Qwen3-14B
- In Input modalities: Text Out Output modalities: Text
- Reasoning
- Reasoning can be off
- Tool use
- Structured output
- Open weights
Prices
3 offerings · prices as listed| Conditions/ 1M tokens | Input | Output |
|---|---|---|
| Standard no longer listed since Oct 11, 2026 | $0.35 | $1.40 |
| Reasoning off no longer listed since Oct 11, 2026 | — | $1.40 |
| Reasoning on no longer listed since Oct 11, 2026 | — | $4.20 |
Prices from qwen3-14b model (opens in a new tab) (checked Oct 10, 2026) · Alibaba Cloud Model Studio pricing (opens in a new tab) (checked Oct 11, 2026)
| Conditions/ 1M tokens | Input | Output |
|---|---|---|
| Standard no longer listed since Oct 11, 2026 | $0.144 | $0.574 |
| Reasoning off no longer listed since Oct 11, 2026 | — | $0.574 |
| Reasoning on no longer listed since Oct 11, 2026 | — | $1.434 |
Prices from Alibaba Cloud Model Studio pricing (opens in a new tab) (checked Oct 11, 2026) · qwen3-14b model (opens in a new tab) (checked Oct 10, 2026)
| Conditions/ 1M tokens | Input | Output |
|---|---|---|
| Standard no longer listed since Oct 11, 2026 | ¥1.00 | — |
| Reasoning off no longer listed since Oct 11, 2026 | — | ¥4.00 |
| Reasoning on no longer listed since Oct 11, 2026 | — | ¥10.00 |
Prices from 阿里云百炼：模型价格 (opens in a new tab) (checked Oct 6, 2026)
Standard: the price a request with no conditions pays (the headline price elsewhere on the site).
Details
- Built-in tools
- Web search
- Knowledge cutoff
- Apr 2025
- Licence
- apache-2.0
- Family
- qwen
- Model ID
Not stated on Alibaba Qwen’s pages: max input, reasoning efforts, max thinking budget, aliases.
Run locally
Weights: Qwen/Qwen3-14B- Parameters 14.8B
- Dense
- Native precision BF16
- Layers 40
- KV cache per token 160 KB
- Native context 32K (model card)
- With YaRN 128K (model card)
- Config positions 40K (config.json max_position_embeddings)
- API context 128K (maker’s API)
- Needs
- ≈ 16.6 GB (weights 14.6 (maker’s file) + KV cache 1.3 + overhead 0.7)
- Usable
- 21.6 GB (90% of its memory)
- Generation speed
- 30–44 tok/s
- Longest context
- 40K (longer doesn’t fit)
- First token
- about 0.48–0.72 s for a 2K prompt
| Precision | Weights | Needs at 8K | On your hardware | Longest context |
|---|---|---|---|---|
| BF16 (native)maker’s file | 27.5 GB | ≈ 30.1 | ○Needs system memory 4–6 tok/s | — |
| Q8_0maker’s file | 14.6 GB | ≈ 16.6 | ●Runs well 30–44 tok/s | 40K |
| FP8maker’s file | 15.2 GB | ≈ 17.2 | ●Runs well 29–43 tok/s | 36K |
| Q6_Kmaker’s file | 11.3 GB | ≈ 13.1 | ●Runs well 37–56 tok/s | 128K |
| Q5_K_Mmaker’s file | 9.8 GB | ≈ 11.5 | ●Runs well 43–64 tok/s | 128K |
| Q5_0maker’s file | 9.6 GB | ≈ 11.3 | ●Runs well 43–65 tok/s | 128K |
| Q4_K_Mmaker’s file | 8.4 GB | ≈ 10.1 | ●Runs well 49–73 tok/s | 128K |
| Q4_0 | 7.7 GB | ≈ 9.5 | ●Runs well 52–78 tok/s | 128K |
| INT4 (AWQ / GPTQ)maker’s file | 9.3 GB | ≈ 11.0 | ●Runs well 45–67 tok/s | 128K |
| IQ4_XS | 7.3 GB | ≈ 9.1 | ●Runs well 55–82 tok/s | 128K |
| Q3_K_Mquality drops | 6.7 GB | ≈ 8.5 | ●Runs well 59–88 tok/s | 128K |
| IQ3_XXSquality drops | 5.3 GB | ≈ 7.0 | ●Runs well 72–108 tok/s | 128K |
| Q2_Kquality drops | 5.2 GB | ≈ 6.9 | ●Runs well 73–110 tok/s | 128K |
| IQ2_XXSquality drops | 3.5 GB | ≈ 5.3 | ●Runs well 98–147 tok/s | 128K |
Click a row to choose a precision. “Maker’s file” sizes are the maker’s own files; others are parameters × bits per weight.
Compared with other hardware
Each at the highest precision it runs. Click one for details.
Smallest that runs it (Q4_K_M, 8K): GPU GeForce RTX 5070; unified memory Apple M5 · 16 GB.
Run commands
llama-server -hf Qwen/Qwen3-14B-GGUF:Q8_0 -c 8192
ollama run hf.co/Qwen/Qwen3-14B-GGUF:Q8_0
Memory to fine-tune
Batch 1, 2,048-token sequences, gradient checkpointing; LoRA and QLoRA train rank-16 adapters on the attention projections.
Estimates; facts from the maker’s Hugging Face repositories, as of 2026-11-06. How it’s estimated
Cited scores
From third-party leaderboards, not measured by us- Epoch Capabilities Index 136.2
#104 of 118 listed models · CI 133.5–138.8
- Epoch AI · GPQA Diamond 63.8%
#107 of 168 listed models · ±2.93
Also listed: reasoning off 53.4%
- Epoch AI · OTIS Mock AIME 2024–2025 66.4%
#96 of 159 listed models · ±6.19
Also listed: reasoning off 25.8%
- EQ-Bench Longform Writing 35.9
#83 of 92 listed models
- Epoch AI, 'Capabilities & benchmarking'. Published online at epoch.ai. Retrieved from 'https://epoch.ai/benchmarks'. Licensed CC BY 4.0. · License · as of Nov 4 – 5, 2026
- EQ-Bench by Samuel J. Paech (eqbench.com; EQ-bench/EQ-bench-site on GitHub), MIT License. · License · as of Oct 28, 2026
- changes we made
Changes
All changes →- Context window 256K → 131.07K
Sources
- Alibaba Cloud Model Studio pricing (opens in a new tab) alibabacloud.com · checked Oct 11, 2026
- 阿里云百炼：模型价格in Chinese (opens in a new tab) help.aliyun.com · checked Oct 6, 2026
- Text generation models - Qwen, DeepSeek, GLM | Model Studio - Alibaba Cloud Model Studio - Alibaba Cloud Documentation Center (opens in a new tab) alibabacloud.com · checked Oct 10, 2026
- 模型上下架与更新-大模型服务平台百炼-阿里云_大模型服务平台百炼(Model Studio)-大模型服务平台百炼(Model Studio)-阿里云帮助中心in Chinese (opens in a new tab) help.aliyun.com · checked Oct 30, 2026
- qwen3-14b model (opens in a new tab) alibabacloud.com · checked Oct 10, 2026
- models.dev: qwen3-14b (community data, MIT) (opens in a new tab) github.com · checked Sep 30, 2026
- qwen3-14b 模型信息-大模型服务平台百炼(Model Studio)-阿里云帮助中心in Chinese (opens in a new tab) help.aliyun.com · checked Oct 9, 2026
- qwen3-14b model (opens in a new tab) alibabacloud.com · checked Oct 10, 2026
- Qwen/Qwen3-14B model card (opens in a new tab) huggingface.co · checked Oct 31, 2026
- Qwen/Qwen3-14B config.json (opens in a new tab) huggingface.co · checked Oct 31, 2026
- Qwen/Qwen3-14B files (opens in a new tab) huggingface.co · checked Oct 31, 2026
- Qwen/Qwen3-14B-AWQ files (opens in a new tab) huggingface.co · checked Nov 2, 2026
- Qwen/Qwen3-14B-FP8 files (opens in a new tab) huggingface.co · checked Oct 31, 2026
- Qwen/Qwen3-14B-GGUF files (opens in a new tab) huggingface.co · checked Nov 1, 2026
- Qwen/Qwen3-14B-MLX-4bit files (opens in a new tab) huggingface.co · checked Oct 31, 2026
- Qwen/Qwen3-14B-MLX-6bit files (opens in a new tab) huggingface.co · checked Nov 2, 2026
- Qwen/Qwen3-14B-MLX-8bit files (opens in a new tab) huggingface.co · checked Nov 2, 2026
- Qwen/Qwen3-14B-MLX-bf16 files (opens in a new tab) huggingface.co · checked Nov 2, 2026
- Qwen3-14B (opens in a new tab) huggingface.co · checked Oct 31, 2026
- Qwen/Qwen3-14B README.md (opens in a new tab) huggingface.co · checked Nov 4, 2026
Alibaba Qwen’s official policies: data use, privacy, terms →
Some values on this page are still waiting to be checked against official pages: a filled dot is verified, a hollow one is not yet (with or without a source on file). How we verify data
Alibaba Qwen · China · qwen.ai
Related models
Snapshots, the same family and other models from this provider