Qwen3.8-Flash-Next vs Qwen3.5-122B-A10B
Specs, VRAM requirements and download trends — updated 10 November 2026.
Qwen · B · Open weights
Params
125.1 B
Context
—
30d
925 K
apache-2.0 · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Qwen3.8-Flash-Next | Qwen3.5-122B-A10B |
|---|---|---|
| Deployment | Open weights · also via API | Open weights · also via API |
| Parameters | 180.0 B | 125.1 B |
| Architecture | Qwen4ExpForConditionalGeneration | Qwen3_5MoeForConditionalGeneration |
| Context length | 1,000,000 | 262,144 |
| Licence | other | apache-2.0 |
| Commercial use | Unknown | Allowed |
| Languages | — | — |
| Downloads 30d | 3,471,211 | 924,624 |
| Downloads all time | 5.9 M | 8.4 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2026-08-24 | 2026-02-24 |
| API input price / 1M tokens | $0.15 | $0.26 |
| API output price / 1M tokens | $0.47 | $2.08 |
| Est. cost per 1M input + 1M output tokens | $0.62 | $2.34 |
| Cached input / 1M tokens | $0.016 | — |
| AA Intelligence Index | — | — |
| AA Coding Index | — | 45.7 |
| AA Agentic Index | — | 7.6 |
| Max output tokens | 131,072 | 65,536 |
| API providers | 1 | 4 |
| Tool calling | Yes | Yes |
| Reasoning mode | Yes | Yes |
API cost
Estimated cost of 1M input + 1M output tokens via OpenRouter
Qwen3.8-Flash-Next
$0.62
Qwen3.5-122B-A10B
$2.34
Qwen3.8-Flash-Next is 3.8× cheaper at list price.
Download trend
Daily snapshots, last 47 days (25 Sep – 10 Nov)
4.2 M830 K
Qwen3.8-Flash-Next
Qwen3.5-122B-A10B
A overtook B on 27 Sep
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Qwen3.5-122B-A10B · fp16
294.5 GB / 24 GB
Qwen3.8-Flash-Next · fp16
423.5 GB / 24 GB
Adjacent comparisons
Qwen3.8-Flash-Next vs Qwen3.8-Flash-Next-GSQ-RCO-GGUF
Qwen3.8-Flash-Next vs Qwen3.8-Flash-Next-GSQ-RCO-abliterated-GGUF
GLM-5.3-Flash vs Qwen3.8-Flash-Next
Qwen3.8-27B-iMatrix-NVFP4-MTP-GGUF vs Qwen3.8-Flash-Next
Qwen3.8-27B-Uncensored-HauhauCS-Aggressive-MTP-GGUF vs Qwen3.8-Flash-Next
Qwen3.6-35B-A3B-MTP-GGUF vs Qwen3.8-Flash-Next