Z.ai · 16B · Dense
Hybrid autoregressive + diffusion model — dense text and knowledge-heavy images, plus editing Check if your GPU or Mac can run GLM-Image locally — 11.2 GB min, 22.5 GB recommended.
2026-014K context
| Quant | Bits | VRAM | Quality | Status |
|---|---|---|---|---|
| Q2_K | 2 | 11.2 GB | low | — |
| Q3_K_M | 3 | 13.3 GB | moderate | — |
| Q4_K_M | 4 | 14.3 GB | good | — |
| Q5_K_M | 5 | 16.3 GB | good | — |
| Q6_K | 6 | 18.4 GB | excellent | — |
| Q8_0 | 8 | 22.5 GB | excellent | — |
| F16 | 16 | 38.9 GB | lossless | — |
Can I run GLM-Image locally?
- Can I run GLM-Image locally?
- GLM-Image needs about 11.2 GB of memory at a minimum and 22.5 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-Image need?
- At Q4_K_M, GLM-Image uses about 14.3 GB of VRAM. Higher quants need more memory; lower quants fit tighter cards with a quality tradeoff.