Qwen3.8-Flash-Next vs Inkling-Small
Specs, VRAM requirements and download trends — updated 24 October 2026.
thinkingmachines · B · Open weights
Params
266.0 B
Context
—
30d
884 K
apache-2.0 · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Qwen3.8-Flash-Next | Inkling-Small |
|---|---|---|
| Deployment | Open weights · also via API | Open weights · also via API |
| Parameters | 180.0 B | 266.0 B |
| Architecture | Qwen4ExpForConditionalGeneration | InklingForConditionalGeneration |
| Context length | 1,000,000 | 524,288 |
| Licence | other | apache-2.0 |
| Commercial use | Unknown | Allowed |
| Languages | — | — |
| Downloads 30d | 2,788,737 | 884,226 |
| Downloads all time | 3.6 M | 1.5 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2026-08-24 | 2026-07-27 |
| API input price / 1M tokens | $0.15 | $0.45 |
| API output price / 1M tokens | $0.47 | $1.20 |
| Est. cost per 1M input + 1M output tokens | $0.62 | $1.65 |
| Cached input / 1M tokens | $0.016 | $0.10 |
| AA Intelligence Index | — | 25.7 |
| AA Coding Index | — | 52.9 |
| AA Agentic Index | — | 23.5 |
| Max output tokens | 131,072 | 262,144 |
| API providers | 1 | 1 |
| 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
Inkling-Small
$1.65
Qwen3.8-Flash-Next is 2.7× cheaper at list price.
Download trend
Daily snapshots, last 30 days (25 Sep – 24 Oct)
2.8 M777 K
Qwen3.8-Flash-Next
Inkling-Small
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Qwen3.8-Flash-Next · fp16
423.5 GB / 24 GB
Inkling-Small · fp16
625.5 GB / 24 GB
Adjacent comparisons
Qwen3.8-Flash-Next vs Qwen3.8-Flash-Next-GSQ-RCO-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
Qwen3.8-Flash-Next vs Qwen3.8-Flash-Next-GSQ-RCO-abliterated-GGUF
GLM-5.3-Flash vs Inkling-Small