Cohere30B (3B active)~19 GB VRAM at Q4_K_M

North Mini Code 1.0 30B-A3B — VRAM, speed & local setup

Written by Jakub Rusinowski · Last updated

All 30B of parameters stay resident — about 18.9 GB at Q4_K_M, so a 24 GB card holds it comfortably — but only ~3B activate per token, which is what makes it quick enough to sit behind an interactive coding agent. 256K context, 64K max generation, Apache 2.0. Cohere tuned it for three jobs specifically: code generation, agentic software engineering, and terminal tasks.

North Mini Code 1.0 30B-A3B needs about 19 GB of VRAM at Q4_K_M — quantized weights plus framework overhead, before any KV cache. On Apple Silicon that figure comes out of unified memory.

Logic82
Creative72
Coding89

VRAM and speed by quantization

Quoted against NVIDIA RTX 4090 (24 GB). Weights plus overhead only: this model's architecture is unpublished, so no KV cache is added.

QuantVRAMSpeed (est.)Fit
Q2_K
2.63 bpw
10.7 GB~212 tok/sFits
Q3_K_M
3.41 bpw
13.6 GB~196 tok/sFits
Q4_K_M
4.83 bpw
18.9 GB~172 tok/sFits
Q5_K_M
5.67 bpw
22.1 GB~160 tok/sTight
Q6_K
6.56 bpw
25.4 GB~22 tok/sOffload
Q8_0
8.50 bpw
32.7 GB~20 tok/sOffload
F16
16.00 bpw
60.8 GB—Too big

Black marker = usable memory on the NVIDIA RTX 4090 (24 GB). Estimates from the memory-bandwidth roofline on the methodology page. North Mini Code 1.0 30B-A3B VRAM calculator →

Get North Mini Code 1.0 30B-A3B running

The cheapest catalogued GPU that runs North Mini Code 1.0 30B-A3B is the AMD Radeon RX 7900 XTX (24 GB).

Buy this hardware AMD Radeon RX 7900 XTX 24GB — 24 GB VRAM · 355 W board powerDeploy in the cloud now RTX 4090 on RunPod — from $0.34/hr · rate checked 2026-07

or compare on Vast.ai from $0.35/hr (typical low · varies)

As an Amazon Associate we earn from qualifying purchases. Cloud GPU links are referral links — we may earn a commission at no extra cost to you.

Affiliate disclosure: Some links on this page are affiliate links — if you buy through them, LLM Configurator may earn a commission at no extra cost to you. As an Amazon Associate, LLM Configurator earns from qualifying purchases.
AMD Radeon RX 7900 XTX 24GB
24 GB VRAM · 355 W board power
2026 prices are volatile — check the current listing.

How to run North Mini Code 1.0 30B-A3B

Install Ollama, then run:

ollama run north-mini-code
Weights on Hugging Face: CohereLabs/North-Mini-Code-1.0 ↗

Specifications

Verified — Checked against the primary source — the model card or the vendor spec page — and corroborated by a second independent source.

Parameters
30 Billion (3B active)
Context window
256,000
Architecture
Sparse MoE Transformer
Provider
Cohere
Licence
Apache 2.0
Practical deployment
Single consumer GPU
Specified at
Q4_K_M
System RAM
32 GB
Record updated
2026-09-11
LicenceApache-2.0Commercial use permitted

Commercial use permitted. No usage restrictions beyond attribution.

Quality and use cases

Scores as published by the model’s authors or an independent evaluator — quality, not throughput, and not measured by us.

Best foragentic codingsoftware engineeringcodingconsumer gpu
BenchmarkScoreProvenance
Coding Index33.4 / 100 ptsvendor-claimed · https://cohere.com/blog/north-mini-code

Can I run North Mini Code 1.0 30B-A3B on my GPU?

North Mini Code 1.0 30B-A3B — frequently asked questions

How much VRAM does North Mini Code 1.0 30B-A3B need?

About 19 GB at Q4_K_M — quantized weights plus framework overhead, before any KV cache. The cache grows with context length and is added on top; the table above folds it in. Apple Silicon counts unified memory toward the same figure.

Does North Mini Code 1.0 30B-A3B run on an RTX 4090 (24 GB)?

Yes. North Mini Code 1.0 30B-A3B needs about 19 GB at Q4_K_M, inside a 24 GB card, at an estimated 172 tokens/sec.

How do I run North Mini Code 1.0 30B-A3B locally?

Install Ollama and run `ollama run north-mini-code`. That pulls the weights and starts a local OpenAI-compatible endpoint; after the download nothing leaves the machine.