Qwen3.8-Flash-Next-GGUF vs GLM-4.5-Air
Specs, VRAM requirements and download trends — updated 10 November 2026.
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Qwen3.8-Flash-Next-GGUF | GLM-4.5-Air |
|---|---|---|
| Deployment | Open weights | Open weights · also via API |
| Parameters | 180.0 B | 110.5 B |
| Architecture | — | Glm4MoeForCausalLM |
| Context length | — | 131,072 |
| Licence | other | mit |
| Commercial use | Unknown | Allowed |
| Languages | — | 2 |
| Downloads 30d | 467,020 | 1,262,683 |
| Downloads all time | 1.3 M | 6.5 M |
| Quantizations on the Hub | GGUF | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2026-08-26 | 2025-07-20 |
| API input price / 1M tokens | not on OpenRouter | $0.20 |
| API output price / 1M tokens | not on OpenRouter | $1.10 |
| Est. cost per 1M input + 1M output tokens | not on OpenRouter | $1.30 |
| Cached input / 1M tokens | not on OpenRouter | $0.03 |
| AA Intelligence Index | not on OpenRouter | — |
| AA Coding Index | not on OpenRouter | — |
| AA Agentic Index | not on OpenRouter | — |
| Max output tokens | not on OpenRouter | 98,304 |
| API providers | not on OpenRouter | 3 |
| 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-4.5-Air
$1.30
Download trend
Daily snapshots, last 53 days (19 Sep – 10 Nov)
1.4 M184 K
Qwen3.8-Flash-Next-GGUF
GLM-4.5-Air
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Qwen3.8-Flash-Next-GGUF · Q4_K_M
76.9 GB / 24 GB
GLM-4.5-Air · fp16 @ 128K ctx
508.7 GB / 24 GB