Mistral NeMo Minitron 8B Base needs about 5.8 GB of memory at IQ3_M (a 4.0 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 25 quants, from 2.1 GB (IQ1_S) to 16.8 GB.
Mistral-NeMo-Minitron 8B Base – a compact text‑to‑text LLM
Mistral-NeMo-Minitron 8B Base is a 8.41‑billion‑parameter model derived from Mistral‑NeMo 12B. It supports up to 8192 context tokens and is available in multiple GGUF quantizations. The model is released under the NVIDIA Open Model License Agreement.
Good at
- Text generation
- Multilingual support
- Code‑aware responses
Limits
- No vision support
- Requires 8k context or less
- License is NVIDIA Open Model License
Best for
- Chatbots on modest GPUs
- Lightweight code generation
- Academic research demos
Who it’s for. Developers and researchers who need a smaller, efficient LLM for text‑only tasks. The model is suitable for environments with limited VRAM and for use with llama.cpp or NeMo 24.05.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 2.1 GB | 4.0 GB | Fits | Get file → | |
| IQ1_M | 2.3 GB | 4.1 GB | Fits | Get file → | |
| IQ2_XXS | 2.5 GB | 4.4 GB | Fits | Get file → | |
| IQ2_XS | 2.7 GB | 4.6 GB | Fits | Get file → | |
| IQ2_S | 2.9 GB | 4.7 GB | Fits | Get file → | |
| IQ2_M | 3.1 GB | 4.9 GB | Fits | Get file → | |
| Q2_K_S | 3.1 GB | 5.0 GB | Fits | Get file → | |
| Q2_K | 3.3 GB | 5.2 GB | Fits | Get file → | |
| IQ3_XXS | 3.4 GB | 5.3 GB | Fits | Get file → | |
| IQ3_XS | 3.7 GB | 5.5 GB | Fits | Get file → | |
| Q3_K_S | 3.8 GB | 5.7 GB | Fits | Get file → | |
| IQ3_S | 3.9 GB | 5.7 GB | Fits | Get file → | |
| IQ3_M | 4.0 GB | 5.8 GB | Fits | Get file → | |
| Q3_K | 4.2 GB | 6.1 GB | Fits | Get file → | |
| Q3_K_L | 4.5 GB | 6.4 GB | Fits | Get file → | |
| IQ4_XS | 4.7 GB | 6.5 GB | Fits | Get file → | |
| IQ4_NL | 4.9 GB | 6.7 GB | Fits | Get file → | |
| Q4_K_S | 4.9 GB | 6.8 GB | Fits | Get file → | |
| Q4_K | 5.1 GB | 7.0 GB | Fits | Get file → | |
| Q5_K_S | 5.9 GB | 7.7 GB | Tight | Get file → | |
| Q5_K | 6.0 GB | 7.8 GB | Tight | Get file → | |
| Q6_K | 6.9 GB | 8.8 GB | Too big | Get file → | |
| Q8_0 | 8.9 GB | 10.8 GB | Too big | Get file → | |
| BF16 | 16.8 GB | 18.7 GB | Too big | Get file → | |
| — | 16.8 GB | 18.7 GB | Too big | Get file → |
For 8 GB VRAM, use IQ1_S (2.12 GB, 4 GB memory) or IQ1_M (2.27 GB, 4.1 GB memory). If 12 GB is available, Q2_K (3.33 GB, 5.2 GB memory) or Q3_K (4.21 GB, 6.1 GB memory) provide higher quality. Larger models such as Q5_K or Q6_K need 18 GB or more.
What GPU do you need for Mistral NeMo Minitron 8B Base?
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: the best quant that fits is IQ1_S (2.1 GB file, about 4.0 GB in use).
- 6 GB VRAM: the best quant that fits is IQ3_M (4.0 GB file, about 5.8 GB in use).
- 8 GB VRAM: the best quant that fits is Q5_K (6.0 GB file, about 7.8 GB in use).
- 12 GB VRAM: the best quant that fits is Q8_0 (8.9 GB file, about 10.8 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_0 (8.9 GB file, about 10.8 GB in use).
- 24 GB VRAM: the best quant that fits is BF16 (16.8 GB file, about 18.7 GB in use).
Which Mistral NeMo Minitron 8B Base quant should you choose?
IQ3_M (4.0 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
If memory is tight, the smallest file is IQ1_S at 2.1 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 Mistral NeMo Minitron 8B Base
How much VRAM does Mistral NeMo Minitron 8B Base need?
About 5.8 GB at IQ3_M with an 8K context window. That is the 4.0 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 Mistral NeMo Minitron 8B Base on an 8 GB GPU?
Yes, with Q5_K: the 6.0 GB file needs about 7.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Mistral NeMo Minitron 8B Base GGUF?
It depends on the quant: IQ1_S is 2.1 GB, IQ1_M is 2.3 GB, IQ2_XXS is 2.5 GB, IQ2_XS is 2.7 GB, IQ2_S is 2.9 GB, IQ2_M is 3.1 GB and 19 more.
What context length does Mistral NeMo Minitron 8B Base support?
The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 1.3 GB at 8K and 1.3 GB at 8K.
Where can I download Mistral NeMo Minitron 8B Base GGUF?
The files are on Hugging Face in the legraphista/Mistral-NeMo-Minitron-8B-Base-IMat-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 Mistral NeMo Minitron 8B Base use?
Hugging Face lists the license as other. 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 this model on 8 GB VRAM?
Yes, the IQ1_S or IQ1_M quantizations fit within 8 GB VRAM and use about 4 GB of memory at 8k context.
Does this model support image input?
No, the model only accepts text input and does not have vision capabilities.
What license applies to this model?
It is released under the NVIDIA Open Model License Agreement.