Hy3 vs GLM-4.6
Specs, VRAM requirements and download trends — updated 25 October 2026.
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Hy3 | GLM-4.6 |
|---|---|---|
| Deployment | Open weights · also via API | Open weights · also via API |
| Parameters | 298.8 B | 356.8 B |
| Architecture | HYV3ForCausalLM | Glm4MoeForCausalLM |
| Context length | 262,144 | 202,752 |
| Licence | apache-2.0 | mit |
| Commercial use | Allowed | Allowed |
| Languages | — | 2 |
| Downloads 30d | 941,699 | 21,104 |
| Downloads all time | 988 K | 825 K |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2026-07-02 | 2025-09-29 |
| API input price / 1M tokens | $0.13 | $0.55 |
| API output price / 1M tokens | $0.53 | $2.20 |
| Est. cost per 1M input + 1M output tokens | $0.66 | $2.75 |
| Cached input / 1M tokens | $0.033 | $0.11 |
| AA Intelligence Index | — | 18.5 |
| AA Coding Index | — | 45.8 |
| AA Agentic Index | — | — |
| Max output tokens | 128,000 | 131,072 |
| API providers | 5 | 4 |
| Tool calling | Yes | Yes |
| Reasoning mode | Yes | Yes |
API cost
Estimated cost of 1M input + 1M output tokens via OpenRouter
Hy3
$0.66
GLM-4.6
$2.75
Hy3 is 4.2× cheaper at list price.
Download trend
Daily snapshots, last 27 days (29 Sep – 25 Oct)
942 K19 K
Hy3
GLM-4.6
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Hy3 · fp16 @ 256K ctx
2,092.0 GB / 24 GB
GLM-4.6 · fp16 @ 198K ctx
2,110.0 GB / 24 GB