Qwen3 32B — Specifications
| Développeur | Alibaba |
|---|
| Type | LLM (dense) |
|---|
| Modalité | Text → Text |
|---|
| Paramètres | 32B |
|---|
| Fenêtre de contexte | 128K |
|---|
| Sortie maximale | — |
|---|
| Licence | Apache 2.0 (open) |
|---|
| Poids ouverts | ✅ Yes |
|---|
| Date de sortie | 2025 |
|---|
| Input price | $0.08 /1M |
|---|
| Output price | $0.28 /1M |
|---|
| API providers | Alibaba, OpenRouter, Ollama |
|---|
🖥️ Run it locally
| VRAM (4-bit) | ~20 GB |
|---|
| Minimum GPU | RTX 4090 24GB (Q4) |
|---|
Official page →
Alibaba’s largest dense Qwen3 — strong general reasoning and coding under a fully permissive Apache 2.0 license, with a 128K context. Comfortably runs 4-bit on a 24GB consumer GPU.
