Mistral v0.3 6B i1 needs about 5.0 GB of memory at Q4_K_M (a 3.6 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 25 quants, from 0.0 GB to 4.9 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 3.5 GB.
Mistral v0.3 6B i1 – a fine‑tuned 5.94B parameter model in GGUF format
Mistral v0.3 6B i1 is a 5.94B parameter model fine‑tuned from pszemraj/Mistral‑v0.3‑6B on the None dataset. It supports a 32768 token context window and is released under the apache‑2.0 license. The model is available in multiple GGUF quantizations.
Good at
- Fine‑tuned language generation
- Large context support
- Low‑latency inference
Limits
- No vision capability
- Requires 8k context for memory estimates
- No mixture of experts
Best for
- Chatbot back‑ends
- Code completion
- Text summarisation
Who it’s for. Developers and researchers who need a lightweight, high‑capacity language model for local deployment. The model is suitable for projects that require a 32768 token context window and can run on consumer GPUs with moderate VRAM.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 1.4 GB | Fits | Get file → | |
| IQ1_S | 1.3 GB | 2.7 GB | Fits | Get file → | |
| IQ1_M | 1.5 GB | 2.8 GB | Fits | Get file → | |
| IQ2_XXS | 1.6 GB | 3.0 GB | Fits | Get file → | |
| IQ2_XS | 1.8 GB | 3.2 GB | Fits | Get file → | |
| IQ2_S | 1.9 GB | 3.3 GB | Fits | Get file → | |
| IQ2_M | 2.1 GB | 3.4 GB | Fits | Get file → | |
| Q2_K_S | 2.1 GB | 3.5 GB | Fits | Get file → | |
| Q2_K | 2.2 GB | 3.6 GB | Fits | Get file → | |
| IQ3_XXS | 2.3 GB | 3.7 GB | Fits | Get file → | |
| IQ3_XS | 2.5 GB | 3.9 GB | Fits | Get file → | |
| Q3_K_S | 2.6 GB | 4.0 GB | Fits | Get file → | |
| IQ3_S | 2.6 GB | 4.0 GB | Fits | Get file → | |
| IQ3_M | 2.7 GB | 4.1 GB | Fits | Get file → | |
| Q3_K_M | 2.9 GB | 4.3 GB | Fits | Get file → | |
| Q3_K_L | 3.1 GB | 4.5 GB | Fits | Get file → | |
| IQ4_XS | 3.2 GB | 4.6 GB | Fits | Get file → | |
| Q4_0 | 3.4 GB | 4.8 GB | Fits | Get file → | |
| IQ4_NL | 3.4 GB | 4.8 GB | Fits | Get file → | |
| Q4_K_S | 3.4 GB | 4.8 GB | Fits | Get file → | |
| Q4_K_M | 3.6 GB | 5.0 GB | Fits | Get file → | |
| Q4_1 | 3.7 GB | 5.1 GB | Fits | Get file → | |
| Q5_K_S | 4.1 GB | 5.5 GB | Fits | Get file → | |
| Q5_K_M | 4.2 GB | 5.6 GB | Fits | Get file → | |
| Q6_K | 4.9 GB | 6.2 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_K_M (3.59 GB file, 5 GB memory at 8k context). If 12 GB VRAM is available, Q5_K_M (4.21 GB file, 5.6 GB memory) offers higher precision. For 16 GB VRAM, Q6_K (4.87 GB file, 6.2 GB memory) provides the best quality.
What GPU do you need for Mistral v0.3 6B i1?
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 IQ3_S (2.6 GB file, about 4.0 GB in use).
- 6 GB VRAM: the best quant that fits is Q5_K_M (4.2 GB file, about 5.6 GB in use).
- 8 GB VRAM: the best quant that fits is Q6_K (4.9 GB file, about 6.2 GB in use).
Which Mistral v0.3 6B i1 quant should you choose?
Q4_K_M is the usual starting point for Mistral v0.3 6B i1: it balances file size and quality well. Here it is a 3.6 GB file.
If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Mistral v0.3 6B i1
How much VRAM does Mistral v0.3 6B i1 need?
About 5.0 GB at Q4_K_M with an 8K context window. That is the 3.6 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 Mistral v0.3 6B i1 on an 8 GB GPU?
Yes, with Q6_K: the 4.9 GB file needs about 6.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Mistral v0.3 6B i1 GGUF?
It depends on the quant: file is 0.0 GB, IQ1_S is 1.3 GB, IQ1_M is 1.5 GB, IQ2_XXS is 1.6 GB, IQ2_XS is 1.8 GB, IQ2_S is 1.9 GB and 19 more.
What context length does Mistral v0.3 6B i1 support?
The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.9 GB at 8K and 3.5 GB at 32K.
Where can I download Mistral v0.3 6B i1 GGUF?
The files are on Hugging Face in the mradermacher/Mistral-v0.3-6B-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 Mistral v0.3 6B i1 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 Mistral v0.3 6B i1 on 8 GB VRAM?
Yes, the Q4_K_M quant requires 3.59 GB file size and estimates 5 GB memory at 8k context, which fits 8 GB VRAM.
Does this model support vision tasks?
No, the model has no vision capability.
What license applies to this model?
The model is released under the apache‑2.0 license.