bartowski/zai-org_GLM-4.7-Flash-GGUF

• en
• zh

Llamacpp imatrix Quantizations of GLM-4.7-Flash by zai-org

Using llama.cpp release b7779 for quantization.

Original model: https://huggingface.co/zai-org/GLM-4.7-Flash

All quants made using imatrix option with dataset from here

Run them in your choice of tools:

• llama.cpp
• LM Studio
• koboldcpp
• Jan AI
• Text Generation Web UI
• LoLLMs

Note: if it's a newly supported model, you may need to wait for an update from the developers.

It's suggested you disable flash attention (--flash-attn off) for improved performance

Re-uploaded with fixed imatrix from the fixed gating function: https://github.com/ggml-org/llama.cpp/pull/18980

You'll need the updated llama.cpp to get proper output

Prompt format

[gMASK]<sop><|system|>{system_prompt}<|user|>{prompt}<|assistant|><think>

Download a file (not the whole branch) from below:

Embed/output weights

Some of these quants (Q3KXL, Q4KL etc) are the standard quantization method with the embeddings and output weights quantized to Q8_0 instead of what they would normally default to.

Downloading using huggingface-cli

pip install -U "huggingface_hub[cli]"

huggingface-cli download bartowski/zai-orgGLM-4.7-Flash-GGUF --include "zai-orgGLM-4.7-Flash-Q4KM.gguf" --local-dir ./

huggingface-cli download bartowski/zai-orgGLM-4.7-Flash-GGUF --include "zai-orgGLM-4.7-Flash-Q8_0/*" --local-dir ./

ARM/AVX information

Previously, you would download Q4044/48/8_8, and these would have their weights interleaved in memory in order to improve performance on ARM and AVX machines by loading up more data in one pass.

Now, however, there is something called "online repacking" for weights. details in this PR. If you use Q40 and your hardware would benefit from repacking weights, it will do it automatically on the fly.

As of llama.cpp build b4282 you will not be able to run the Q40XX files and will instead need to use Q4_0.

Additionally, if you want to get slightly better quality for , you can use IQ4NL thanks to this PR which will also repack the weights for ARM, though only the 4_4 for now. The loading time may be slower but it will result in an overall speed incrase.