// GLM / CogVideoX (Z.ai) · Vision-language
GLM-4.6V: VRAM & local deployment
107.7B (MoE) parameters. About 73.9 GB at 4-bit and 239 GB at BF16 with one 8K-token request.
released 2025-12-07licence: Commercial OKmemory figures are estimates
01Specs
| Publisher | Z.ai (Zhipu) · zai-org |
|---|---|
| Family / series | GLM / CogVideoX (Z.ai) · GLM-4.6V |
| Type | Vision-language (image-text-to-text) |
| Parameters | 107.7B (MoE) Source: counted from official safetensors weights |
| Context length | 128K tokens (131,072)max_position_embeddings in config.json |
| Architecture | 46 layers · GQA · MoE |
| Released weights | BF16 · 215 GBdownload |
| Licence | MIT · Commercial OKPermissive licence (Apache-2.0 / MIT / CC-BY / OpenMDW): commercial use allowed. |
| Released | 2025-12-07 (Hugging Face repo created) |
02How much VRAM it needs (estimate)
Total = weights + 10% + 0.5GB overhead + KV cache for one request (FP16 KV). More concurrent users multiply the KV column.
| Precision | Weights | Total @ 8K | Total @ 32K | Total @ 128K | Smallest GPU | Mac |
|---|---|---|---|---|---|---|
| BF16 / FP16 (original) | 215 GB | 239 GB | 244 GB | 262 GB | 4 × RTX PRO 6000 (384GB) | Mac 512GB |
| FP8 / INT8 / Q8_0 | 114 GB | 128 GB | 133 GB | 151 GB | 4 × RTX PRO 6000 (384GB) | Mac 256GB |
| 4-bit (Q4_K_M / AWQ / GPTQ-Int4) | 65.3 GB | 73.9 GB | 78.5 GB | 97.0 GB | RTX PRO 6000 96GB | Mac 128GB |
KV cache per request: 8K 1.5 GB · 32K 6.2 GB · 128K 24.7 GB
Bits per weight: BF16 16, FP8 8.5, 4-bit 4.85. “Fits” = total ≤ 90% of memory; Mac GPU can use ~2/3 of unified memory (≤36GB) or ~3/4 (larger). For MoE, all experts must be in memory, so size by total parameters. Method →
03How to run it
Only runtimes the publisher or the runtime’s official library names for this model.
- vLLM — mentioned in the official model card
- SGLang — mentioned in the official model card
- Transformers — mentioned in the official model card
04Official repositories & quantised builds
2 official repo(s) from zai-org.
- GLM-4.6V main
- GLM-4.6V-FP8 FP8
05Other GLM / CogVideoX (Z.ai) models
All 35 →| Model | Params | 4-bit total | Released |
|---|---|---|---|
| GLM-5.3 | 753.3B | 504 GB | 2026-08-25 |
| GLM-5.3-Flash | 320B / 18B | 214 GB | 2026-08-25 |
| GLM-5.2 | 753.3B | 504 GB | 2026-06-16 |
| SCAIL-2 | — | — | 2026-06-09 |
| GLM-5.1 | 753.9B | 504 GB | 2026-04-03 |
| GLM-5 | 744B / 40B | 497 GB | 2026-02-11 |
| GLM-OCR | 1.32B | 1.9 GB | 2026-01-30 |
| GLM-4.7-Flash | 31.2B / 3B | 21.8 GB | 2026-01-19 |
06Sources
Data checked 2025-12-09. Parameters, context and licence are copied from the official repository; memory figures are our estimates.