Filename	Quant type	File Size	Status	Uses IMatrix	Is Split
Mistral-Large-Instruct-2407.Q8_0/*	Q8_0	130.28GB	✅ Available	⚪ Static	✂ Yes
Mistral-Large-Instruct-2407.Q6_K/*	Q6_K	100.59GB	✅ Available	⚪ Static	✂ Yes
Mistral-Large-Instruct-2407.Q4_K/*	Q4_K	73.22GB	✅ Available	🟢 IMatrix	✂ Yes
Mistral-Large-Instruct-2407.Q3_K/*	Q3_K	59.10GB	✅ Available	🟢 IMatrix	✂ Yes
Mistral-Large-Instruct-2407.Q2_K/*	Q2_K	45.20GB	✅ Available	🟢 IMatrix	✂ Yes

All Quants

Filename	Quant type	File Size	Status	Uses IMatrix	Is Split
Mistral-Large-Instruct-2407.BF16/*	BF16	245.23GB	✅ Available	⚪ Static	✂ Yes
Mistral-Large-Instruct-2407.FP16/*	F16	245.23GB	✅ Available	⚪ Static	✂ Yes
Mistral-Large-Instruct-2407.Q8_0/*	Q8_0	130.28GB	✅ Available	⚪ Static	✂ Yes
Mistral-Large-Instruct-2407.Q6_K/*	Q6_K	100.59GB	✅ Available	⚪ Static	✂ Yes
Mistral-Large-Instruct-2407.Q5_K/*	Q5_K	86.49GB	✅ Available	⚪ Static	✂ Yes
Mistral-Large-Instruct-2407.Q5_K_S/*	Q5_K_S	84.36GB	✅ Available	⚪ Static	✂ Yes
Mistral-Large-Instruct-2407.Q4_K/*	Q4_K	73.22GB	✅ Available	🟢 IMatrix	✂ Yes
Mistral-Large-Instruct-2407.Q4_K_S/*	Q4_K_S	69.57GB	✅ Available	🟢 IMatrix	✂ Yes
Mistral-Large-Instruct-2407.IQ4_NL/*	IQ4_NL	69.22GB	✅ Available	🟢 IMatrix	✂ Yes
Mistral-Large-Instruct-2407.IQ4_XS/*	IQ4_XS	65.43GB	✅ Available	🟢 IMatrix	✂ Yes
Mistral-Large-Instruct-2407.Q3_K/*	Q3_K	59.10GB	✅ Available	🟢 IMatrix	✂ Yes
Mistral-Large-Instruct-2407.Q3_K_L/*	Q3_K_L	64.55GB	✅ Available	🟢 IMatrix	✂ Yes
Mistral-Large-Instruct-2407.Q3_K_S/*	Q3_K_S	52.85GB	✅ Available	🟢 IMatrix	✂ Yes
Mistral-Large-Instruct-2407.IQ3_M/*	IQ3_M	55.28GB	✅ Available	🟢 IMatrix	✂ Yes
Mistral-Large-Instruct-2407.IQ3_S/*	IQ3_S	53.00GB	✅ Available	🟢 IMatrix	✂ Yes
Mistral-Large-Instruct-2407.IQ3_XS/*	IQ3_XS	50.14GB	✅ Available	🟢 IMatrix	✂ Yes
Mistral-Large-Instruct-2407.IQ3_XXS/*	IQ3_XXS	47.01GB	✅ Available	🟢 IMatrix	✂ Yes
Mistral-Large-Instruct-2407.Q2_K/*	Q2_K	45.20GB	✅ Available	🟢 IMatrix	✂ Yes
Mistral-Large-Instruct-2407.Q2_K_S.gguf	Q2_K_S	41.61GB	✅ Available	🟢 IMatrix	📦 No
Mistral-Large-Instruct-2407.IQ2_M.gguf	IQ2_M	41.62GB	✅ Available	🟢 IMatrix	📦 No
Mistral-Large-Instruct-2407.IQ2_S.gguf	IQ2_S	38.38GB	✅ Available	🟢 IMatrix	📦 No
Mistral-Large-Instruct-2407.IQ2_XS.gguf	IQ2_XS	36.08GB	✅ Available	🟢 IMatrix	📦 No
Mistral-Large-Instruct-2407.IQ2_XXS.gguf	IQ2_XXS	32.43GB	✅ Available	🟢 IMatrix	📦 No
Mistral-Large-Instruct-2407.IQ1_M.gguf	IQ1_M	28.39GB	✅ Available	🟢 IMatrix	📦 No
Mistral-Large-Instruct-2407.IQ1_S.gguf	IQ1_S	25.96GB	✅ Available	🟢 IMatrix	📦 No

Downloading using huggingface-cli

If you do not have hugginface-cli installed:

pip install -U "huggingface_hub[cli]"

Download the specific file you want:

huggingface-cli download legraphista/Mistral-Large-Instruct-2407-IMat-GGUF --include "Mistral-Large-Instruct-2407.Q8_0.gguf" --local-dir ./

If the model file is big, it has been split into multiple files. In order to download them all to a local folder, run:

huggingface-cli download legraphista/Mistral-Large-Instruct-2407-IMat-GGUF --include "Mistral-Large-Instruct-2407.Q8_0/*" --local-dir ./
# see FAQ for merging GGUF's

Inference

Llama.cpp

llama.cpp/main -m Mistral-Large-Instruct-2407.Q8_0.gguf --color -i -p "prompt here"

FAQ

Why is the IMatrix not applied everywhere?

According to this investigation, it appears that lower quantizations are the only ones that benefit from the imatrix input (as per hellaswag results).

How do I merge a split GGUF?

Make sure you have gguf-split available
- To get hold of gguf-split, navigate to https://github.com/ggerganov/llama.cpp/releases
- Download the appropriate zip for your system from the latest release
- Unzip the archive and you should be able to find gguf-split
Locate your GGUF chunks folder (ex: Mistral-Large-Instruct-2407.Q8_0)
Run gguf-split --merge Mistral-Large-Instruct-2407.Q8_0/Mistral-Large-Instruct-2407.Q8_0-00001-of-XXXXX.gguf Mistral-Large-Instruct-2407.Q8_0.gguf
- Make sure to point gguf-split to the first chunk of the split.

Got a suggestion? Ping me @legraphista!