (4k)

~21.1 GB

Context

500 k

Q4_K_M and Q8_0 are GGUF download (file) sizes. Memory @ Q4 includes the KV cache and overhead, so it runs larger than the file on disk.

Will it run on your device?

North Mini Code 1.0 runs on 12 of 40 tracked devices at Q4_K_M.

9 run well 3 tight fit 28 too small

Fit check Q4_K_M

Your device

Apple M4 (16GB)

No, not enough memory

needs 21.1 GB usable 10.5 GB

See the full breakdown

Memory breakdown

Weights (Q4_K_M)19 GB

KV cache (4k)1.3 GB

Overhead0.8 GB

Total21.1 GB

How context length changes it

4k context ~21.1 GB 32k context ~30.4 GB 128k context ~62.2 GB

Longer context grows the KV cache, which for North Mini Code 1.0 is sized by its 3B active params, not the full 30.5B. It needs ~21.1 GB at 4k and ~62.2 GB at 128k.

Quantization sizes

GGUF quantson disk

Quantization	Size on disk
Q2_K	12.8 GB est
Q3_K_M	14.9 GB est
Q4_K_M (default)	19 GB
Q5_K_M	21.7 GB est
Q6_K	25 GB est
Q8_0	32 GB
FP16	61 GB

Lower quant = smaller and faster, slightly lower quality. Q4_K_M is the common default.

Run it

Ollama

$ ollama run north-mini-code-1.0

llama.cpp

$ llama-cli -hf bartowski/North-Mini-Code-1.0-GGUF:Q4_K_M

LM Studio

$ lms get bartowski/North-Mini-Code-1.0-GGUF

Which devices can run North Mini Code 1.0?

Apple Silicon Macs

RAM-only laptops

iPhone & iPad

Android

NVIDIA GPUs

AMD GPUs

Same job, different size

Pick by what fits your memory: step down to free up VRAM, or step up if you have headroom.

Next size down GLM-4.7-Flash 30B Next size up Qwen2.5 32B 32B

Similar models

FAQ

How much VRAM or RAM does North Mini Code 1.0 need?

At Q4_K_M, North Mini Code 1.0 needs about 21.1 GB (weights ~19 GB + KV cache + overhead) at a 4k context. At Q8_0 budget ~34.1 GB.

What is the Q4_K_M GGUF file size of North Mini Code 1.0?

The Q4_K_M GGUF file is about 19 GB to download, and the Q8_0 GGUF is about 32 GB. That is the weights file on disk; to run it you also need room for the KV cache and overhead, so budget ~21.1 GB of memory at Q4_K_M.

Can North Mini Code 1.0 run on a laptop?

North Mini Code 1.0 is large; you need a 24 GB+ GPU or a 32-48 GB Mac at Q4_K_M.

Is North Mini Code 1.0 cheaper to run because it is a MoE model?

It is faster, not lighter. North Mini Code 1.0 activates only 3B of 30.5B params per token (so it runs quickly), but all experts must stay in memory, so it still needs memory for the full 30.5B.

Can I use North Mini Code 1.0 commercially?

Yes. North Mini Code 1.0 is licensed Apache-2.0, which permits commercial use.

Understand the numbers

Short guides to the ideas behind North Mini Code 1.0's memory and quant figures.

Cohere Labs' open-weight code model: 30B total, 3B active, optimized for code generation, agentic software engineering and terminal tasks. Unusually long 500K context. Apache-2.0. Sizes from the Ollama tag listing.

Sources

Last validated 2026-08-03. Memory figures are estimates. See methodology.