Qwen3.8-27B vs Qwen3.8-27B-4bit
Specs, VRAM requirements and download trends — updated 24 October 2026.
mlx-community · B · Open weights
Params
27.4 B
Context
—
30d
880 K
apache-2.0 · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Qwen3.8-27B | Qwen3.8-27B-4bit |
|---|---|---|
| Deployment | Open weights · also via API | Open weights |
| Parameters | 27.8 B | 27.4 B |
| Architecture | Qwen3_5ForConditionalGeneration | Qwen3_5ForConditionalGeneration |
| Context length | 262,144 | — |
| Licence | apache-2.0 | apache-2.0 |
| Commercial use | Allowed | Allowed |
| Languages | — | — |
| Downloads 30d | 7,710,011 | 880,431 |
| Downloads all time | 17.7 M | 1.1 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2026-08-05 | 2026-08-14 |
| API input price / 1M tokens | $0.20 | not on OpenRouter |
| API output price / 1M tokens | $2.50 | not on OpenRouter |
| Est. cost per 1M input + 1M output tokens | $2.70 | not on OpenRouter |
| Cached input / 1M tokens | $0.09 | not on OpenRouter |
| AA Intelligence Index | 33.7 | not on OpenRouter |
| AA Coding Index | 68.1 | not on OpenRouter |
| AA Agentic Index | 45.8 | not on OpenRouter |
| Max output tokens | 235,929 | not on OpenRouter |
| API providers | 21 | 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
Qwen3.8-27B
$2.70
Download trend
Daily snapshots, last 66 days (20 Aug – 24 Oct)
7.8 M800 K
Qwen3.8-27B
Qwen3.8-27B-4bit
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Qwen3.8-27B-4bit · fp16
22.3 GB / 24 GB
Qwen3.8-27B · fp16
65.8 GB / 24 GB