Mistral 7B Instruct v0.3 needs about 12.9 GB of memory at Q4_K_M (a 9.9 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 21 quants, from 3.6 GB (IQ1_S) to 13.5 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 9.9 GB.
Mistral 7B Instruct v0.3 – a 16.4B parameter instruction model
Mistral 7B Instruct v0.3 is a 16.4B parameter model merged from Mistral‑7B‑Instruct‑v0.3. It supports a 32768 token context window and is quantized into multiple GGUF variants. The model is available in a range of IQ and Q quantizations.
Good at
- Instruction following
- Tool usage
- Large context handling
Limits
- No vision support
- No license specified
- Large VRAM needed for higher quants
Best for
- Chatbots with long context
- Code generation with tool calls
- Research prototyping
Who it’s for. Developers and researchers who need a large‑context instruction model and can run GGUF files locally. The model is suitable for applications that require tool integration and extended dialogue history.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 3.6 GB | 6.5 GB | Fits | Get file → | |
| IQ1_M | 3.9 GB | 6.9 GB | Fits | Get file → | |
| IQ2_XXS | 4.4 GB | 7.4 GB | Tight | Get file → | |
| IQ2_XS | 4.9 GB | 7.9 GB | Tight | Get file → | |
| IQ2_S | 5.2 GB | 8.1 GB | Too big | Get file → | |
| IQ2_M | 5.6 GB | 8.6 GB | Too big | Get file → | |
| Q2_K | 6.1 GB | 9.1 GB | Too big | Get file → | |
| IQ3_XXS | 6.3 GB | 9.3 GB | Too big | Get file → | |
| IQ3_XS | 6.8 GB | 9.8 GB | Too big | Get file → | |
| Q3_K_S | 7.1 GB | 10.1 GB | Too big | Get file → | |
| IQ3_S | 7.1 GB | 10.1 GB | Too big | Get file → | |
| IQ3_M | 7.4 GB | 10.4 GB | Too big | Get file → | |
| Q3_K_M | 7.9 GB | 10.9 GB | Too big | Get file → | |
| Q3_K_L | 8.6 GB | 11.6 GB | Too big | Get file → | |
| IQ4_XS | 8.8 GB | 11.8 GB | Too big | Get file → | |
| Q4_0 | 9.3 GB | 12.3 GB | Too big | Get file → | |
| Q4_K_S | 9.3 GB | 12.3 GB | Too big | Get file → | |
| Q4_K_M | 9.9 GB | 12.9 GB | Too big | Get file → | |
| Q5_K_S | 11.3 GB | 14.3 GB | Too big | Get file → | |
| Q5_K_M | 11.6 GB | 14.6 GB | Too big | Get file → | |
| Q6_K | 13.5 GB | 16.4 GB | Too big | Get file → |
For 8 GB VRAM, use IQ1_S (3.55 GB, 6.5 GB memory at 8 k context) or IQ1_M (3.88 GB, 6.9 GB memory). For 12 GB VRAM, IQ4_0 (9.3 GB, 12.3 GB memory) or Q4_K_S (9.34 GB, 12.3 GB memory) are suitable. Higher quants like Q5_K_M (11.61 GB, 14.6 GB memory) require 16 GB or more.
What GPU do you need for Mistral 7B Instruct v0.3?
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: the best quant that fits is IQ2_XS (4.9 GB file, about 7.9 GB in use).
- 12 GB VRAM: the best quant that fits is IQ4_XS (8.8 GB file, about 11.8 GB in use).
- 16 GB VRAM: the best quant that fits is Q5_K_M (11.6 GB file, about 14.6 GB in use).
- 24 GB VRAM: the best quant that fits is Q6_K (13.5 GB file, about 16.4 GB in use).
Which Mistral 7B Instruct v0.3 quant should you choose?
Q4_K_M is the usual starting point for Mistral 7B Instruct v0.3: it balances file size and quality well. Here it is a 9.9 GB file.
If memory is tight, the smallest file is IQ1_S at 3.6 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
Frequently asked questions about Mistral 7B Instruct v0.3
How much VRAM does Mistral 7B Instruct v0.3 need?
About 12.9 GB at Q4_K_M with an 8K context window. That is the 9.9 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 7B Instruct v0.3 on an 8 GB GPU?
Yes, with IQ2_XS: the 4.9 GB file needs about 7.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Mistral 7B Instruct v0.3 GGUF?
It depends on the quant: IQ1_S is 3.6 GB, IQ1_M is 3.9 GB, IQ2_XXS is 4.4 GB, IQ2_XS is 4.9 GB, IQ2_S is 5.2 GB, IQ2_M is 5.6 GB and 15 more.
What context length does Mistral 7B Instruct v0.3 support?
The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 2.5 GB at 8K and 9.9 GB at 32K.
Where can I download Mistral 7B Instruct v0.3 GGUF?
The files are on Hugging Face in the mradermacher/Ryze-Mistral-7B-Instruct-v0.3-10-i1-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
Can I run this model on 8 GB VRAM?
Yes, use IQ1_S or IQ1_M quantizations; they use about 6.5–6.9 GB memory at 8 k context.
Does this model support vision?
No, the model has no vision capabilities.
What is the maximum context length?
The model supports 32768 tokens of context.