dragon mistral 7b v0 needs about 5.9 GB of memory at Q4_K_M (a 4.4 GB file) with an 8K context window, so it fits on a 6 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.
Dragon Mistral 7B v0 – fact‑based RAG model for enterprise QA
Dragon Mistral 7B v0 is a 7.24 billion‑parameter Mistral‑based model fine‑tuned for RAG‑instruct tasks. It delivers accurate, short answers over complex business and legal documents. The model is released under Apache 2.0.
Good at
- Fact‑based question answering
- RAG key‑value extraction
- Basic summarization
Limits
- Requires 5.9 GB VRAM at 8 k context
- Only Q4_K_M quant available
- No vision support
Best for
- Enterprise automation workflows
- Financial and legal document QA
- RAG‑based knowledge extraction
Who it’s for. Developers building enterprise applications that need reliable, concise answers from large documents. The model is suited for teams in finance, legal, and regulatory sectors requiring low hallucination rates.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 4.4 GB | 5.9 GB | Fits | Get file → |
For 8 GB VRAM, use the Q4_K_M quant (4.37 GB file). It will need approximately 5.9 GB VRAM at 8 k context. No other quantizations are provided.
What GPU do you need for dragon mistral 7b v0?
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: the best quant that fits is Q4_K_M (4.4 GB file, about 5.9 GB in use).
Which dragon mistral 7b v0 quant should you choose?
Q4_K_M is the usual starting point for dragon mistral 7b v0: it balances file size and quality well. Here it is a 4.4 GB file.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about dragon mistral 7b v0
How much VRAM does dragon mistral 7b v0 need?
About 5.9 GB at Q4_K_M with an 8K context window. That is the 4.4 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 dragon mistral 7b v0 on an 8 GB GPU?
Yes, with Q4_K_M: the 4.4 GB file needs about 5.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of dragon mistral 7b v0 GGUF?
It depends on the quant: Q4_K_M is 4.4 GB.
What context length does dragon mistral 7b v0 support?
The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.
Where can I download dragon mistral 7b v0 GGUF?
The files are on Hugging Face in the llmware/dragon-mistral-7b-v0 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does dragon mistral 7b v0 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 8 GB VRAM?
Yes, the Q4_K_M quant uses about 5.9 GB VRAM at 8 k context, fitting within an 8 GB GPU.
Does it support multiple languages?
The model is trained for English only; no other languages are supported.
Is it suitable for legal document QA?
Yes, it is fine‑tuned for fact‑based QA over complex legal documents with low hallucination.