GLM 5 Models — Hardware Requirements
7 GLM 5 models from Z.ai and the community, from the smallest that runs in 1.3 GB of VRAM at Q4 up to 753.9B parameters. Every row links to full quantization tables and GPU compatibility.
All GLM 5 Models by Size
| Model | Params | Runs from (Q4) | Context | Publisher | Quant downloads |
|---|---|---|---|---|---|
| GLM 5.3 Flash | 321.3B | 205.2 GB | 1049K | ||
| GLM 5.3 Flash BF16 | 321.3B | 205.2 GB | 1049K | ||
| GLM 5.3 | 753.3B | 453.8 GB | 1049K | ||
| GLM 5.2 | 753.3B | 453.8 GB | 1049K | ||
| GLM 5.3 BF16 | 753.3B | 453.8 GB | 1049K | ||
| GLM 5 | 753.9B | 454.1 GB | 203K | ||
| GLM 5.1 | 753.9B | 454.1 GB | 203K |
Community variants and fine-tunes(12)
| Model | Params | Runs from (Q4) | Context | Publisher | Quant downloads |
|---|---|---|---|---|---|
| GLM 5.3 Flash DFlash2 | 1.2B | 1.3 GB | 1049K | ||
| GLM 5.3 DFlash2 | 2.5B | 2.1 GB | 1049K | ||
| GLM 5.2 Speculator.dspark | 3.8B | 4.6 GB | — | ||
| GLM 5.3 Flash EXL3 K2 | 48.9B | 41.7 GB | 1049K | ||
| GLM 5.3 UNCENSORED EXL3 3.0bpw | 146.3B | 89.6 GB | 1049K | ||
| GLM 5.3 EXL3 TR3 3.25bpw | 169.6B | 103.5 GB | 1049K | ||
| GLM 5.3 EXL3 TR3 3.42bpw | 177.5B | 108.3 GB | 1049K | ||
| GLM 5.3 W4AFP8 | 386.1B | 233.4 GB | 1049K | ||
| GLM 5.2 W4AFP8 | 391.9B | 236.9 GB | 1049K | ||
| Penclaw GLM 5.3 Abliterated | 753.3B | 506.4 GB | — | ||
| GLM 5.3 MXFP4 | 753.3B | 453.8 GB | 1049K | ||
| GLM 5 Abliterated | 753.9B | 454.1 GB | 203K |
How GLM 5 Compares — llmrun Composite Score
GLM 5.3 is the highest-scoring GLM 5 model with an llmrun Composite Score of 130.1 — #6 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
Step 5 Preview128.0
GLM 5.3 Flash124.1
GLM 5.2122.9
GLM 5.1117.8
GLM 5111.8
Frequently Asked Questions
- How much VRAM do I need to run a GLM 5 model?
- The smallest GLM 5 model, GLM 5.3 Flash DFlash2, runs from 1.3 GB of VRAM at Q4_K_M (smaller low-bit quantizations start at 0.8 GB with a noticeable quality loss). Larger family members need proportionally more — see the table above for every model.
- Which GLM 5 models can I run on a 16 GB GPU?
- 3 of 19 GLM 5 models fit in 16 GB of VRAM at Q4_K_M, including GLM 5.3 Flash DFlash2, GLM 5.2 Speculator.dspark, GLM 5.3 DFlash2.
- What is the most popular GLM 5 model to run locally?
- GLM 5.3 Flash is the most downloaded GLM 5 model in local-friendly quantized formats. It runs from 205.2 GB of VRAM at Q4_K_M.
- How do GLM 5 models score on benchmarks?
- GLM 5.3 leads the family with an llmrun Composite Score of 130.1, ranking #6 among 106 open models, while the top proprietary model, Gemini 4 Carbon, scores 158.6. See the comparison chart above for the full standings.