// Qwen · Text LLM
Qwen3-14B: VRAM & local deployment
14.8B parameters. About 11.7 GB at 4-bit and 34.3 GB at BF16 with one 8K-token request.
released 2025-04-27licence: Commercial OKmemory figures are estimates
01Specs
| Publisher | Alibaba Qwen · Qwen |
|---|---|
| Family / series | Qwen · Qwen3 |
| Type | Text LLM (text-generation) |
| Parameters | 14.8B Source: counted from official safetensors weights |
| Context length | 40K tokens (40,960)max_position_embeddings in config.json |
| Architecture | 40 layers · GQA |
| Released weights | BF16 · 29.5 GBdownload |
| Licence | Apache-2.0 · Commercial OKPermissive licence (Apache-2.0 / MIT / CC-BY / OpenMDW): commercial use allowed. |
| Released | 2025-04-27 (Hugging Face repo created) |
02How much VRAM it needs (estimate)
Total = weights + 10% + 0.5GB overhead + KV cache for one request (FP16 KV). More concurrent users multiply the KV column.
| Precision | Weights | Total @ 8K | Total @ 32K | Smallest GPU | Mac |
|---|---|---|---|---|---|
| BF16 / FP16 (original) | 29.5 GB | 34.3 GB | 38.4 GB | 2 × RTX 5090 (64GB) | Mac 64GB |
| FP8 / INT8 / Q8_0 | 15.7 GB | 19.1 GB | 23.1 GB | RTX 4090 24GB | Mac 36GB |
| 4-bit (Q4_K_M / AWQ / GPTQ-Int4) | 8.9 GB | 11.7 GB | 15.7 GB | 16GB GPU | Mac 24GB |
KV cache per request: 8K 1.3 GB · 32K 5.4 GB
Bits per weight: BF16 16, FP8 8.5, 4-bit 4.85. “Fits” = total ≤ 90% of memory; Mac GPU can use ~2/3 of unified memory (≤36GB) or ~3/4 (larger). For MoE, all experts must be in memory, so size by total parameters. Method →
03How to run it
Only runtimes the publisher or the runtime’s official library names for this model.
- vLLM — mentioned in the official model card
- SGLang — mentioned in the official model card
- llama.cpp — mentioned in the official model card
- LM Studio — mentioned in the official model card
- MLX — mentioned in the official model card
- Transformers — mentioned in the official model card
- KTransformers — mentioned in the official model card
- Ollama — in the official Ollama library · qwen3:14b
ollama run qwen3:14b04Official repositories & quantised builds
9 official repo(s) from Qwen.
- Qwen3-14B main
- Qwen3-14B-AWQ AWQ
- Qwen3-14B-GGUF GGUF
- Qwen3-14B-Base Base
- Qwen3-14B-FP8 FP8
- Qwen3-14B-MLX-4bit MLX
- Qwen3-14B-MLX-8bit MLX
- Qwen3-14B-MLX-6bit MLX
- Qwen3-14B-MLX-bf16 MLX/BF16
05Other Qwen models
All 112 →| Model | Params | 4-bit total | Released |
|---|---|---|---|
| Qwen3-0.6B · same series | 752M | 1.9 GB | 2025-04-27 |
| Qwen3-1.7B · same series | 2.03B | 2.8 GB | 2025-04-27 |
| Qwen3-4B · same series | 4.02B | 4.4 GB | 2025-04-27 |
| Qwen3-4B-Instruct-2507 · same series | 4.02B | 4.4 GB | 2025-08-05 |
| Qwen3-8B · same series | 8.19B | 7.2 GB | 2025-04-27 |
| Qwen3-30B-A3B-Instruct-2507 · same series | 30.5B / 3B | 21.7 GB | 2025-07-28 |
| Qwen3-30B-A3B · same series | 30.5B / 3B | 21.7 GB | 2025-04-27 |
| Qwen3-32B · same series | 32.8B | 24.5 GB | 2025-04-27 |
| Qwen3-235B-A22B · same series | 235.1B / 22B | 159 GB | 2025-04-27 |
| Qwen3-235B-A22B-Instruct-2507 · same series | 235.1B / 22B | 159 GB | 2025-07-21 |
| Qwen-Image-2.1-Turbo | 7.12B | 5.2 GB | 2026-10-09 |
| Qwen-Image-2.1 | 7.12B | 5.2 GB | 2026-09-14 |
| Qwen3.8-Flash-Next | 180B / 6B | 121 GB | 2026-08-24 |
| Qwen3.8-2.4T-A95B | 2.4T / 95B | 1.60 TB | 2026-08-08 |
| Qwen3.8-27B | 27.8B | 19.6 GB | 2026-08-05 |
| Qwen3.6-27B | 27.8B | 19.6 GB | 2026-04-21 |
| Qwen3.6-35B-A3B | 36B / 3B | 24.6 GB | 2026-04-15 |
| Qwen3.5-0.8B | 873M | 1.2 GB | 2026-02-28 |
06Sources
Data checked 2025-07-26. Parameters, context and licence are copied from the official repository; memory figures are our estimates.