Candle llava v1.6 mistral 7b needs about 6.3 GB of memory at its main file (a 5.2 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 13 quants, from 2.5 GB to 15.1 GB (F16).
Candle llava v1.6 mistral 7b – a 7.57B parameter LLM
Candle llava v1.6 mistral 7b is a 7.57B parameter model released under the apache-2.0 license. It is a Mistral family model with no mixture of experts. The model is available in several GGUF quantizations.
Good at
- Large context handling
- Versatile language tasks
- Compact quant options
Limits
- No vision support
- Requires 8k context for estimates
- License is apache-2.0
Best for
- Chat applications
- Text generation
- Lightweight inference
Who it’s for. Developers needing a small yet capable LLM for local deployment. The model is suitable for projects that require a balance between performance and memory usage.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 2.5 GB | 3.3 GB | Fits | Get file → | |
| — | 3.3 GB | 4.1 GB | Fits | Get file → | |
| Q4_0 | 4.3 GB | 5.3 GB | Fits | Get file → | |
| — | 4.3 GB | 5.3 GB | Fits | Get file → | |
| Q4_1 | 4.7 GB | 5.8 GB | Fits | Get file → | |
| Q5_0 | 5.2 GB | 6.3 GB | Fits | Get file → | |
| — | 5.2 GB | 6.3 GB | Fits | Get file → | |
| Q5_1 | 5.7 GB | 6.9 GB | Fits | Get file → | |
| — | 6.2 GB | 7.5 GB | Tight | Get file → | |
| Q8_0 | 8.0 GB | 9.5 GB | Too big | Get file → | |
| Q8_1 | 8.5 GB | 10.0 GB | Too big | Get file → | |
| — | 8.6 GB | 10.2 GB | Too big | Get file → | |
| F16 | 15.1 GB | 17.5 GB | Too big | Get file → |
For 8GB VRAM, use Q4_0 (est. 5.3GB) or Q4_1 (est. 5.8GB). For 12GB VRAM, Q5_0 (est. 6.3GB) or Q5_1 (est. 6.9GB) are suitable. Higher precision Q8_0 or Q8_1 requires 9.5GB or 10GB respectively.
What GPU do you need for Candle llava v1.6 mistral 7b?
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 the main file (2.5 GB file, about 3.3 GB in use).
- 6 GB VRAM: the best quant that fits is Q4_1 (4.7 GB file, about 5.8 GB in use).
- 8 GB VRAM: the best quant that fits is the main file (6.2 GB file, about 7.5 GB in use).
- 12 GB VRAM: the best quant that fits is the main file (8.6 GB file, about 10.2 GB in use).
- 16 GB VRAM: the best quant that fits is the main file (8.6 GB file, about 10.2 GB in use).
- 24 GB VRAM: the best quant that fits is F16 (15.1 GB file, about 17.5 GB in use).
Which Candle llava v1.6 mistral 7b quant should you choose?
If memory is tight, the smallest file is the first one in the table at 2.5 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 Candle llava v1.6 mistral 7b
How much VRAM does Candle llava v1.6 mistral 7b need?
About 6.3 GB at its main file with an 8K context window. That is the 5.2 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 Candle llava v1.6 mistral 7b on an 8 GB GPU?
Yes, with the smaller files: the 6.2 GB file needs about 7.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Candle llava v1.6 mistral 7b GGUF?
It depends on the quant: file is 2.5 GB, file is 3.3 GB, Q4_0 is 4.3 GB, file is 4.3 GB, Q4_1 is 4.7 GB, Q5_0 is 5.2 GB and 7 more.
Where can I download Candle llava v1.6 mistral 7b GGUF?
The files are on Hugging Face in the DanielClough/Candle_llava-v1.6-mistral-7b repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Candle llava v1.6 mistral 7b 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 this model on 8GB VRAM?
Yes, the Q4_0 quantization uses about 5.3GB of VRAM at 8k context, which fits within 8GB. The Q4_1 quantization uses about 5.8GB.
What is the smallest quant available?
The smallest file is 2.49GB with an unknown quant, estimated to use 3.3GB of VRAM at 8k context.
Does this model support vision tasks?
No, the model does not have vision capabilities.