Qwen3.5-9B vs Qwen3.8-27B-MLX-8bit
Specs, VRAM requirements and download trends — updated 24 October 2026.
lmstudio-community · B · Open weights
Params
8.0 B
Context
—
30d
3.6 M
apache-2.0 · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Qwen3.5-9B | Qwen3.8-27B-MLX-8bit |
|---|---|---|
| Deployment | Open weights · also via API | Open weights |
| Parameters | 9.7 B | 8.0 B |
| Architecture | Qwen3_5ForConditionalGeneration | Qwen3_5ForConditionalGeneration |
| Context length | 262,144 | — |
| Licence | apache-2.0 | apache-2.0 |
| Commercial use | Allowed | Allowed |
| Languages | — | — |
| Downloads 30d | 6,369,264 | 3,583,711 |
| Downloads all time | 71.5 M | 9.6 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2026-02-27 | 2026-08-14 |
| API input price / 1M tokens | $0.17 | not on OpenRouter |
| API output price / 1M tokens | $0.25 | not on OpenRouter |
| Est. cost per 1M input + 1M output tokens | $0.42 | not on OpenRouter |
| Cached input / 1M tokens | — | not on OpenRouter |
| AA Intelligence Index | 13.3 | not on OpenRouter |
| AA Coding Index | 23.5 | not on OpenRouter |
| AA Agentic Index | — | not on OpenRouter |
| Max output tokens | 235,929 | not on OpenRouter |
| API providers | 5 | 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
Qwen3.5-9B
$0.42
Download trend
Daily snapshots, last 89 days (28 Jul – 24 Oct)
14.3 M996 K
Qwen3.5-9B
Qwen3.8-27B-MLX-8bit
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Qwen3.5-9B · fp16
23.2 GB / 24 GB
Qwen3.8-27B-MLX-8bit · fp16
34.2 GB / 24 GB