North Mini Code 1.0 needs about 19.9 GB of memory at Q4_K_M (a 18.6 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 10 quants, from 8.3 GB (IQ2_XXS) to 61.0 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 3.3 GB.
30B total, 3B active sparse MoE code model
North Mini Code 1.0 is a 30.5B total, 3B active sparse MoE model optimized for code generation and terminal tasks. It uses the cohere2moe architecture and is released under Apache 2.0.
Good at
- Code generation
- Agentic software engineering
- Terminal tool use
Limits
- No vision support
- Requires cohere2moe support in llama.cpp
- Large VRAM needed for higher quant levels
Best for
- Developing coding assistants
- Automating terminal workflows
- Testing code generation benchmarks
Who it’s for. Engineers and researchers needing a lightweight code model with MoE capabilities. Suitable for developers who can run llama.cpp with cohere2moe support and have sufficient GPU memory.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ2_XXS | 8.3 GB | 9.6 GB | Too big | Get file → | |
| IQ2_XS | 9.2 GB | 10.5 GB | Too big | Get file → | |
| IQ2_M | 10.3 GB | 11.6 GB | Too big | Get file → | |
| IQ3_M | 13.6 GB | 14.9 GB | Too big | Get file → | |
| IQ4_XS | 16.4 GB | 17.7 GB | Too big | Get file → | |
| Q4_K_M | 18.6 GB | 19.9 GB | Too big | Get file → | |
| Q5_K_M | 21.7 GB | 23.0 GB | Too big | Get file → | |
| Q6_K | 25.1 GB | 26.4 GB | Too big | Get file → | |
| Q8_0 | 32.4 GB | 33.8 GB | Too big | Get file → | |
| BF16 | 61.0 GB (2 parts) | 62.3 GB | Too big | Get file → |
For 8 GB VRAM, use IQ2_XXS (file size 8.31 GB, estimated 9.6 GB memory). For 12 GB VRAM, IQ2_XS (9.21 GB, 10.5 GB memory). For 16 GB VRAM, IQ4_XS (16.41 GB, 17.7 GB memory).
What GPU do you need for North Mini Code 1.0?
These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: no quant fits at an 8K context.
- 6 GB VRAM: no quant fits at an 8K context.
- 8 GB VRAM: no quant fits at an 8K context.
- 12 GB VRAM: the best quant that fits is IQ2_M (10.3 GB file, about 11.6 GB in use).
- 16 GB VRAM: the best quant that fits is IQ3_M (13.6 GB file, about 14.9 GB in use).
- 24 GB VRAM: the best quant that fits is Q5_K_M (21.7 GB file, about 23.0 GB in use).
- 32 GB VRAM: the best quant that fits is Q6_K (25.1 GB file, about 26.4 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_0 (32.4 GB file, about 33.8 GB in use).
Which North Mini Code 1.0 quant should you choose?
Q4_K_M is the usual starting point for North Mini Code 1.0: it balances file size and quality well. Here it is a 18.6 GB file.
The Q8_0 file is 32.4 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
If memory is tight, the smallest file is IQ2_XXS at 8.3 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about North Mini Code 1.0
How much VRAM does North Mini Code 1.0 need?
About 19.9 GB at Q4_K_M with an 8K context window. That is the 18.6 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run North Mini Code 1.0 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 9.6 GB, so you would need a larger GPU or CPU offloading.
What is the file size of North Mini Code 1.0 GGUF?
It depends on the quant: IQ2_XXS is 8.3 GB, IQ2_XS is 9.2 GB, IQ2_M is 10.3 GB, IQ3_M is 13.6 GB, IQ4_XS is 16.4 GB, Q4_K_M is 18.6 GB and 4 more.
What context length does North Mini Code 1.0 support?
The GGUF header lists a trained context length of 500,000 tokens (488K). The KV cache grows with the context you use: about 0.8 GB at 8K and 3.3 GB at 32K.
Where can I download North Mini Code 1.0 GGUF?
The files are on Hugging Face in the Arki05/North-Mini-Code-1.0-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does North Mini Code 1.0 use?
Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.
Can I run North Mini Code on 8 GB VRAM?
Yes, the IQ2_XXS quant requires about 9.6 GB memory at 8k context, which fits within 8 GB VRAM with some overhead.
Does this model support vision tasks?
No, North Mini Code is a code-only model with no vision capabilities.
What license applies to the GGUF weights?
The GGUF weights are released under Apache 2.0, matching the parent model license.