GLM 4 Models — Hardware Requirements
18 GLM 4 models from Z.ai and the community, from the smallest that runs in 6.6 GB of VRAM at Q4 up to 358.3B parameters. Every row links to full quantization tables and GPU compatibility.
All GLM 4 Models by Size
| Model | Params | Runs from (Q4) | Context | Publisher | Quant downloads |
|---|---|---|---|---|---|
| Glm 4 9B Chat | 9.4B | 8.9 GB | 131K | ||
| GLM 4 9B 0414 | 9.4B | 6.6 GB | 33K | ||
| GLM 4.6V Flash | 10.3B | 7.2 GB | 131K | ||
| GLM 4.1V 9B Thinking | 10.3B | 7.2 GB | 66K | ||
| GLM 4.7 Flash | 31.2B | 19.9 GB | 203K | ||
| GLM 4.6V | 107.7B | 66.0 GB | 131K | ||
| GLM 4.5V | 107.7B | 66.0 GB | 66K | ||
| GLM 4.5 Air | 110.5B | 67.6 GB | 131K | ||
| GLM 4.6 | 356.8B | 216.9 GB | 203K | ||
| GLM 4.7 | 358.3B | 217.9 GB | 203K | ||
| GLM 4.5 | 358.3B | 217.9 GB | 131K |
Community variants and fine-tunes(8)
| Model | Params | Runs from (Q4) | Context | Publisher | Quant downloads |
|---|---|---|---|---|---|
| GLM 4.7 Flash REAP 23B A3B | 23.0B | 15.0 GB | 203K | ||
| GLM 4.7 Flash Heretic | 29.9B | 19.1 GB | 203K | ||
| GLM 4.7 Flash Heretic 1.2.0 | 29.9B | 19.1 GB | 203K | ||
| GLM 4.7 Flash Ultimate Irrefusable Heretic | 29.9B | 19.1 GB | 203K | ||
| GLM 4.7 Flash Coder | 29.9B | 19.1 GB | 203K | ||
| GLM 4.5 Air Derestricted | 110.5B | 67.6 GB | 131K | ||
| GLM 4.6 Derestricted | 356.8B | 216.9 GB | 203K | ||
| GLM 4.6 Derestricted v3 | 356.8B | 216.9 GB | 203K |
How GLM 4 Compares — llmrun Composite Score
GLM 4.7 is the highest-scoring GLM 4 model with an llmrun Composite Score of 109.1 — #34 among 106 open models. The top proprietary model, Gemini 4 Carbon, scores 158.6. Click a model to see its full benchmark breakdown.
Gemini 4 Carbon · proprietary158.6
GPT 6 Astra · proprietary156.2
Claude Opus 5.5 · proprietary153.0
GPT 6.1 Sol · proprietary151.7
GPT 6.1 Terra · proprietary150.1
Kimi K3.1 Pro142.8
MiMo V2.6 Pro RL133.3
Kimi K3132.7
MiMo V2.6 Flash RL131.9
GLM 5.3130.1
DeepSeek V4.1 Flash129.4
DeepSeek V4 Pro 0813129.2
GLM 4.7109.1
GLM 4.6103.1
GLM 4.5100.9
GLM 4.5 Air98.6
Frequently Asked Questions
- How much VRAM do I need to run a GLM 4 model?
- The smallest GLM 4 model, GLM 4 9B 0414, runs from 6.6 GB of VRAM at Q4_K_M (smaller low-bit quantizations start at 4.4 GB with a noticeable quality loss). Larger family members need proportionally more — see the table above for every model.
- Which GLM 4 models can I run on a 16 GB GPU?
- 5 of 19 GLM 4 models fit in 16 GB of VRAM at Q4_K_M, including GLM 4.6V Flash, GLM 4.7 Flash REAP 23B A3B, Glm 4 9B Chat.
- What is the most popular GLM 4 model to run locally?
- GLM 4.7 Flash is the most downloaded GLM 4 model in local-friendly quantized formats. It runs from 19.9 GB of VRAM at Q4_K_M.
- How do GLM 4 models score on benchmarks?
- GLM 4.7 leads the family with an llmrun Composite Score of 109.1, ranking #34 among 106 open models, while the top proprietary model, Gemini 4 Carbon, scores 158.6. See the comparison chart above for the full standings.