Autor: Jakub Rusinowski · Ostatnia aktualizacja: 11 września 2026
Model library → North Mini Code → North Mini Code 1.0 30B-A3B
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.
| Parameters | 30 Billion (3B active) |
| Context window | 256,000 |
| Architecture | Sparse MoE Transformer |
| Provider | Cohere |
| Licence | Apache 2.0 |
| Specified at | Q4_K_M |
| System RAM | 32 GB |
| Record updated | 2026-09-11 |
Apache-2.0 — commercial use permitted. Commercial use permitted. No usage restrictions beyond attribution.
Modelled on a reference NVIDIA RTX 4090 (24 GB), with no KV cache (this record has no published architecture). Speed figures are ESTIMATES from the memory-bandwidth roofline described on the methodology page, not benchmarks we ran — rows marked measured come from published or reader-submitted runs. VRAM here includes the KV cache, so it reads higher than the headline figure above, which does not.
| Quant | Weights | VRAM needed | Est. speed | Fit on 24 GB |
|---|---|---|---|---|
| Q2_K | 9.9 GB | 10.7 GB | ~212 tok/s (est.) | Fits comfortably |
| Q3_K_M | 12.8 GB | 13.6 GB | ~196 tok/s (est.) | Fits comfortably |
| Q4_K_M | 18.1 GB | 18.9 GB | ~172 tok/s (est.) | Fits comfortably |
| Q5_K_M | 21.3 GB | 22.1 GB | ~160 tok/s (est.) | Tight fit |
| Q6_K | 24.6 GB | 25.4 GB | ~22 tok/s (est.) | Offloads to system RAM (slow) |
| Q8_0 | 31.9 GB | 32.7 GB | ~20 tok/s (est.) | Offloads to system RAM (slow) |
| F16 | 60.0 GB | 60.8 GB | — | Won't fit |
Want the memory numbers alone, at every quantization level and your own context length? Use the North Mini Code 1.0 30B-A3B VRAM calculator.
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.
The cheapest catalogued GPU that runs North Mini Code 1.0 30B-A3B is the AMD Radeon RX 7900 XT (20 GB).
Install Ollama, then run:
ollama run north-mini-codeWeights on Hugging Face: CohereLabs/North-Mini-Code-1.0.
Quality scores as published by the model's authors or an independent evaluator — not throughput, and not measured by us.
| Benchmark | Score | Provenance |
|---|---|---|
| Coding Index | 33.4 / 100 pts | vendor-claimed · https://cohere.com/blog/north-mini-code |
Best for: agentic coding, software engineering, coding, consumer gpu.
← All North Mini Code models | VRAM calculator | Check your own hardware