All models
Alibaba (Qwen)
Qwen2.5 Coder 32B Instruct fastruns locally
alibaba/qwen-2-5-coder-32b
Qwen2.5-Coder is the latest series of Code-Specific Qwen large language models (formerly known as CodeQwen). Qwen2.5-Coder brings the following improvements upon CodeQwen1.5: - Significantly improvements in **code generation**, **code reasoning**...
Input / 1M
$0.66
USD per million tokens
Output / 1M
$1.00
USD per million tokens
Est. cost / token
$0.000000745
$0.74 per 1M, 3:1 mix
Context window
33K
max output 29K
Major features
Open weightsJSON schema
Task suitability (heuristic 1–5, not a benchmark)
- coding4
- reasoning2
- math2
- summarization4
- extraction4
- classification4
- chat3
- creative3
- translation4
- vision1
- long context2
- agentic1
Run it locally
Will it run on my machine? →ollama run qwen2.5-coder:32b| Quantization | Quality | Memory needed (8K ctx) |
|---|---|---|
| Q2_K | poor | 17 GB |
| Q3_K_M | fair | 19.4 GB |
| Q4_K_Mrecommended | good | 23.6 GB |
| Q5_K_M | very good | 27 GB |
| Q6_K | excellent | 30.8 GB |
| Q8_0 | near-lossless | 39.1 GB |
| F16 | lossless | 71.4 GB |
Estimates.
Price history
| Recorded | Input | Output | Cached | Source |
|---|---|---|---|---|
| 2026-11-05 03:20 | $0.66 | $1.00 | — | openrouter |
A row is added whenever a sync detects a price change. Vendor pricing source
Pricing (USD per 1M tokens)
- Input
- $0.66
- Output
- $1.00
- Blended (3:1)
- $0.74
Details
- Company
- Alibaba (Qwen)
- Version
- 2.5
- Family
- Qwen
- Released
- 2024-11-11
- Parameters
- 32.8B
- Max output
- 29K
- Open weights
- Yes
- Inputs
- text
- Last synced
- 25 min ago