GLM-5-FP8 vs MiniMax-M3-NVFP4
Specs, VRAM requirements and download trends — updated 30 July 2026.
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | GLM-5-FP8 | MiniMax-M3-NVFP4 |
|---|---|---|
| Parameters | 753.9 B | 246.6 B |
| Architecture | GlmMoeDsaForCausalLM | MiniMaxM3SparseForConditionalGeneration |
| Context length | 202,752 | — |
| Licence | mit | other |
| Commercial use | Allowed | Unknown |
| Languages | 2 | — |
| Downloads 30d | 202,976 | 185,942 |
| Downloads all time | 13.0 M | 842 K |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2026-02-11 | 2026-06-23 |
Download trend
Daily snapshots, last 56 days (28 Jul – 21 Sep)
1.3 M186 K
GLM-5-FP8
MiniMax-M3-NVFP4
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
MiniMax-M3-NVFP4 · fp16
312.6 GB / 24 GB
GLM-5-FP8 · fp16 @ 198K ctx
3,631.2 GB / 24 GB