Qwen3.6-27B vs Qwen3.6-27B-MLX-5bit
Specs, VRAM requirements and download trends — updated 28 July 2026.
lmstudio-community · B · Open weights
Params
5.5 B
Context
—
30d
892 K
apache-2.0 · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Qwen3.6-27B | Qwen3.6-27B-MLX-5bit |
|---|---|---|
| Deployment | Open weights · also via API | Open weights |
| Parameters | 27.8 B | 5.5 B |
| Architecture | Qwen3_5ForConditionalGeneration | Qwen3_5ForConditionalGeneration |
| Context length | 262,144 | — |
| Licence | apache-2.0 | apache-2.0 |
| Commercial use | Allowed | Allowed |
| Languages | — | — |
| Downloads 30d | 2,349,158 | 892,271 |
| Downloads all time | 30.9 M | 2.1 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2026-04-21 | 2026-06-02 |
| API input price / 1M tokens | $0.32 | not on OpenRouter |
| API output price / 1M tokens | $3.20 | not on OpenRouter |
| Est. cost per 1M input + 1M output tokens | $3.52 | not on OpenRouter |
| Cached input / 1M tokens | — | not on OpenRouter |
| AA Intelligence Index | — | not on OpenRouter |
| AA Coding Index | 53.7 | not on OpenRouter |
| AA Agentic Index | 18.5 | not on OpenRouter |
| Max output tokens | 81,920 | not on OpenRouter |
| API providers | 7 | 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
Qwen3.6-27B
$3.52
Download trend
Daily snapshots, last 90 days (13 Aug – 10 Nov)
7.1 M892 K
Qwen3.6-27B
Qwen3.6-27B-MLX-5bit
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Qwen3.6-27B-MLX-5bit · fp16
22.7 GB / 24 GB
Qwen3.6-27B · fp16
65.8 GB / 24 GB