Qwen2.5-32B-Instruct-IMat-GGUF

Llama.cpp imatrix quantization of Qwen/Qwen2.5-32B-Instruct

Original Model: Qwen/Qwen2.5-32B-Instruct
Original dtype: BF16 (bfloat16)
Quantized by: llama.cpp b3787
IMatrix dataset: here


Files

IMatrix

Status: βœ… Available
Link: here

Common Quants

Filename Quant type File Size Status Uses IMatrix Is Split
Qwen2.5-32B-Instruct.Q8_0.gguf Q8_0 34.82GB βœ… Available βšͺ Static πŸ“¦ No
Qwen2.5-32B-Instruct.Q6_K.gguf Q6_K 26.89GB βœ… Available βšͺ Static πŸ“¦ No
Qwen2.5-32B-Instruct.Q4_K.gguf Q4_K 19.85GB βœ… Available 🟒 IMatrix πŸ“¦ No
Qwen2.5-32B-Instruct.Q3_K.gguf Q3_K 15.94GB βœ… Available 🟒 IMatrix πŸ“¦ No
Qwen2.5-32B-Instruct.Q2_K.gguf Q2_K 12.31GB βœ… Available 🟒 IMatrix πŸ“¦ No

All Quants

Filename Quant type File Size Status Uses IMatrix Is Split
Qwen2.5-32B-Instruct.BF16/* BF16 65.54GB βœ… Available βšͺ Static βœ‚ Yes
Qwen2.5-32B-Instruct.FP16/* F16 65.54GB βœ… Available βšͺ Static βœ‚ Yes
Qwen2.5-32B-Instruct.Q8_0.gguf Q8_0 34.82GB βœ… Available βšͺ Static πŸ“¦ No
Qwen2.5-32B-Instruct.Q6_K.gguf Q6_K 26.89GB βœ… Available βšͺ Static πŸ“¦ No
Qwen2.5-32B-Instruct.Q5_K.gguf Q5_K 23.26GB βœ… Available βšͺ Static πŸ“¦ No
Qwen2.5-32B-Instruct.Q5_K_S.gguf Q5_K_S 22.64GB βœ… Available βšͺ Static πŸ“¦ No
Qwen2.5-32B-Instruct.Q4_K.gguf Q4_K 19.85GB βœ… Available 🟒 IMatrix πŸ“¦ No
Qwen2.5-32B-Instruct.Q4_K_S.gguf Q4_K_S 18.78GB βœ… Available 🟒 IMatrix πŸ“¦ No
Qwen2.5-32B-Instruct.IQ4_NL.gguf IQ4_NL 18.68GB βœ… Available 🟒 IMatrix πŸ“¦ No
Qwen2.5-32B-Instruct.IQ4_XS.gguf IQ4_XS 17.69GB βœ… Available 🟒 IMatrix πŸ“¦ No
Qwen2.5-32B-Instruct.Q3_K.gguf Q3_K 15.94GB βœ… Available 🟒 IMatrix πŸ“¦ No
Qwen2.5-32B-Instruct.Q3_K_L.gguf Q3_K_L 17.25GB βœ… Available 🟒 IMatrix πŸ“¦ No
Qwen2.5-32B-Instruct.Q3_K_S.gguf Q3_K_S 14.39GB βœ… Available 🟒 IMatrix πŸ“¦ No
Qwen2.5-32B-Instruct.IQ3_M.gguf IQ3_M 14.81GB βœ… Available 🟒 IMatrix πŸ“¦ No
Qwen2.5-32B-Instruct.IQ3_S.gguf IQ3_S 14.44GB βœ… Available 🟒 IMatrix πŸ“¦ No
Qwen2.5-32B-Instruct.IQ3_XS.gguf IQ3_XS 13.71GB βœ… Available 🟒 IMatrix πŸ“¦ No
Qwen2.5-32B-Instruct.IQ3_XXS.gguf IQ3_XXS 12.84GB βœ… Available 🟒 IMatrix πŸ“¦ No
Qwen2.5-32B-Instruct.Q2_K.gguf Q2_K 12.31GB βœ… Available 🟒 IMatrix πŸ“¦ No
Qwen2.5-32B-Instruct.Q2_K_S.gguf Q2_K_S 11.49GB βœ… Available 🟒 IMatrix πŸ“¦ No
Qwen2.5-32B-Instruct.IQ2_M.gguf IQ2_M 11.26GB βœ… Available 🟒 IMatrix πŸ“¦ No
Qwen2.5-32B-Instruct.IQ2_S.gguf IQ2_S 10.39GB βœ… Available 🟒 IMatrix πŸ“¦ No
Qwen2.5-32B-Instruct.IQ2_XS.gguf IQ2_XS 9.96GB βœ… Available 🟒 IMatrix πŸ“¦ No
Qwen2.5-32B-Instruct.IQ2_XXS.gguf IQ2_XXS 9.03GB βœ… Available 🟒 IMatrix πŸ“¦ No
Qwen2.5-32B-Instruct.IQ1_M.gguf IQ1_M 7.93GB βœ… Available 🟒 IMatrix πŸ“¦ No
Qwen2.5-32B-Instruct.IQ1_S.gguf IQ1_S 7.27GB βœ… Available 🟒 IMatrix πŸ“¦ 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/Qwen2.5-32B-Instruct-IMat-GGUF --include "Qwen2.5-32B-Instruct.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/Qwen2.5-32B-Instruct-IMat-GGUF --include "Qwen2.5-32B-Instruct.Q8_0/*" --local-dir ./
# see FAQ for merging GGUF's

Inference

Simple chat template

<|im_start|>system
You are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>
<|im_start|>user
{user_prompt}<|im_end|>
<|im_start|>assistant
{assistant_response}<|im_end|>
<|im_start|>user
{next_user_prompt}<|im_end|>

Chat template with system prompt

<|im_start|>system
{system_prompt}<|im_end|>
<|im_start|>user
{user_prompt}<|im_end|>
<|im_start|>assistant
{assistant_response}<|im_end|>
<|im_start|>user
{next_user_prompt}<|im_end|>

Llama.cpp

llama.cpp/main -m Qwen2.5-32B-Instruct.Q8_0.gguf --color -i -p "prompt here (according to the chat template)"

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?

  1. Make sure you have gguf-split available
  2. Locate your GGUF chunks folder (ex: Qwen2.5-32B-Instruct.Q8_0)
  3. Run gguf-split --merge Qwen2.5-32B-Instruct.Q8_0/Qwen2.5-32B-Instruct.Q8_0-00001-of-XXXXX.gguf Qwen2.5-32B-Instruct.Q8_0.gguf
    • Make sure to point gguf-split to the first chunk of the split.

Got a suggestion? Ping me @legraphista!

Downloads last month
181
GGUF
Model size
32.8B params
Architecture
qwen2

1-bit

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

Inference Examples
Inference API (serverless) has been turned off for this model.

Model tree for legraphista/Qwen2.5-32B-Instruct-IMat-GGUF

Base model

Qwen/Qwen2.5-32B
Quantized
(87)
this model