North · 30B
Can you run Cohere North Mini Code locally?
Cohere North Mini Code is a 30B-parameter model. At 4-bit or better it runs on 73 of the 120 hardware configurations listed here; the smallest is the RTX 4090 (24 GB). On a 128 GB DGX Spark it runs at Q4_K_M.
Data as of 2 November 2026
Fastest machines for Cohere North Mini Code
Every machine that runs it, fastest first. Filter by type; your machine is marked. Compare machines running it side by side
- 1RTX 4090Graphics card · 24 GBno estimateQ4_K_M · 20 of 23 GB
- 2RTX 3090 TiGraphics card · 24 GBno estimateQ4_K_M · 20 of 23 GB
- 3RTX 3090Graphics card · 24 GBno estimateQ4_K_M · 20 of 23 GB
- 4RX 7900 XTXGraphics card · 24 GBno estimateQ4_K_M · 20 of 23 GB
- 5M2 MaxMac · 32–96 GB · 5 variantsno estimateQ4_K_M · 20 GB
- 6M1 MaxMac · 32–64 GB · 4 variantsno estimateQ4_K_M · 20 GB
- 7M2 Pro · 32 GBMac · 32 GBno estimateQ4_K_M · 20 of 21 GB
- 8M1 Pro · 32 GBMac · 32 GBno estimateQ4_K_M · 20 of 21 GB
- 9M6 · 32 GB · 12cMac · 32 GBno estimateQ4_K_M · 20 of 21 GB
- 10M5Mac · 32 GB · 2 variantsno estimateQ4_K_M · 20 GB
- 11M4 · 32 GBMac · 32 GBno estimateQ4_K_M · 20 of 21 GB
- 12RTX 5090Graphics card · 32 GBno estimateQ4_K_M · 20 of 31 GB
- 13M5 MaxMac · 36–128 GB · 4 variantsno estimateQ4_K_M · 20 GB
- 14M4 MaxMac · 36–128 GB · 4 variantsno estimateQ4_K_M · 20 GB
- 15M3 MaxMac · 36–128 GB · 5 variantsno estimateQ4_K_M · 20 GB
- 16M3 Pro · 36 GBMac · 36 GBno estimateQ4_K_M · 20 of 24 GB
- 17M5 ProMac · 48–64 GB · 4 variantsno estimateQ4_K_M · 20 GB
- 18M4 ProMac · 48–64 GB · 4 variantsno estimateQ4_K_M · 20 GB
- 192x RTX 4090Graphics card · 48 GBno estimateQ4_K_M · 20 of 46 GB
- 202x RTX 3090 TiGraphics card · 48 GBno estimateQ4_K_M · 20 of 46 GB
- 212x RTX 3090Graphics card · 48 GBno estimateQ4_K_M · 20 of 46 GB
- 222x RX 7900 XTXGraphics card · 48 GBno estimateQ4_K_M · 20 of 46 GB
- 23Ryzen AI Max+ 395AI mini PC · 64–128 GB · 2 variantsno estimateQ4_K_M · 20 GB
- 24M2 UltraMac · 64–192 GB · 7 variantsno estimateQ4_K_M · 20 GB
- 25M1 UltraMac · 64–128 GB · 4 variantsno estimateQ4_K_M · 20 GB
- 262x RTX 5090Graphics card · 64 GBno estimateQ4_K_M · 20 of 62 GB
- 27M5 UltraMac · 96–512 GB · 5 variantsno estimateQ4_K_M · 20 GB
- 28M3 UltraMac · 96–512 GB · 5 variantsno estimateQ4_K_M · 20 GB
- 29RTX PRO 6000 BlackwellGraphics card · 96 GBno estimateQ4_K_M · 20 of 95 GB
- 30DGX Spark (GB10)AI mini PC · 128 GBno estimateQ4_K_M · 20 of 122 GB
- 312x RTX PRO 6000 BlackwellGraphics card · 192 GBno estimateQ4_K_M · 20 of 190 GB
Too big for 47 machines
RX 7900 XT, M5 Pro · 24 GB · 20c, M5 Pro · 24 GB · 16c, M4 Pro · 24 GB · 20c, M4 Pro · 24 GB · 16c, M6 · 24 GB · 12c, M6 · 24 GB · 10c, M5 · 24 GB · 10c, M5 · 24 GB · 8c, M4 · 24 GB, M3 · 24 GB, M2 · 24 GB, RTX 5080, RTX 5070 Ti, RTX 5060 Ti, RTX 4080 SUPER, RTX 4080, RTX 4070 Ti SUPER, RTX 4060 Ti, Tesla T4, Tesla P100, RX 9070 XT, RX 9060 XT, M3 Pro · 18 GB, RTX 5070, RTX 4070 Ti, RTX 4070 SUPER, RTX 4070, RTX 3060, M2 Pro · 16 GB, M1 Pro · 16 GB, M6 · 16 GB · 12c, M6 · 16 GB · 10c, M5 · 16 GB · 10c, M5 · 16 GB · 8c, M4 · 16 GB, M3 · 16 GB, M2 · 16 GB, M1 · 16 GB, RTX 5060, RTX 4060, RTX 3070, RTX 3060 Ti, RTX 2070, M3 · 8 GB, M2 · 8 GB, M1 · 8 GB. Cohere North Mini Code needs about 20 GB at its smallest build.
Speeds are single-user decode estimates, not measurements. "ModelFit est." comes from ModelFit's model fitted on published runs (CC BY 4.0); "our est." is memory bandwidth divided by bytes read per token, times 0.55. Memory is what the best build needs, against what the machine can give a model. Method
About the model
- Parameters
- 30B
- Active per token
- not in our sources
- Type
- not in our sources
- Good for
- Agentic coding, repo-scale software engineering
Builds and how to run them
| Quantization | Load | Min. RAM | Command |
|---|---|---|---|
| Q4_K_M | 19.0 GB | 32 GB | ollama run north-mini-code-1.0:q4_K_M |
Load, minimum RAM and Ollama commands: ModelFit, CC BY 4.0. Load is memory with the model loaded, before long contexts.
Questions
Can I run Cohere North Mini Code on a Mac?
Yes on a Mac with enough memory: the smallest Apple configuration listed here that runs it at 4-bit or better is the M2 Max · 32 GB · 38c.
How much memory does Cohere North Mini Code need?
About 20 GB at the smallest build in our data, including a margin for the runtime and an 8K-token context. Longer contexts need more.
Does Cohere North Mini Code run on a DGX Spark?
Yes, at Q4_K_M. The Spark has 128 GB of unified memory, about 121.6 GB usable.