GLM-5.1-FP8 vs GLM-5
Specs, VRAM requirements and download trends — updated 25 October 2026.
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | GLM-5.1-FP8 | GLM-5 |
|---|---|---|
| Deployment | Open weights | Open weights · also via API |
| Parameters | 753.9 B | 753.9 B |
| Architecture | GlmMoeDsaForCausalLM | GlmMoeDsaForCausalLM |
| Context length | 202,752 | 202,752 |
| Licence | mit | mit |
| Commercial use | Allowed | Allowed |
| Languages | 2 | 2 |
| Downloads 30d | 200,338 | 1,138,007 |
| Downloads all time | 4.1 M | 2.5 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2026-04-03 | 2026-02-11 |
| API input price / 1M tokens | not on OpenRouter | $1.00 |
| API output price / 1M tokens | not on OpenRouter | $3.20 |
| Est. cost per 1M input + 1M output tokens | not on OpenRouter | $4.20 |
| Cached input / 1M tokens | not on OpenRouter | $0.20 |
| AA Intelligence Index | not on OpenRouter | 27.9 |
| AA Coding Index | not on OpenRouter | — |
| AA Agentic Index | not on OpenRouter | — |
| Max output tokens | not on OpenRouter | 131,072 |
| API providers | not on OpenRouter | 8 |
| Tool calling | not on OpenRouter | Yes |
| Reasoning mode | not on OpenRouter | Yes |
API cost
Estimated cost of 1M input + 1M output tokens via OpenRouter
GLM-5
$4.20
Download trend
Daily snapshots, last 90 days (28 Jul – 25 Oct)
1.1 M157 K
GLM-5.1-FP8
GLM-5
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
GLM-5.1-FP8 · fp16 @ 198K ctx
3,631.2 GB / 24 GB
GLM-5 · fp16 @ 198K ctx
4,457.7 GB / 24 GB