GLM-5 vs Qwen3.8-2.4T-A95B
Specs, VRAM requirements and download trends — updated 24 October 2026.
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | GLM-5 | Qwen3.8-2.4T-A95B |
|---|---|---|
| Deployment | Open weights · also via API | Open weights · also via API |
| Parameters | 753.9 B | 2,446.2 B |
| Architecture | GlmMoeDsaForCausalLM | Qwen3_5MoeForCausalLM |
| Context length | 202,752 | 262,144 |
| Licence | mit | other |
| Commercial use | Allowed | Unknown |
| Languages | 2 | — |
| Downloads 30d | 1,020,783 | 24,938 |
| Downloads all time | 2.4 M | 101 K |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2026-02-11 | 2026-08-08 |
| API input price / 1M tokens | $1.00 | $2.00 |
| API output price / 1M tokens | $3.20 | $6.00 |
| Est. cost per 1M input + 1M output tokens | $4.20 | $8.00 |
| Cached input / 1M tokens | $0.20 | $0.25 |
| AA Intelligence Index | 27.9 | 39.9 |
| AA Coding Index | — | 71.9 |
| AA Agentic Index | — | 50.1 |
| Max output tokens | 131,072 | 909,000 |
| API providers | 8 | 5 |
| Tool calling | Yes | Yes |
| Reasoning mode | Yes | Yes |
API cost
Estimated cost of 1M input + 1M output tokens via OpenRouter
GLM-5
$4.20
Qwen3.8-2.4T-A95B
$8.00
GLM-5 is 1.9× cheaper at list price.
Download trend
Daily snapshots, last 89 days (28 Jul – 24 Oct)
1.0 M25 K
GLM-5
Qwen3.8-2.4T-A95B
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
GLM-5 · fp16 @ 198K ctx
4,457.7 GB / 24 GB
Qwen3.8-2.4T-A95B · fp16 @ 256K ctx
17,123.8 GB / 24 GB