GLM-4.5-Air vs Laguna-S-2.1-APEX-GGUF
Specs, VRAM requirements and download trends — updated 23 October 2026.
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | GLM-4.5-Air | Laguna-S-2.1-APEX-GGUF |
|---|---|---|
| Deployment | Open weights · also via API | Open weights |
| Parameters | 110.5 B | 117.6 B |
| Architecture | Glm4MoeForCausalLM | — |
| Context length | 131,072 | 1,048,576 |
| Licence | mit | openmdw-1.1 |
| Commercial use | Allowed | Unknown |
| Languages | 2 | — |
| Downloads 30d | 817,559 | 184,755 |
| Downloads all time | 5.5 M | 329 K |
| Quantizations on the Hub | SAFETENSORS | GGUF |
| Gated | No | No |
| First seen on the Hub | 2025-07-20 | 2026-07-22 |
| API input price / 1M tokens | $0.13 | not on OpenRouter |
| API output price / 1M tokens | $0.85 | not on OpenRouter |
| Est. cost per 1M input + 1M output tokens | $0.98 | not on OpenRouter |
| Cached input / 1M tokens | $0.025 | not on OpenRouter |
| AA Intelligence Index | 11.1 | not on OpenRouter |
| AA Coding Index | — | not on OpenRouter |
| AA Agentic Index | — | not on OpenRouter |
| Max output tokens | 98,304 | not on OpenRouter |
| API providers | 3 | not on OpenRouter |
| Tool calling | Yes | not on OpenRouter |
| Reasoning mode | Yes | not on OpenRouter |
API cost
Estimated cost of 1M input + 1M output tokens via OpenRouter
GLM-4.5-Air
$0.98
Download trend
Daily snapshots, last 88 days (28 Jul – 23 Oct)
818 K183 K
GLM-4.5-Air
Laguna-S-2.1-APEX-GGUF
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Laguna-S-2.1-APEX-GGUF · Q4_K
18.9 GB / 24 GB
GLM-4.5-Air · fp16 @ 128K ctx
508.7 GB / 24 GB