Qwen2.5-Coder-32B-Instruct
- In Input modalities: Text Out Output modalities: Text
- Tool use
- Open weights
Prices
1 offering · prices as listed@cf/qwen/qwen2.5-coder-32b-instruct| Conditions/ 1M tokens | Input | Output |
|---|---|---|
| Standard | $0.66 | $1.00 |
Prices from Cloudflare Workers AI pricing (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
- —
- Licence
- apache-2.0
- Family
- qwen-coder
- Model ID
Not stated on Alibaba Qwen’s pages: max input, reasoning efforts, reasoning can be off, max thinking budget, structured output, built-in tools, knowledge cutoff, aliases.
Run locally
Weights: Qwen/Qwen2.5-Coder-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 128K (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 | 64.9 GB | ≈ 70.1 | ✕Doesn’t fit | — |
| 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 | 50.1 GB | ≈ 54.6 | ✕Doesn’t fit | — |
| Q5_K_Mmaker’s file | 43.3 GB | ≈ 47.5 | ✕Doesn’t fit | — |
| Q5_0maker’s file | 42.2 GB | ≈ 46.3 | ✕Doesn’t fit | — |
| Q4_K_Mmaker’s file | 37.0 GB | ≈ 40.8 | ○Needs system memory 2–3 tok/s | — |
| Q4_0maker’s file | 34.7 GB | ≈ 38.5 | ○Needs system memory 2–3 tok/s | — |
| 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 | 29.7 GB | ≈ 33.2 | ○Needs system memory 3–5 tok/s | — |
| IQ3_XXSquality drops | 11.7 GB | ≈ 14.3 | ●Runs well 34–51 tok/s | 32K |
| Q2_Kmaker’s filequality drops | 22.9 GB | ≈ 26.1 | ○Needs system memory 7–10 tok/s | — |
| 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 NVIDIA RTX 6000 Ada Generation; unified memory Apple M5 Max (40-core GPU) · 64 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- LMArena Text 1,271
#153 of 163 listed models · CI 1,263–1,279 · 5,432 votes
- LMArena Text · Chinese 1,281
#148 of 161 listed models · CI 1,256–1,306 · 528 votes
- LMArena Text · Coding 1,342
#147 of 163 listed models · CI 1,323–1,360 · 873 votes
- LMArena Text · Creative writing 1,207
#157 of 163 listed models · CI 1,187–1,226 · 836 votes
- LMArena (Arena), leaderboard-dataset on Hugging Face, licensed CC BY 4.0 · License · as of Oct 28, 2026
- changes we made
Changes
All changes →- Now priced on Cloudflare Workers AI Input $0.66 · Output $1.00
Sources
- Qwen/Qwen2.5-Coder-32B-Instruct model card (opens in a new tab) huggingface.co · checked Oct 31, 2026
- Cloudflare Workers AI pricing (opens in a new tab) developers.cloudflare.com · checked Nov 1, 2026
- Qwen/Qwen2.5-Coder-32B-Instruct model card (opens in a new tab) huggingface.co · checked Oct 31, 2026
- Qwen/Qwen2.5-Coder-32B-Instruct · Hugging Face (opens in a new tab) huggingface.co · checked Oct 31, 2026
- models.dev: alibaba/qwen2.5-coder-32b-instruct (community data, MIT) (opens in a new tab) github.com · checked Oct 11, 2026
- Qwen/Qwen2.5-Coder-32B-Instruct config.json (opens in a new tab) huggingface.co · checked Oct 31, 2026
- Qwen/Qwen2.5-Coder-32B-Instruct files (opens in a new tab) huggingface.co · checked Oct 31, 2026
- Qwen/Qwen2.5-Coder-32B-Instruct-AWQ files (opens in a new tab) huggingface.co · checked Nov 3, 2026
- Qwen/Qwen2.5-Coder-32B-Instruct-GGUF files (opens in a new tab) huggingface.co · checked Nov 1, 2026
- Qwen/Qwen2.5-Coder-32B-Instruct-GPTQ-Int4 files (opens in a new tab) huggingface.co · checked Oct 31, 2026
- Qwen/Qwen2.5-Coder-32B-Instruct-GPTQ-Int8 files (opens in a new tab) huggingface.co · checked Oct 31, 2026
- Qwen/Qwen2.5-Coder-32B-Instruct · Hugging Face (opens in a new tab) huggingface.co · checked Oct 31, 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