Flux2Mistral needs about 12.7 GB of memory at Q4_K_M (a 10.9 GB file) with an 8K context window, so it fits on a 16 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.
Flux2Mistral – 18B llama-based model with tool‑use capability
Flux2Mistral is an 18B parameter llama architecture model trained on 131072 context tokens. It supports tool usage and is available as a Q4_K_M quantized GGUF file. The model is derived from Flux and Mistral components.
Good at
- Tool integration
- Large context handling
- Efficient inference with Q4_K_M
Limits
- No vision support
- Requires 12.7GB VRAM at 8k context
- No license information provided
Best for
- Tool‑enabled text generation
- Long‑form content with 131072 token context
- Low‑memory inference on GPUs with 12.7GB VRAM
Who it’s for. Developers needing a lightweight, tool‑aware LLM for text tasks. Suitable for projects that can run the Q4_K_M quantized model on GPUs with at least 12.7GB VRAM.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 10.9 GB | 12.7 GB | Too big | Get file → |
The only available quant is Q4_K_M, file size 10.9GB. It requires approximately 12.7GB VRAM at 8k context. For lower VRAM budgets, no other quant is provided.
What GPU do you need for Flux2Mistral?
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: no quant fits at an 8K context.
- 12 GB VRAM: no quant fits at an 8K context.
- 16 GB VRAM: the best quant that fits is Q4_K_M (10.9 GB file, about 12.7 GB in use).
Which Flux2Mistral quant should you choose?
Q4_K_M is the usual starting point for Flux2Mistral: it balances file size and quality well. Here it is a 10.9 GB file.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Flux2Mistral
How much VRAM does Flux2Mistral need?
About 12.7 GB at Q4_K_M with an 8K context window. That is the 10.9 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 Flux2Mistral on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 12.7 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Flux2Mistral GGUF?
It depends on the quant: Q4_K_M is 10.9 GB.
What context length does Flux2Mistral support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.3 GB at 8K and 5.4 GB at 32K.
Where can I download Flux2Mistral GGUF?
The files are on Hugging Face in the mcmonkey/Flux2MistralGGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
Can I run Flux2Mistral on 8 GB VRAM?
No, the Q4_K_M quant requires about 12.7GB VRAM at 8k context, so 8GB is insufficient.
Does Flux2Mistral have vision capabilities?
No, the model does not support vision.