GLM-5.2-NVFP4 vs DeepSeek-V4-Flash-0731
Specs, VRAM requirements and download trends — updated 20 September 2026.
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | GLM-5.2-NVFP4 | DeepSeek-V4-Flash-0731 |
|---|---|---|
| Parameters | 381.0 B | 304.2 B |
| Architecture | GlmMoeDsaForCausalLM | DeepseekV4ForCausalLM |
| Context length | 1,048,576 | 1,048,576 |
| Licence | mit | mit |
| Commercial use | Allowed | Allowed |
| Languages | — | — |
| Downloads 30d | 791,024 | 4,178,593 |
| Downloads all time | 3.6 M | 7.0 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2026-06-22 | 2026-07-31 |
Download trend
Daily snapshots, last 55 days (28 Jul – 20 Sep)
4.7 M236 K
GLM-5.2-NVFP4
DeepSeek-V4-Flash-0731
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
DeepSeek-V4-Flash-0731 · fp16 @ 1024K ctx
6,024.3 GB / 24 GB
GLM-5.2-NVFP4 · fp16 @ 1024K ctx
7,826.8 GB / 24 GB