Zhipu AI · 9B · Dense
Multilingual model supporting 26 languages with 128K context Check if your GPU or Mac can run GLM-4 9B locally — 5 GB min, 8.4 GB recommended.
2024-06128K context
| Quant | Bits | VRAM | Quality | Status |
|---|---|---|---|---|
| Q2_K | 2 | 3.4 GB | low | — |
| Q3_K_M | 3 | 4.5 GB | moderate | — |
| Q4_K_M | 4 | 5.1 GB | good | — |
| Q5_K_M | 5 | 6.3 GB | good | — |
| Q6_K | 6 | 7.4 GB | excellent | — |
| Q8_0 | 8 | 9.7 GB | excellent | — |
| F16 | 16 | 18.9 GB | lossless | — |
About this model
Note: this model requires Ollama 0.2 or later.
In the evaluation of data sets in semantics, mathematics, reasoning, code, and knowledge, this model has shown superior performance beyond even Llama 3 8B.
This generation of models includes multi-language support, supporting 26 languages including Japanese, Korean, and German.
References
Can I run GLM-4 9B locally?
- Can I run GLM-4 9B locally?
- GLM-4 9B needs about 5 GB of memory at a minimum and 8.4 GB recommended. Open this page to grade it against your GPU or Mac, then run it with runai, Ollama or LM Studio.
- How much VRAM does GLM-4 9B need?
- At Q4_K_M, GLM-4 9B uses about 5.1 GB of VRAM. Higher quants need more memory; lower quants fit tighter cards with a quality tradeoff.