| | --- |
| | license: mit |
| | base_model: zai-org/GLM-4.6V |
| | base_model_relation: quantized |
| | quantized_by: turboderp |
| | tags: |
| | - exl3 |
| | --- |
| | |
| | EXL3 quants of [GLM-4.6V](https://huggingface.co/zai-org/GLM-4.6V) |
| |
|
| | ⚠️ Requires ExLlamaV3 v0.0.18 (or v0.0.17 `dev` branch) |
| |
|
| | Base bitrates: |
| |
|
| | [2.00 bits per weight](https://huggingface.co/turboderp/GLM-4.6V-exl3/tree/2.00bpw) |
| | [3.00 bits per weight](https://huggingface.co/turboderp/GLM-4.6V-exl3/tree/3.00bpw) |
| | [4.00 bits per weight](https://huggingface.co/turboderp/GLM-4.6V-exl3/tree/4.00bpw) |
| | [5.00 bits per weight](https://huggingface.co/turboderp/GLM-4.6V-exl3/tree/5.00bpw) |
| |
|
| | Optimized: |
| |
|
| | [2.13 bits per weight](https://huggingface.co/turboderp/GLM-4.6V-exl3/tree/2.13bpw) |
| | [2.32 bits per weight](https://huggingface.co/turboderp/GLM-4.6V-exl3/tree/2.32bpw) |
| | [2.55 bits per weight](https://huggingface.co/turboderp/GLM-4.6V-exl3/tree/2.55bpw) |
| | [2.80 bits per weight](https://huggingface.co/turboderp/GLM-4.6V-exl3/tree/2.80bpw) |
| | [3.13 bits per weight](https://huggingface.co/turboderp/GLM-4.6V-exl3/tree/3.13bpw) |
| | [3.55 bits per weight](https://huggingface.co/turboderp/GLM-4.6V-exl3/tree/3.55bpw) |
| | [4.07 bits per weight](https://huggingface.co/turboderp/GLM-4.6V-exl3/tree/4.07bpw) |
| |
|
