North Mini Code 1.0 runs at 70 tok/s (69.8 as recorded) on a 64 GB M5 Pro, a community run reported by omlx.ai (MLX, 4-bit, 1k context). It needs about 21 GB of unified memory. It is Cohere's 30.5B mixture-of-experts model (3B active), released under the Apache 2.0 licence.
Want to run North Mini Code 1.0 faster — or step up to bigger models? Find your Mac →This is a community run: a real run, reported by its source and linked below. The index records it as given and never adjusts it.
| Metric | Value |
|---|---|
| Tokens per second | community70 tok/s |
| Provenance | community run · omlx.ai |
| Quantization | 4-bit |
| Engine | MLX |
| Context | 1k |
| Figure dated | 2026-06-13 |
| Minimum RAM | 21 GB |
| Parameters | 30.5B MoE (3B active) |
| Chip bandwidth | 307 GB/s |
Each row as the index holds it, with its source. “Mac RAM” is the memory of the Mac a run used, not the model’s requirement (21 GB). The headline figure follows the reference rule: the lower-median measured plain-decode run at 5 bits or fewer (a run whose quant was not stated counts only when no stated-quant run qualifies), else the estimate; a run marked “not used to anchor estimates” is listed here but never becomes the headline.
| Speed | Quant | Engine | Mac RAM | Context | Source | Note |
|---|---|---|---|---|---|---|
| community69.8 tok/s | 4-bit | MLX | 64 GB | 1k | omlx.ai | 20-core GPU. oMLX v0.4.4rc1; MLX 4-bit. 61.8 tok/s at 4k. |
Ollama — install it (brew install ollama or the app from ollama.com), then pull the model by its tag, checked on ollama.com on 2026-10-17:
MLX — pick a build from Hugging Face’s MLX listings, then run it with its repo id:
Downloads: Ollama page → · model card →
The 70 tok/s figure above came from MLX at 4-bit; other runtimes and quants run at different speeds.
Prefer a GUI? LM Studio downloads GGUF and MLX builds in one click. Step by step: install Ollama on a Mac.
Cohere's Apache 2.0 agentic coder (Jun 2026): a 30B MoE with 3B active and 256K context; SWE-bench Verified 67.6 on Cohere's SWE-agent v1.1.0 run. It fits a 24 GB Mac at 4-bit, and community oMLX runs measured 119.7 tok/s on an M5 Max, 69.8 on an M5 Pro and 34.2 on a base M5.
Apache 2.0 licence · 30.5B MoE · 256K context · LLMCheck capability 36/50 · see its leaderboard rank →
North Mini Code 1.0 needs about 21 GB of unified memory. These current Apple Silicon Macs have the headroom to run it comfortably:
As an Amazon Associate, LLMCheck earns from qualifying purchases. These affiliate links cost you nothing extra and help keep the LLMCheck index free.
See how North Mini Code 1.0 stacks up against other models on your specific Mac hardware.
Open Compare Tool Full Leaderboard