Mpt 30b needs about 30.9 GB of memory at Q4_K_M (a 19.1 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 21 quants, from 6.4 GB (IQ1_S) to 24.6 GB (Q6_K).
Mpt 30b – 30‑billion‑parameter language model in GGUF format
Mpt 30b is a 30‑billion‑parameter model from the Mpt family, based on mosaicml/mpt-30b. It supports a context length of 8192 tokens and is released under the Apache‑2.0 license. The model is available in multiple quantizations for use with llama.cpp.
Good at
- Large context handling
- High‑capacity language modeling
- Versatile quantization options
Limits
- No vision support
- Requires significant VRAM for higher‑quality quants
- License is Apache‑2.0
Best for
- Research prototyping
- Fine‑tuning large language models
- Running on high‑end GPUs
Who it’s for. Developers and researchers who need a large language model with a long context window and who have access to GPUs with ample VRAM. The model is suitable for tasks that require detailed text generation and analysis.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 6.4 GB | 18.1 GB | Too big | Get file → | |
| IQ1_M | 7.0 GB | 18.7 GB | Too big | Get file → | |
| IQ2_XXS | 8.0 GB | 19.7 GB | Too big | Get file → | |
| IQ2_XS | 8.9 GB | 20.6 GB | Too big | Get file → | |
| IQ2_S | 9.3 GB | 21.1 GB | Too big | Get file → | |
| IQ2_M | 10.1 GB | 21.9 GB | Too big | Get file → | |
| Q2_K | 11.3 GB | 23.0 GB | Too big | Get file → | |
| IQ3_XXS | 11.7 GB | 23.5 GB | Too big | Get file → | |
| IQ3_XS | 12.7 GB | 24.4 GB | Too big | Get file → | |
| IQ3_S | 13.0 GB | 24.8 GB | Too big | Get file → | |
| Q3_K_S | 13.0 GB | 24.8 GB | Too big | Get file → | |
| IQ3_M | 14.5 GB | 26.3 GB | Too big | Get file → | |
| Q3_K_M | 15.7 GB | 27.5 GB | Too big | Get file → | |
| IQ4_XS | 16.0 GB | 27.8 GB | Too big | Get file → | |
| Q4_0 | 17.0 GB | 28.8 GB | Too big | Get file → | |
| Q4_K_S | 17.1 GB | 28.9 GB | Too big | Get file → | |
| Q3_K_L | 17.2 GB | 29.0 GB | Too big | Get file → | |
| Q4_K_M | 19.1 GB | 30.9 GB | Too big | Get file → | |
| Q5_K_S | 20.6 GB | 32.4 GB | Too big | Get file → | |
| Q5_K_M | 22.3 GB | 34.1 GB | Too big | Get file → | |
| Q6_K | 24.6 GB | 36.4 GB | Too big | Get file → |
For 8 GB VRAM, use IQ1_S (6.35 GB file, 18.1 GB memory). If 12 GB VRAM is available, IQ2_XS (8.86 GB file, 20.6 GB memory) is a good balance. For 24 GB VRAM, Q4_K_M (19.14 GB file, 30.9 GB memory) offers higher quality. Estimates are approximate.
What GPU do you need for Mpt 30b?
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: no quant fits at an 8K context.
- 16 GB VRAM: no quant fits at an 8K context.
- 24 GB VRAM: the best quant that fits is IQ3_XXS (11.7 GB file, about 23.5 GB in use).
- 32 GB VRAM: the best quant that fits is Q4_K_M (19.1 GB file, about 30.9 GB in use).
- 48 GB VRAM: the best quant that fits is Q6_K (24.6 GB file, about 36.4 GB in use).
Which Mpt 30b quant should you choose?
Q4_K_M is the usual starting point for Mpt 30b: it balances file size and quality well. Here it is a 19.1 GB file.
If memory is tight, the smallest file is IQ1_S at 6.4 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 Mpt 30b
How much VRAM does Mpt 30b need?
About 30.9 GB at Q4_K_M with an 8K context window. That is the 19.1 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 Mpt 30b on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 18.1 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Mpt 30b GGUF?
It depends on the quant: IQ1_S is 6.4 GB, IQ1_M is 7.0 GB, IQ2_XXS is 8.0 GB, IQ2_XS is 8.9 GB, IQ2_S is 9.3 GB, IQ2_M is 10.1 GB and 15 more.
What context length does Mpt 30b support?
The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 11.3 GB at 8K and 11.3 GB at 8K.
Where can I download Mpt 30b GGUF?
The files are on Hugging Face in the mradermacher/mpt-30b-i1-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 Mpt 30b 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 Mpt 30b on 8 GB VRAM?
Use the IQ1_S quant, which requires about 18.1 GB memory at 8k context. 8 GB VRAM is insufficient for any quant of this model.
Does Mpt 30b support vision tasks?
No, the model has no vision capabilities.
What license applies to Mpt 30b?
The model is released under the Apache‑2.0 license.