CohereNorthCohere2MoeForCausalLM

North Mini Code 1.0 — Hardware Requirements & GPU Compatibility

ChatCodeFunctions

North Mini Code 1.0 is Cohere's first open-weight coding model, a mixture-of-experts design with about 30.5 billion total parameters and roughly 3.3 billion active per token. It is tuned for agentic coding: tool calling, terminal workflows, and software-engineering tasks rather than general chat. Only the active parameters compute per token, so it decodes quickly for its size, though all weights must fit in memory; it runs on a single high-end consumer GPU once quantized. The model supports a 500,000 token context window, useful for large codebases or long agent transcripts. It is released under the Apache 2.0 license, allowing unrestricted commercial and research use. Published in June 2026 as the debut release in Cohere's North family, it is designed to run on a single H100-class GPU in FP8.

30.5B params · MoE3.3B active500K contextApache 2.0Jun 20268.3K downloads587 likes265.7K quant downloads

Your hardware

Verdicts below are for the reference RTX 4090. Set yours to personalise the page.

Detection reads your browser's GPU name with no data sent anywhere.

Runs great on a 24 GB GPU

Runs from 12 GB (IQ2_M · 16K)Best on 24 GB (Q4_K_M · ~173 tok/s · 64K)Macs from 16 GB (IQ2_M · ~55 tok/s)

Apache 2.0

Reference GPU · RTX 4090 24 GB

Estimates, ±20% · how we estimate

Run North Mini Code 1.0

One recommended way. Every other method, OS and quant is in the step-by-step guide.Each way opens a step-by-step guide for your OS and quant.

Ways to runOther ways

each opens step-by-step

Run in cloud

Your own private copy · Q4_K_M · 24 GB GPU

The easiest way to try this model
Running in a few minutes, easy setup
Chat right here or connect any app

$5+ bonus for new users

Run North Mini Code 1.0

19.4 GB VRAM at 16K context · fits the RTX 4090 (4.6 GB free)

Works on macOS, Windows and Linux.

Install Ollama (Linux)
$curl -fsSL https://ollama.com/install.sh | sh
Install Ollama (macOS / Windows)
Download and run the app; it installs the ollama command.
Download Ollama ↗
Run Q4_K_M
$ollama run hf.co/unsloth/North-Mini-Code-1.0-GGUF:Q4_K_M
Raise the context window
Type it inside the chat. For the API server instead, start it with OLLAMA_CONTEXT_LENGTH=16384 ollama serve.
$/set parameter num_ctx 16384
A larger context needs more memory than the weights alone.
Use the API
Ollama serves its API on http://localhost:11434.

Works on macOS, Windows and Linux.

Install LM Studio
Desktop app for macOS (Apple silicon), Windows and Linux.
lmstudio.ai ↗
Download the model
In the app press Ctrl/Cmd + Shift + M and paste https://huggingface.co/unsloth/North-Mini-Code-1.0-GGUF, then pick Q4_K_M. Or use the CLI (run LM Studio once first):
$lms get https://huggingface.co/unsloth/North-Mini-Code-1.0-GGUF@Q4_K_M
Open on Hugging Face ↗
Load and chat
Open the model loader, select the model and set Context Length to 16384. Leave GPU offload at maximum if it fits.
Start the local server (optional)
$lms server start

Works on macOS, Windows and Linux.

Install llama.cpp (macOS)
MacPorts, Nix and conda-forge also work.
$brew install llama.cpp
Install options ↗
Install llama.cpp (Windows)
$winget install llama.cpp
Install llama.cpp (Linux)
Download the prebuilt llama-*-bin-ubuntu-* archive for your GPU backend (CPU, Vulkan) from the releases page, unpack it and run the binaries from that folder. Homebrew (brew install llama.cpp) and conda-forge also work on Linux.
llama.cpp releases ↗
Start the server
Downloads the model on first run. The chat UI and an OpenAI-compatible API are at http://localhost:8080.
$llama-server -hf unsloth/North-Mini-Code-1.0-GGUF:Q4_K_M -c 16384 -ngl 99 --port 8080

Works on macOS, Windows and Linux.

Option A: Docker Model Runner
Docker Desktop: Settings > AI > Enable Docker Model Runner. Docker Engine on Linux: install the docker-model-plugin package.
$docker model run hf.co/unsloth/North-Mini-Code-1.0-GGUF:Q4_K_M
Model Runner docs ↗
The quant tag after the repo is how Hugging Face cards write it; if your Docker version rejects it, drop the tag and pick the quant by repo.
Option B: llama.cpp server image (NVIDIA)
Needs the NVIDIA Container Toolkit. Models are cached in the llama-cache volume. Open http://localhost:8080.
$docker run --gpus all -p 8080:8080 -v llama-cache:/root/.cache ghcr.io/ggml-org/llama.cpp:server-cuda -hf unsloth/North-Mini-Code-1.0-GGUF:Q4_K_M -c 16384 -ngl 99 --host 0.0.0.0 --port 8080
Image tags (cuda13, vulkan, rocm) ↗
Cache path inside the image is not in the docs; remove the -v flag if the volume complains.

Linux only.

Install vLLM
Linux only; on Windows run it inside WSL2. NVIDIA GPU shown; AMD ROCm, Intel and CPU builds have their own install pages.
$uv venv --python 3.12 --seed
$source .venv/bin/activate
$uv pip install vllm --torch-backend=auto
vLLM installation ↗
Serve the model
OpenAI-compatible API at http://localhost:8000/v1.
$vllm serve CohereLabs/North-Mini-Code-1.0 --max-model-len 16384
Runs the original weights, not the Q4_K_M GGUF; needs ~67 GB of GPU memory.

macOS only.

MLX supports only macOS, so follow these steps for that setup.

Install mlx-lm
$pip install mlx-lm
Chat in the terminal
$mlx_lm.chat --model mlx-community/North-Mini-Code-1.0-4bit
Downloads the model on first run. The MLX repo has its own quantisation; it may not match the quant selected above.
Or start a local server
Listens on http://localhost:8080.
$mlx_lm.server --model mlx-community/North-Mini-Code-1.0-4bit

Works on macOS, Windows and Linux.

Install Jan
jan.ai ↗
Find the model
Open the Hub tab, paste this model ID in Search, and choose Q4_K_M if offered.
$unsloth/North-Mini-Code-1.0-GGUF
Use the local API (optional)
Settings > Local API Server > Start Server. It listens on http://127.0.0.1:1337.

Rent GPUs hourly to run Q4_K_M right there. Pricing comes from partner marketplaces and varies.

Available GPU rentals for Q4_K_M, prioritized by value
GPU	Speed	$/1M tokens	Rent
RTX 3090 (24 GB)CheapestCheapest4 GB free	~166 tok/s	$0.33	Deploy on Vast.aifrom $0.20/hr (opens in new tab)	24 GB · 4 GB free · ~166 tok/s · $0.33 / 1M tokens
TITAN RTX (24 GB)4 GB free	~136 tok/s	$0.44	Deploy on Vast.aifrom $0.22/hr (opens in new tab)	24 GB · 4 GB free · ~136 tok/s · $0.44 / 1M tokens
RTX A5000 (24 GB)4 GB free	~148 tok/s	$0.43	Deploy on Vast.aifrom $0.23/hr (opens in new tab)	24 GB · 4 GB free · ~148 tok/s · $0.43 / 1M tokens
RTX PRO 4000 (24 GB)4 GB free	~136 tok/s	$0.55	Deploy on Vast.aifrom $0.27/hr (opens in new tab)	24 GB · 4 GB free · ~136 tok/s · $0.55 / 1M tokens
RTX PRO 4500 (32 GB)12 GB free	~162 tok/s	$0.58	Deploy on RunPodfrom $0.34/hr (opens in new tab)	32 GB · 12 GB free · ~162 tok/s · $0.58 / 1M tokens
RTX 4090 (24 GB)4 GB free	~173 tok/s	$0.55	Deploy on RunPodfrom $0.34/hr (opens in new tab)	24 GB · 4 GB free · ~173 tok/s · $0.55 / 1M tokens
A40 (48 GB)28 GB free	~139 tok/s	$0.70	Deploy on RunPodfrom $0.35/hr (opens in new tab)	48 GB · 28 GB free · ~139 tok/s · $0.70 / 1M tokens
L4 (24 GB)4 GB free	~76 tok/s	$1.60	Deploy on RunPodfrom $0.44/hr (opens in new tab)	24 GB · 4 GB free · ~76 tok/s · $1.60 / 1M tokens

Compare GPUs →

Your own private copy of North Mini Code 1.0 · Q4_K_M · OpenAI-compatible API

Open the llama.cpp listing on RunPod
Open on RunPodServerless (opens in new tab)
New to RunPod? Sign up and add credit first.
2
Fill in the form
Press Deploy and fill in:
Model
unsloth/North-Mini-Code-1.0-GGUF
Quantization
UD-Q4_K_M
Context Size
16384
After pasting the model press Esc — don’t pick a suggestion. Press Next.
Create the endpoint
Keep the default 24 GB and 48 GB, then Create Endpoint. Right away: Manage → Edit endpoint → Max workers 1 → Save (changing settings later restarts the worker).
The first start downloads the model, usually 5–15 min. After that, replies after a pause come in seconds.
Create an API key
RunPod → Settings → API Keys → Create. Pick “Restricted” with access to this endpoint only.

Use it

Copy the endpoint URL from its page on RunPod (any of its links works) and paste it with the key. Both stay in this browser.

Endpoint URL

API key

Chats and keys stay only in this browser.

https://api.runpod.ai/v2/<ENDPOINT_ID>/openai/v1

Put your endpoint ID in place of <ENDPOINT_ID>. The API key is the one from step 2.

from openai import OpenAI
client = OpenAI(base_url="https://api.runpod.ai/v2/<ENDPOINT_ID>/openai/v1", api_key="rpa_...")
r = client.chat.completions.create(
    model="any",
    messages=[{"role": "user", "content": "Hello!"}])
print(r.choices[0].message.content)

Works with any OpenAI client.

https://api.runpod.ai/v2/<ENDPOINT_ID>/openai/v1

Put your endpoint ID in place of <ENDPOINT_ID>. The API key is the one from step 2.

Free on Windows, macOS, Linux, iOS, Android and the web.

Open the web app ↗ (opens in a new tab)Download ↗ (opens in a new tab)

1. Settings → Model Provider → Add → Add Custom Provider
2. API Mode OpenAI API Compatible; paste the API key and the base URL as API Host
3. Model → Fetch, pick the model
4. New chat → pick the provider → start chatting

Free and open source for Windows, macOS and Linux.

Download Jan ↗ (opens in a new tab)

1.Settings → next to Model Providers press +
2.API format OpenAI-compatible; Base URL is the base URL above (with /v1); API key is your key; Create
3.If no model appears, click + in Models and type any
4.New chat → pick the model → start chatting

How Much VRAM Does North Mini Code 1.0 Need?

Select a quantization level; the listed hardware adheres to it.

VRAM	+32K	+128K	File	Quality	On RTX 4090 (reference)
8.8 GB	10.3 GB	15.3 GB	9.8 GB	2-bit · i-quant extreme compression — Importance-weighted 2-bit, extreme compression — significant quality loss	Fits: 256K context · ~241 tok/s
9.6 GB	11.1 GB	16 GB	9.4 GB	2-bit · i-quant extra small — Importance-weighted 2-bit, extra small	Fits: 256K context · ~234 tok/s
9.9 GB	11.5 GB	16.4 GB	9.6 GB	2-bit · i-quant small — Importance-weighted 2-bit, small	Fits: 256K context · ~231 tok/s
10.7 GB	12.2 GB	17.2 GB	9.9 GB	2-bit · i-quant medium — Importance-weighted 2-bit, medium	Fits: 256K context · ~224 tok/s
12.2 GB	13.8 GB	18.7 GB	11.7 GB	3-bit · i-quant — Importance-weighted 3-bit	Fits: 128K context · ~212 tok/s
12.6 GB	14.1 GB	19.1 GB	10.6 GB	2-bit · small K-quant — 2-bit small K-quant	Fits: 128K context · ~209 tok/s
13.0 GB	14.5 GB	19.5 GB	14.2 GB	3-bit · i-quant extra small — Importance-weighted 3-bit, extra small	Fits: 128K context · ~207 tok/s
13.4 GB	14.9 GB	19.8 GB	12.8 GB	3-bit · i-quant small — Importance-weighted 3-bit, small	Fits: 128K context · ~204 tok/s
13.4 GB	14.9 GB	19.8 GB	11.1 GB	2-bit · K-quant — 2-bit quantization with K-quant improvements	Fits: 128K context · ~204 tok/s
13.7 GB	15.3 GB	20.2 GB	13.6 GB	3-bit small — 3-bit small quantization	Fits: 128K context · ~201 tok/s
14.1 GB	15.7 GB	20.6 GB	14.9 GB	3-bit · i-quant medium — Importance-weighted 3-bit, medium	Fits: 128K context · ~199 tok/s
15.3 GB	16.8 GB	21.7 GB	14.2 GB	3-bit medium — 3-bit medium quantization	Fits: 128K context · ~192 tok/s
15.6 GB	17.2 GB	22.1 GB	17.5 GB	4-bit · legacy — 4-bit legacy quantization	Fits: 128K context · ~189 tok/s
16.0 GB	17.6 GB	22.5 GB	14.8 GB	3-bit large — 3-bit large quantization	Fits: 128K context · ~187 tok/s
16.8 GB	18.3 GB	23.3 GB	15.2 GB	4-bit · i-quant compact — Importance-weighted 4-bit, compact	Fits: 128K context · ~183 tok/s
17.6 GB	19.1 GB	24 GB	19.3 GB	4-bit · legacy+ — 4-bit legacy quantization with offset	Fits: 64K context · ~179 tok/s
17.6 GB	19.1 GB	24 GB	18 GB	4-bit small — 4-bit small quantization	Fits: 64K context · ~179 tok/s
17.6 GB	19.1 GB	24 GB	15.5 GB	4-bit · i-quant non-linear — Importance-weighted 4-bit, non-linear	Fits: 64K context · ~179 tok/s
18.7 GB	20.2 GB	25.2 GB	19.2 GB	4-bit medium — 4-bit medium quantization — most popular sweet spot	Fits: 64K context · ~173 tok/s
19.1 GB	20.6 GB	25.5 GB	18.9 GB	4-bit large — 4-bit large quantization	Fits: 64K context · ~171 tok/s
21.4 GB	22.9 GB	27.8 GB	21.6 GB	5-bit small — 5-bit small quantization	Fits: 32K context · ~161 tok/s
22.1 GB	23.7 GB	28.6 GB	22.9 GB	5-bit medium — 5-bit medium quantization — good quality/size tradeoff	Fits: 32K context · ~157 tok/s
22.5 GB	24 GB	29 GB	22 GB	5-bit large — 5-bit large quantization	Fits: 16K context · ~156 tok/s
25.6 GB	27.1 GB	32 GB	25.5 GB	6-bit, very good — 6-bit quantization, very good quality	Does not fit: needs 26.3 GB
30.9 GB	32.4 GB	37.4 GB	32.4 GB	8-bit, near-lossless — 8-bit quantization, near-lossless	Does not fit: needs 31.6 GB
61.4 GB	62.9 GB	67.8 GB	61 GB	16-bit · bfloat — Brain floating point 16 — preferred for training	Does not fit: needs 62.1 GB

Selected Q4_K_M

4-bit medium quantization

19.4GBat 16K context

Weights: 18.3 GB
KV cache: 0.8 GB
Overhead: 0.3 GB

Fits RTX 4090 (reference) · 4.6 GB free · ~173 tok/s

≥50 tok/s needs ≥180 GB/s · RTX 5090 ~226, RTX 3090 Ti ~173

Which Hardware Can Run North Mini Code 1.0?

Q4_K_M · 18.7 GB

North Mini Code 1.0 (Q4_K_M) requires 18.7 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 25+ GB is recommended. Using the full 500K context window can add up to 25.0 GB, bringing total usage to 43.7 GB. 8 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti. 122 devices with unified memory can run North Mini Code 1.0, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB), Mac Mini M5 Pro (24 GB).

By VRAM tier · typical GPUs and Macs at Q4_K_M

Typical hardwareQuantVRAMtok/sContext that fits

8 GB · RTX 4060Doesn't fit — smallest quant needs 9.5 GB8 GB tier →

12 GB · RTX 3060 12GBIQ2_M · 11.4 GB · ~131 tok/s · 16K11.4~13116K12 GB tier →

16 GB · RTX 5060 Ti 16GBQ3_K_M · 16 GB · ~119 tok/s · 16K16~11916K16 GB tier →

24 GB · RTX 4090referenceQ4_K_M · 19.4 GB · ~173 tok/s · 64K19.4~17364K24 GB tier →

Mac 32 GB · Mac Mini M4Q4_K_M · 19.4 GB · ~30 tok/s · 128K19.4~30128KMacs →

Mac 64 GB · Mac Studio M4 MaxQ4_K_M · 19.4 GB · ~66 tok/s · 488K19.4~66488KMacs →

Alternatives to North Mini Code 1.0

Similar models

6tok/s on RTX 4090

Model	Score	VRAM	tok/s	Why it is similar
Hy Memory 30B A3BTencent	—	19.1 GB	~184	same size
Granite Switch 4.1 30BIBM	—	22.7 GB	~35	same size
Llm Jp 4.1 32B A3b Thinkingllm-jp	—	20.1 GB	~188	same size
Muse Glimmer 30BMeta	—	19.6 GB	~36	same size
NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA	—	19.3 GB	~197	same size
Hy MT2 30B A3BTencent	—	19.1 GB	~170	same size

Specifications

Publisher: Cohere
Family: North
Parameters: 30.5B
Active parameters: 3.3B per token
Architecture: Cohere2MoeForCausalLM
Context Length: 500,000 tokens
Vocabulary Size: 262,144
Release Date: 2026-06-05
License: Apache 2.0

Resources

Hugging Face model card (opens in a new tab)

Frequently Asked Questions

How much VRAM does North Mini Code 1.0 need?

North Mini Code 1.0 requires 18.7 GB of VRAM at Q4_K_M, or 61.4 GB at BF16. Full 500K context adds up to 25.0 GB (43.7 GB total).

VRAM = Weights + KV Cache + Overhead

Weights = 30.5B × 4.8 bits ÷ 8 = 18.3 GB

KV Cache + Overhead ≈ 0.4 GB (at 2K context + ~0.3 GB framework)

Fit ratings and hardware model lists check this model with room for a 16K-token context, which needs a little more memory.

KV Cache + Overhead ≈ 25.4 GB (at full 500K context)

VRAM usage by quantization

Q4_K_M

18.7 GB

Q4_K_M + full context

43.7 GB

Learn more about VRAM estimation →

Can NVIDIA GeForce RTX 4090 run North Mini Code 1.0?

Yes, at Q5_K_L (22.5 GB) or lower. Higher quantizations like Q6_K (25.6 GB) exceed the NVIDIA GeForce RTX 4090's 24 GB.

What's the best quantization for North Mini Code 1.0?

For North Mini Code 1.0, Q4_K_M (18.7 GB) offers the best balance of quality and VRAM usage. Q4_K_L (19.1 GB) provides better quality if you have the VRAM. The smallest option is IQ2_XXS at 8.8 GB.

VRAM requirement by quantization

IQ2_XXS

8.8 GB~53%

IQ3_XS

13.0 GB~73%

Q3_K_L

16.0 GB~86%

Q4_K_M ★

18.7 GB~89%

Q4_K_L

19.1 GB~90%

BF16

61.4 GB~100%

★ Recommended — best balance of quality and VRAM usage.

Learn more about quantization →

Can I run North Mini Code 1.0 on a Mac?

Yes — Mac Mini M2 Pro (16 GB) and 133 other Macs can run North Mini Code 1.0, the smallest at IQ2_M. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 18.7 GB of usable unified memory (RAM minus macOS overhead), from Mac Mini M5 Pro (24 GB).

Can I run North Mini Code 1.0 locally?

Yes — North Mini Code 1.0 can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.

How fast is North Mini Code 1.0?

At Q4_K_M, North Mini Code 1.0 can reach ~98 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~173 tok/s. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.

tok/s = 1000 ÷ (active GB ÷ (bandwidth GB/s × efficiency) × 1000 + layers × routing ms)

Mixture-of-Experts: just the active experts get read for each token, along with a fixed routing cost per layer.

Example: NVIDIA B200 → 2.0 GB active ÷ (8000 × 0.65) = 0.390 ms, plus 49 layers × 0.055 ms = 2.695 ms, so 1000 ÷ 3.085 ms = ~324 tok/s

Estimated speed at Q4_K_M (18.7 GB)

NVIDIA B200

~324 tok/s

NVIDIA GeForce RTX 4090

~173 tok/s

NVIDIA B300

~324 tok/s

NVIDIA GH200 Grace Hopper Superchip

~300 tok/s

Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.

Learn more about tok/s estimation →

What's the download size of North Mini Code 1.0?

At Q4_K_M, the download is about 18.29 GB. The full-precision BF16 version is 60.97 GB. The smallest option (IQ2_XXS) is 8.38 GB.

Which GPUs can run North Mini Code 1.0?

8 consumer GPUs can run North Mini Code 1.0 at Q4_K_M. Top options include NVIDIA GeForce RTX 5090, AMD Radeon RX 7900 XT, AMD Radeon RX 7900 XTX. 1 GPU has plenty of headroom for comfortable inference.

Which devices can run North Mini Code 1.0?

122 devices with unified memory can run North Mini Code 1.0 at Q4_K_M (18.7 GB), including AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10, Beelink GTR9 Pro (Ryzen AI Max+ 395, 128 GB), Framework Desktop (Ryzen AI Max+ 395, 128 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.