Edit model card

glm-4-9b-chat-IMat-GGUF

Llama.cpp imatrix quantization of THUDM/glm-4-9b-chat

Original Model: THUDM/glm-4-9b-chat
Original dtype: BF16 (bfloat16)
Quantized by: https://github.com/ggerganov/llama.cpp/pull/6999
IMatrix dataset: here


Files

IMatrix

Status: โœ… Available
Link: here

Common Quants

Filename Quant type File Size Status Uses IMatrix Is Split
glm-4-9b-chat.Q8_0.gguf Q8_0 9.99GB โœ… Available โšช Static ๐Ÿ“ฆ No
glm-4-9b-chat.Q6_K.gguf Q6_K 8.26GB โœ… Available โšช Static ๐Ÿ“ฆ No
glm-4-9b-chat.Q4_K.gguf Q4_K 6.25GB โœ… Available ๐ŸŸข IMatrix ๐Ÿ“ฆ No
glm-4-9b-chat.Q3_K.gguf Q3_K 5.06GB โœ… Available ๐ŸŸข IMatrix ๐Ÿ“ฆ No
glm-4-9b-chat.Q2_K.gguf Q2_K 3.99GB โœ… Available ๐ŸŸข IMatrix ๐Ÿ“ฆ No

All Quants

Filename Quant type File Size Status Uses IMatrix Is Split
glm-4-9b-chat.BF16.gguf BF16 18.81GB โœ… Available โšช Static ๐Ÿ“ฆ No
glm-4-9b-chat.FP16.gguf F16 18.81GB โœ… Available โšช Static ๐Ÿ“ฆ No
glm-4-9b-chat.Q8_0.gguf Q8_0 9.99GB โœ… Available โšช Static ๐Ÿ“ฆ No
glm-4-9b-chat.Q6_K.gguf Q6_K 8.26GB โœ… Available โšช Static ๐Ÿ“ฆ No
glm-4-9b-chat.Q5_K.gguf Q5_K 7.14GB โœ… Available โšช Static ๐Ÿ“ฆ No
glm-4-9b-chat.Q5_K_S.gguf Q5_K_S 6.69GB โœ… Available โšช Static ๐Ÿ“ฆ No
glm-4-9b-chat.Q4_K.gguf Q4_K 6.25GB โœ… Available ๐ŸŸข IMatrix ๐Ÿ“ฆ No
glm-4-9b-chat.Q4_K_S.gguf Q4_K_S 5.75GB โœ… Available ๐ŸŸข IMatrix ๐Ÿ“ฆ No
glm-4-9b-chat.IQ4_NL.gguf IQ4_NL 5.46GB โœ… Available ๐ŸŸข IMatrix ๐Ÿ“ฆ No
glm-4-9b-chat.IQ4_XS.gguf IQ4_XS 5.25GB โœ… Available ๐ŸŸข IMatrix ๐Ÿ“ฆ No
glm-4-9b-chat.Q3_K.gguf Q3_K 5.06GB โœ… Available ๐ŸŸข IMatrix ๐Ÿ“ฆ No
glm-4-9b-chat.Q3_K_L.gguf Q3_K_L 5.28GB โœ… Available ๐ŸŸข IMatrix ๐Ÿ“ฆ No
glm-4-9b-chat.Q3_K_S.gguf Q3_K_S 4.59GB โœ… Available ๐ŸŸข IMatrix ๐Ÿ“ฆ No
glm-4-9b-chat.IQ3_M.gguf IQ3_M 4.81GB โœ… Available ๐ŸŸข IMatrix ๐Ÿ“ฆ No
glm-4-9b-chat.IQ3_S.gguf IQ3_S 4.59GB โœ… Available ๐ŸŸข IMatrix ๐Ÿ“ฆ No
glm-4-9b-chat.IQ3_XS.gguf IQ3_XS 4.43GB โœ… Available ๐ŸŸข IMatrix ๐Ÿ“ฆ No
glm-4-9b-chat.IQ3_XXS.gguf IQ3_XXS 4.26GB โœ… Available ๐ŸŸข IMatrix ๐Ÿ“ฆ No
glm-4-9b-chat.Q2_K.gguf Q2_K 3.99GB โœ… Available ๐ŸŸข IMatrix ๐Ÿ“ฆ No
glm-4-9b-chat.Q2_K_S.gguf Q2_K_S 3.96GB โœ… Available ๐ŸŸข IMatrix ๐Ÿ“ฆ No
glm-4-9b-chat.IQ2_M.gguf IQ2_M 3.93GB โœ… Available ๐ŸŸข IMatrix ๐Ÿ“ฆ No
glm-4-9b-chat.IQ2_S.gguf IQ2_S 3.77GB โœ… Available ๐ŸŸข IMatrix ๐Ÿ“ฆ No
glm-4-9b-chat.IQ2_XS.gguf IQ2_XS 3.61GB โœ… Available ๐ŸŸข IMatrix ๐Ÿ“ฆ No
glm-4-9b-chat.IQ2_XXS.gguf IQ2_XXS 3.43GB โœ… Available ๐ŸŸข IMatrix ๐Ÿ“ฆ No
glm-4-9b-chat.IQ1_M.gguf IQ1_M 3.22GB โœ… Available ๐ŸŸข IMatrix ๐Ÿ“ฆ No
glm-4-9b-chat.IQ1_S.gguf IQ1_S 3.10GB โœ… Available ๐ŸŸข IMatrix ๐Ÿ“ฆ 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/glm-4-9b-chat-IMat-GGUF --include "glm-4-9b-chat.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/glm-4-9b-chat-IMat-GGUF --include "glm-4-9b-chat.Q8_0/*" --local-dir ./
# see FAQ for merging GGUF's

Inference

Simple chat template

[gMASK]<sop><|user|>
{user_prompt}<|assistant|>
{assistant_response}<|user|>
{next_user_prompt}

Chat template with system prompt

[gMASK]<sop><|system|>
{system_prompt}<|user|>
{user_prompt}<|assistant|>
{assistant_response}<|user|>
{next_user_prompt}

Llama.cpp

llama.cpp/main -m glm-4-9b-chat.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: glm-4-9b-chat.Q8_0)
  3. Run gguf-split --merge glm-4-9b-chat.Q8_0/glm-4-9b-chat.Q8_0-00001-of-XXXXX.gguf glm-4-9b-chat.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
17,152
GGUF
Model size
9.4B params
Architecture
chatglm
+4
Inference API (serverless) has been turned off for this model.

Quantized from

Collection including legraphista/glm-4-9b-chat-IMat-GGUF