GLM-5.2-FP8 vs GLM-5.2-AWQ-INT4
Specs, VRAM requirements and download trends — updated 11 September 2026.
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | GLM-5.2-FP8 | GLM-5.2-AWQ-INT4 |
|---|---|---|
| Parameters | 753.3 B | 753.3 B |
| Architecture | GlmMoeDsaForCausalLM | GlmMoeDsaForCausalLM |
| Context length | 1,048,576 | 1,048,576 |
| Licence | mit | mit |
| Commercial use | Allowed | Allowed |
| Languages | 2 | 2 |
| Downloads 30d | 977,752 | 195,725 |
| Downloads all time | 6.4 M | 517 K |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2026-06-16 | 2026-06-19 |
Download trend
Daily snapshots, last 56 days (28 Jul – 21 Sep)
3.1 M196 K
GLM-5.2-FP8
GLM-5.2-AWQ-INT4
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
GLM-5.2-AWQ-INT4 · fp16 @ 1024K ctx
14,986.1 GB / 24 GB
GLM-5.2-FP8 · fp16 @ 1024K ctx
15,295.6 GB / 24 GB