Mixtral 13Bx2 MOE 22B i1 needs about 20.2 GB of memory at Q4_K_M (a 13.0 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 23 quants, from 4.6 GB (IQ1_S) to 17.6 GB (Q6_K).
Mixtral 13Bx2 MOE 22B i1 – 21.5B parameter LLM with mixture of experts
Mixtral 13Bx2 MOE 22B i1 is a 21.5B parameter model built on the Mistral family. It uses a 4096 token context window and is available in multiple GGUF quantizations. The model is licensed under cc‑by‑nc‑4.0.
Good at
- Large context reasoning
- Mixture of experts for diverse outputs
- High token throughput
Limits
- No vision support
- Requires 8‑k context for memory estimates
- cc‑by‑nc‑4.0 license
Best for
- Chatbot development
- Research prototyping
- Content generation
Who it’s for. Developers and researchers who need a large LLM with expert routing and can work within a 4096 token context. The model is suitable for non‑commercial use only due to its license.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 4.6 GB | 8.5 GB | Too big | Get file → | |
| IQ1_M | 5.0 GB | 8.9 GB | Too big | Get file → | |
| IQ2_XXS | 5.8 GB | 9.6 GB | Too big | Get file → | |
| IQ2_XS | 6.4 GB | 10.2 GB | Too big | Get file → | |
| IQ2_S | 6.7 GB | 10.6 GB | Too big | Get file → | |
| IQ2_M | 7.3 GB | 11.1 GB | Too big | Get file → | |
| Q2_K_S | 7.3 GB | 11.2 GB | Too big | Get file → | |
| Q2_K | 7.9 GB | 11.8 GB | Too big | Get file → | |
| IQ3_XXS | 8.2 GB | 12.1 GB | Too big | Get file → | |
| IQ3_XS | 8.8 GB | 12.7 GB | Too big | Get file → | |
| IQ3_S | 9.3 GB | 13.2 GB | Too big | Get file → | |
| Q3_K_S | 9.3 GB | 13.2 GB | Too big | Get file → | |
| IQ3_M | 9.7 GB | 13.5 GB | Too big | Get file → | |
| Q3_K_M | 10.4 GB | 14.2 GB | Too big | Get file → | |
| Q3_K_L | 11.3 GB | 15.2 GB | Too big | Get file → | |
| IQ4_XS | 11.5 GB | 15.3 GB | Too big | Get file → | |
| Q4_0 | 12.2 GB | 16.0 GB | Too big | Get file → | |
| Q4_K_S | 12.2 GB | 16.1 GB | Too big | Get file → | |
| Q4_K_M | 13.0 GB | 16.9 GB | Too big | Get file → | |
| Q4_1 | 13.5 GB | 17.3 GB | Too big | Get file → | |
| Q5_K_S | 14.8 GB | 18.7 GB | Too big | Get file → | |
| Q5_K_M | 15.3 GB | 19.1 GB | Too big | Get file → | |
| Q6_K | 17.6 GB | 21.5 GB | Too big | Get file → |
For 8‑GB VRAM, use IQ1_S (4.61 GB, 11.8 GB memory at 8k context). For 12‑GB VRAM, IQ1_M (5.04 GB, 12.2 GB memory). For 16‑GB VRAM, Q4_K_M (13.01 GB, 20.2 GB memory). Estimates are approximate.
What GPU do you need for Mixtral 13Bx2 MOE 22B 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: 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: the best quant that fits is IQ1_S (4.6 GB file, about 11.8 GB in use).
- 16 GB VRAM: the best quant that fits is IQ3_XS (8.8 GB file, about 16.0 GB in use).
- 24 GB VRAM: the best quant that fits is Q5_K_M (15.3 GB file, about 22.5 GB in use).
- 32 GB VRAM: the best quant that fits is Q6_K (17.6 GB file, about 24.9 GB in use).
Which Mixtral 13Bx2 MOE 22B i1 quant should you choose?
Q4_K_M is the usual starting point for Mixtral 13Bx2 MOE 22B i1: it balances file size and quality well. Here it is a 13.0 GB file.
If memory is tight, the smallest file is IQ1_S at 4.6 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
Source
Frequently asked questions about Mixtral 13Bx2 MOE 22B i1
How much VRAM does Mixtral 13Bx2 MOE 22B i1 need?
About 20.2 GB at Q4_K_M with an 8K context window. That is the 13.0 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 Mixtral 13Bx2 MOE 22B i1 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 11.8 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Mixtral 13Bx2 MOE 22B i1 GGUF?
It depends on the quant: IQ1_S is 4.6 GB, IQ1_M is 5.0 GB, IQ2_XXS is 5.8 GB, IQ2_XS is 6.4 GB, IQ2_S is 6.7 GB, IQ2_M is 7.3 GB and 17 more.
What context length does Mixtral 13Bx2 MOE 22B i1 support?
The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 6.7 GB at 8K and 3.4 GB at 4K.
Where can I download Mixtral 13Bx2 MOE 22B i1 GGUF?
The files are on Hugging Face in the mradermacher/Mixtral_13Bx2_MOE_22B-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 Mixtral 13Bx2 MOE 22B i1 use?
Hugging Face lists the license as cc-by-nc-4.0. 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 Mixtral 13Bx2 MOE 22B i1 on 8 GB VRAM?
Yes, using the IQ1_S quantization which is 4.61 GB and requires about 11.8 GB of VRAM at 8k context.
Does this model support vision tasks?
No, the model does not have vision capabilities.
What license applies to this model?
The model is released under cc‑by‑nc‑4.0, allowing non‑commercial use only.