M3 needs about 2.9 GB of memory at Q4_K_M (a 2.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 4 quants, from 1.4 GB (Q2_K) to 2.4 GB (Q2_K).
M3 is a 5.69B-parameter Emerald model in GGUF format, quantized by Emerald7664. Its trained context length is 10K tokens. The repository has 4 quant files, from 1.4 GB (Q2_K) to 2.4 GB (Q2_K).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 1.4 GB | 2.1 GB | Fits | Get file → | |
| Q4_K_M | 2.1 GB | 2.9 GB | Fits | Get file → | |
| Q2_K | 2.4 GB | 3.2 GB | Fits | Get file → | |
| Q2_K | 2.4 GB | 3.2 GB | Fits | Get file → |
What GPU do you need for M3?
These figures add the file size, an fp16 KV cache at an 8K context window 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: the best quant that fits is Q2_K (2.4 GB file, about 3.2 GB in use).
Which M3 quant should you choose?
Q4_K_M is the usual starting point for M3: it balances file size and quality well. Here it is a 2.1 GB file.
If memory is tight, the smallest file is Q2_K at 1.4 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 M3
How much VRAM does M3 need?
About 2.9 GB at Q4_K_M with an 8K context window. That is the 2.1 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 M3 on an 8 GB GPU?
Yes, with Q2_K: the 2.4 GB file needs about 3.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of M3 GGUF?
It depends on the quant: Q2_K is 1.4 GB, Q4_K_M is 2.1 GB, Q2_K is 2.4 GB, Q2_K is 2.4 GB.
What context length does M3 support?
The GGUF header lists a trained context length of 10,240 tokens (10K).
Where can I download M3 GGUF?
The files are on Hugging Face in the Emerald7664/M3 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does M3 use?
Hugging Face lists the license as MiniMax-Music3 Community License. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.