Skip to content
localllm
日本語

mistralai

Mixtral-8x22B-Instruct-v0.1

Parameters
140.6B
Max context length
65,536
Architecture
llama
License
Commercial OK
Base model
mistralai/Mixtral-8x22B-Instruct-v0.1
License
apache-2.0

About Mixtral-8x22B-Instruct-v0.1

Mixtral-8x22B-Instruct-v0.1 is a GGUF model based on mistralai/Mixtral-8x22B-Instruct-v0.1 on Hugging Face. GGUF files are published by mradermacher/Mixtral-8x22B-Instruct-v0.1-i1-GGUF. It has about 140.6B parameters, the llama architecture, a maximum context length of 65,536 tokens (values written in the GGUF).

There are 6 quantizations, with file sizes from 29.7 GB (IQ1_S) to 46.7 GB (IQ2_M) (actual sizes on Hugging Face).

Running IQ1_S (29.7 GB) with an 8,192-token context needs an estimated 32.1 GB of memory, and an estimated 37.8 GB at 32,768 tokens. For 8,192 tokens, a GPU with 32 GB or more of VRAM (such as GeForce RTX 5090), or a Mac with 32 GB or more of unified memory, is a rough guide (macOS caps how much memory the GPU can use, so leave some headroom).

The original model is licensed under Apache License 2.0, which allows commercial use (keep the license text and copyright notice when redistributing). Check the original license for the terms of use.

File size and estimated memory per quantization

  • Up to 8 GB
  • Up to 16 GB
  • Up to 24 GB
  • Up to 48 GB
  • Up to 128 GB
  • More

File sizes are the actual values on Hugging Face. Memory is estimated for each context length (KV cache f16). The formula is in How memory is calculated.

All memory figures are Estimated (KV cache f16). It should run on a setup with at least this much VRAM (or Mac unified memory). Click a value to see the devices and models that fit that amount (Find by GPU / Mac).

About the "quality guide" (how far a quantization drifts from the original)

For each quantization type, how far the output drifts from the original model, grouped into six levels from values llama.cpp measured on Llama-3-8B.

The value is mean KLD (the difference between the original and quantized model in next-token probabilities); smaller means closer to the original. Quantizations made with an imatrix (importance data) come out slightly smaller. Levels use the value without an imatrix (or with one, for types that only have that).

These values were not measured on this model. Larger models and MoE models tend to drift less with the same type. Distributor-specific mixed types (such as UD-Q4_K_XL) cannot be matched by type name alone, so they show "-".

Quantization Quality guide KLD (no imatrix) KLD (imatrix) Size (Llama-3-8B)
Q8_0 Nearly identical 0.0014 - 7.96 GiB
Q6_K Very small 0.0055 - 6.14 GiB
Q5_K_M Very small 0.0108 - 5.33 GiB
Q5_K_S Small 0.0166 - 5.21 GiB
Q5_1 Small 0.0180 - 5.65 GiB
Q5_0 Small 0.0222 - 5.21 GiB
Q4_K_M Small 0.0313 0.0282 4.58 GiB
Q4_K_S Medium 0.0431 0.0320 4.37 GiB
IQ4_NL Small - 0.0357 4.35 GiB
IQ4_XS Small - 0.0363 4.14 GiB
Q4_1 Medium 0.0717 - 4.78 GiB
Q4_0 Medium 0.0719 - 4.34 GiB
Q3_K_L Medium 0.0872 0.0731 4.03 GiB
Q3_K_M Medium 0.1019 0.0844 3.74 GiB
IQ3_M Medium - 0.1025 3.53 GiB
IQ3_S Medium - 0.1113 3.42 GiB
IQ3_XS Large - 0.1387 3.28 GiB
IQ3_XXS Large - 0.1836 3.05 GiB
Q3_K_S Large 0.2282 0.1998 3.41 GiB
IQ2_M Large - 0.3260 2.74 GiB
Q2_K Very large 0.4451 0.3322 2.96 GiB
Q2_K_S Very large - 0.4034 2.96 GiB
IQ2_S Very large - 0.4392 2.56 GiB
IQ2_XS Very large - 0.5463 2.43 GiB
IQ2_XXS Very large - 0.8120 2.24 GiB
IQ1_M Very large - 1.3931 2.01 GiB
IQ1_S Very large - 2.2546 1.88 GiB

Source: llama.cpp (MIT), measured on Llama-3-8B against FP16, Wikitext-2, revision f364eb6f. Original table · Reading and choosing quantizations

GGUF source

mradermacher/Mixtral-8x22B-Instruct-v0.1-i1-GGUF

Converted and published by a third party About this label

Last checked: Oct 21, 2026

Architecture
llama
Supported before llama.cpp b4409
Parameters
140.6B
Max context length
65,536
License
apache-2.0 Commercial OK
File size and memory per quantization for Mixtral-8x22B-Instruct-v0.1 (mradermacher/Mixtral-8x22B-Instruct-v0.1-i1-GGUF)
Quantization File size Measured Quality guide 4,096 8,192 16,384 32,768 65,536 max
IQ1_S 29.7 GB Very large 31.2 GB 32.1 GB 34.0 GB 37.8 GB 45.3 GB
IQ1_M 32.7 GB Very large 34.3 GB 35.2 GB 37.1 GB 40.9 GB 48.4 GB
IQ2_XXS 37.9 GB Very large 39.4 GB 40.4 GB 42.3 GB 46.0 GB 53.5 GB
IQ2_XS 42.0 GB Very large 43.6 GB 44.5 GB 46.4 GB 50.1 GB 57.6 GB
IQ2_S 42.6 GB Very large 44.1 GB 45.1 GB 47.0 GB 50.7 GB 58.2 GB
IQ2_M 46.7 GB Large 48.3 GB 49.2 GB 51.1 GB 54.8 GB 62.4 GB 
Ollama  ollama run hf.co/mradermacher/Mixtral-8x22B-Instruct-v0.1-i1-GGUF:IQ1_S
llama.cpp  llama-server -hf mradermacher/Mixtral-8x22B-Instruct-v0.1-i1-GGUF:IQ1_S

Third-party evaluations

Values from other organizations for the original model before quantization. Not this site's own rating. Values are for the original model before quantization. GGUF quantization (especially small quantizations) can lower performance.

Human preference (LMArena)

1,230 1,225–1,234

Mixtral 8x22B Instruct v0.1 · 51,416 votes · Values as of Nov 9, 2026

Source: LMArena (CC BY 4.0). Original leaderboard · See in ranking

License and commercial use

Apache License 2.0 Commercial OK

Allows commercial use, modification and redistribution. When redistributing, keep the license text and copyright notice, and note changes in modified files.

Based on the license on the original model's Hugging Face page. Original license text (checked Oct 18, 2026)

The summary states facts this site read from the original text and is not legal advice. Always check the original license and its latest terms before use. All licenses

How to run

Example commands using IQ1_S. To use another quantization, replace the name with one from the table above. How to run local LLMs

Ollama

Run it by pointing directly at the GGUF on Hugging Face.

ollama run hf.co/mradermacher/Mixtral-8x22B-Instruct-v0.1-i1-GGUF:IQ1_S

llama.cpp

Pass the repository and quantization name to llama-server (or llama-cli) with -hf.

llama-server -hf mradermacher/Mixtral-8x22B-Instruct-v0.1-i1-GGUF:IQ1_S

LM Studio

Paste mradermacher/Mixtral-8x22B-Instruct-v0.1-i1-GGUF into the search box, download it, and choose the quantization from the file list.

Frequently asked questions

How much memory do I need to run Mixtral-8x22B-Instruct-v0.1 (IQ1_S)?
The file size is 29.7 GB (measured). With a 8,192-token context, the estimated memory including the KV cache is 32.1 GB. The formula is published at https://localllm.az-arte.com/en/guide/memory-calculation.
Can Mixtral-8x22B-Instruct-v0.1 be used commercially?
The original model's license is Apache License 2.0 (Commercial use allowed).Allows commercial use, modification and redistribution. When redistributing, keep the license text and copyright notice, and note changes in modified files. Check the original license text before deciding.
Does Mixtral-8x22B-Instruct-v0.1 run in 8 GB, 12 GB, 16 GB or 24 GB of VRAM?
8 GB: no quantization fits; 12 GB: no quantization fits; 16 GB: no quantization fits; 24 GB: no quantization fits (estimated at 8,192 tokens with an f16 KV cache, files from the most-downloaded source).
What is the command to run Mixtral-8x22B-Instruct-v0.1 with Ollama?
Run "ollama run hf.co/mradermacher/Mixtral-8x22B-Instruct-v0.1-i1-GGUF:IQ1_S" to use the GGUF on Hugging Face directly. To use another quantization, replace the name at the end.