GLM-5.3 vs Trinity-Large-Thinking
Specs, VRAM requirements and download trends — updated 24 October 2026.
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | GLM-5.3 | Trinity-Large-Thinking |
|---|---|---|
| Deployment | Open weights · also via API | Open weights · also via API |
| Parameters | 753.3 B | 398.6 B |
| Architecture | GlmMoeDsaForCausalLM | AfmoeForCausalLM |
| Context length | 1,048,576 | 262,144 |
| Licence | other | other |
| Commercial use | Unknown | Unknown |
| Languages | 2 | 11 |
| Downloads 30d | 1,942,665 | 2,245 |
| Downloads all time | 3.1 M | 72 K |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2026-08-25 | 2026-04-01 |
| API input price / 1M tokens | $0.079 | $0.25 |
| API output price / 1M tokens | $1.40 | $0.80 |
| Est. cost per 1M input + 1M output tokens | $1.48 | $1.05 |
| Cached input / 1M tokens | $0.078 | $0.06 |
| AA Intelligence Index | 44.8 | 10.8 |
| AA Coding Index | 74.8 | 25.8 |
| AA Agentic Index | 53.1 | 1 |
| Max output tokens | 943,718 | 80,000 |
| API providers | 37 | 1 |
| Tool calling | Yes | Yes |
| Reasoning mode | Yes | Yes |
API cost
Estimated cost of 1M input + 1M output tokens via OpenRouter
GLM-5.3
$1.48
Trinity-Large-Thinking
$1.05
Trinity-Large-Thinking is 1.4× cheaper at list price.
Download trend
Daily snapshots, last 50 days (5 Sep – 24 Oct)
1.9 M2 K
GLM-5.3
Trinity-Large-Thinking
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Trinity-Large-Thinking · fp16 @ 256K ctx
2,791.0 GB / 24 GB
GLM-5.3 · fp16 @ 1024K ctx
15,295.6 GB / 24 GB