Qwen2.5-32B-Instruct
- In Input modalities: Text Out Output modalities: Text
- Tool use
- Structured output
- Open weights
Prices
1 offering · prices as listedqwen2.5-32b-instruct| Conditions/ 1M tokens | Input | Output |
|---|---|---|
| Standard | ¥2.00 | ¥6.00 |
Prices from How to check model training and deployment pricing-Alibaba Cloud Model Studio(Model Studio)-阿里云帮助中心 (opens in a new tab) (checked Nov 1, 2026)
Standard: the price a request with no conditions pays (the headline price elsewhere on the site).
Details
- Reasoning
- —
- Knowledge cutoff
- Apr 2024
- Licence
- apache-2.0
- Family
- qwen
- Model ID
Not stated on Alibaba Qwen’s pages: max input, reasoning efforts, reasoning can be off, max thinking budget, built-in tools, aliases.
Run locally
Weights: Qwen/Qwen2.5-32B-Instruct- Parameters 32.8B
- Dense
- Native precision BF16
- Layers 64
- KV cache per token 256 KB
- Config positions 32K (config.json max_position_embeddings)
- API context 977K (maker’s API)
- Needs
- ≈ 19.0 GB (weights 16.2 + KV cache 2.0 + overhead 0.8)
- Usable
- 21.6 GB (90% of its memory)
- Generation speed
- 26–39 tok/s
- Longest context
- 18K (longer doesn’t fit)
- First token
- about 1.06–1.59 s for a 2K prompt
| Precision | Weights | Needs at 8K | On your hardware | Longest context |
|---|---|---|---|---|
| BF16 (native)maker’s file | 61.0 GB | ≈ 66.1 | ✕Doesn’t fit | — |
| Q8_0maker’s file | 32.4 GB | ≈ 36.1 | ○Needs system memory 3–4 tok/s | — |
| INT8 (GPTQ)maker’s file | 32.7 GB | ≈ 36.3 | ○Needs system memory 3–4 tok/s | — |
| FP8 | 30.5 GB | ≈ 34.0 | ○Needs system memory 3–4 tok/s | — |
| Q6_Kmaker’s file | 25.0 GB | ≈ 28.3 | ○Needs system memory 5–7 tok/s | — |
| Q5_K_Mmaker’s file | 21.7 GB | ≈ 24.7 | ○Needs system memory 8–12 tok/s | — |
| Q5_0maker’s file | 21.1 GB | ≈ 24.1 | ○Needs system memory 10–15 tok/s | — |
| Q4_K_Mmaker’s file | 18.5 GB | ≈ 21.4 | ●Runs well 23–34 tok/s | 9K |
| Q4_0maker’s file | 17.4 GB | ≈ 20.2 | ●Runs well 24–36 tok/s | 13K |
| INT4 (AWQ / GPTQ)maker’s file | 18.0 GB | ≈ 20.9 | ●Runs well 23–35 tok/s | 11K |
| IQ4_XS | 16.2 GB | ≈ 19.0 | ●Runs well 26–39 tok/s | 18K |
| Q3_K_Mmaker’s filequality drops | 14.8 GB | ≈ 17.6 | ●Runs well 28–42 tok/s | 24K |
| IQ3_XXSquality drops | 11.7 GB | ≈ 14.3 | ●Runs well 34–51 tok/s | 32K |
| Q2_Kmaker’s filequality drops | 11.5 GB | ≈ 14.0 | ●Runs well 35–52 tok/s | 32K |
| IQ2_XXSquality drops | 7.9 GB | ≈ 10.4 | ●Runs well 48–71 tok/s | 32K |
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 4090; unified memory Apple M5 Max (32-core GPU) · 36 GB.
Run commands
The maker publishes no files at this precision. Choose its native precision or one of its own builds, or quantise it yourself with llama.cpp.
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 AI · GPQA Diamond 46.1%
#138 of 168 listed models · ±2.6
- Epoch AI · MATH Level 5 56.1%
#34 of 64 listed models · ±1.08
- Epoch AI · OTIS Mock AIME 2024–2025 7.4%
#135 of 159 listed models · ±2.14
- Epoch AI, 'Capabilities & benchmarking'. Published online at epoch.ai. Retrieved from 'https://epoch.ai/benchmarks'. Licensed CC BY 4.0. · License · as of Oct 18 – Nov 4, 2026
- changes we made
Changes
All changes →No changes recorded yet.
Sources
- Text generation models - Qwen, DeepSeek, GLM | Model Studio - Alibaba Cloud Model Studio - Alibaba Cloud Documentation Center (opens in a new tab) docs.modelstudio.console.alibabacloud.com · checked Oct 15, 2026
- Qwen2.5-32B-Instruct (opens in a new tab) huggingface.co · checked Oct 31, 2026
- How to check model training and deployment pricing-Alibaba Cloud Model Studio(Model Studio)-阿里云帮助中心in Chinese (opens in a new tab) help.aliyun.com · checked Nov 1, 2026
- models.dev: qwen2-5-32b-instruct (community data, MIT) (opens in a new tab) github.com · checked Sep 30, 2026
- Qwen2.5: A Party of Foundation Models! | Qwen (opens in a new tab) qwenlm.github.io · checked Sep 30, 2026
- Qwen/Qwen2.5-32B-Instruct model card (opens in a new tab) huggingface.co · checked Oct 31, 2026
- Qwen/Qwen2.5-32B-Instruct config.json (opens in a new tab) huggingface.co · checked Oct 31, 2026
- Qwen/Qwen2.5-32B-Instruct files (opens in a new tab) huggingface.co · checked Oct 31, 2026
- Qwen/Qwen2.5-32B-Instruct-AWQ files (opens in a new tab) huggingface.co · checked Oct 31, 2026
- Qwen/Qwen2.5-32B-Instruct-GGUF files (opens in a new tab) huggingface.co · checked Oct 31, 2026
- Qwen/Qwen2.5-32B-Instruct-GPTQ-Int4 files (opens in a new tab) huggingface.co · checked Nov 1, 2026
- Qwen/Qwen2.5-32B-Instruct-GPTQ-Int8 files (opens in a new tab) huggingface.co · checked Oct 31, 2026
- Qwen2.5-32B-Instruct-GGUF (opens in a new tab) huggingface.co · checked Nov 1, 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