// GLM / CogVideoX (Z.ai) · Text LLM
GLM-4.5: VRAM & local deployment
355B total · 32B active (MoE) parameters. About 240 GB at 4-bit and 785 GB at BF16 with one 8K-token request.
released 2025-07-20licence: Commercial OKmemory figures are estimates
01Specs
| Publisher | Z.ai (Zhipu) · zai-org |
|---|---|
| Family / series | GLM / CogVideoX (Z.ai) · GLM-4.5 |
| Type | Text LLM (text-generation) |
| Parameters | 355B total · 32B active (MoE) Source: official model card“GLM-4.5 has 355 billion total parameters with 32 billion active parameters” |
| Context length | 128K tokens (131,072)max_position_embeddings in config.json |
| Architecture | 92 layers · GQA · MoE |
| Released weights | BF16 · 717 GBdownload |
| Licence | MIT · Commercial OKPermissive licence (Apache-2.0 / MIT / CC-BY / OpenMDW): commercial use allowed. |
| Released | 2025-07-20 (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) | 710 GB | 785 GB | 794 GB | 831 GB | 8 × H200 (1,128GB) | — |
| FP8 / INT8 / Q8_0 | 377 GB | 418 GB | 428 GB | 465 GB | 8 × H100 (640GB) | — |
| 4-bit (Q4_K_M / AWQ / GPTQ-Int4) | 215 GB | 240 GB | 250 GB | 287 GB | 4 × RTX PRO 6000 (384GB) | Mac 512GB |
KV cache per request: 8K 3.1 GB · 32K 12.3 GB · 128K 49.4 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
3 official repo(s) from zai-org.
- GLM-4.5 main
- GLM-4.5-FP8 FP8
- GLM-4.5-Base Base
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 2025-08-11. Parameters, context and licence are copied from the official repository; memory figures are our estimates.