# Qwen2.5 Coder 32B Instruct

> Qwen2.5-Coder is the latest series of Code-Specific Qwen large language models (formerly known as CodeQwen).

Qwen2.5 Coder 32B Instruct has a SharkScore of 34.3/100, ranked #209 of 608 in Models (updated 2026-11-19).

- Website: https://openrouter.ai/qwen/qwen-2.5-coder-32b-instruct (openrouter.ai)
- Kind: Model · Pricing: Open source
- Maker: qwen
- Categories: Models, Model APIs & inference
- Verified by the maker: no

## Why it scores 34.3

| Part | Score (0–100) | Weight |
|---|---|---|
| Adoption | 29 | 30% |
| User reviews | no data | 25% |
| Maintenance | 0 | 20% |
| Trust & transparency | 80 | 15% |
| Momentum | no data | 10% |

Evidence covers 87% of the score's weight. Compared with other listings in Models.

## Evidence

| Signal | Value |
|---|---|
| Traffic rank (Tranco) | — |
| GitHub stars | — |
| Stars, last 90 days | — |
| Downloads, 30 days | 529.9K |
| Reviews | none yet |
| Last update | 676 days ago |
| Uptime, 30 days | — |
| Public pricing / Free tier / API / MCP | yes / yes / yes / no |

## RankShark review

Automated evaluation by RankShark · 2026-11-18 · method review-1.0 · https://rankshark.pro/how-we-review
We were not paid for this review.

As of 2026-11-18, Qwen2.5 Coder 32B Instruct is a text model aimed at coding tasks; the OpenRouter listing reports a 32,768-token context window and usage-based rates. [E1, E2]

An instruction-tuned, 32.5-billion-parameter text model in Qwen’s code-specific model series. The model card documents Transformers use and an Apache-2.0 license. [E1]

### Pros

- The model card provides a Transformers loading and generation example.
- The model card lists an Apache-2.0 license.
- The OpenRouter listing provides rates per input and output token.

### Cons

- The OpenRouter listing reports a 32,768-token context window; using longer contexts requires additional YaRN configuration according to the model card.
- The vendor notes that vLLM’s static YaRN scaling can potentially affect performance on shorter texts.
- No free plan or free trial stated on the pages we checked.
- Whether customer data is used for model training is not stated on the pages we checked.

### Pricing

| Plan | Price | Limits |
|---|---|---|
| OpenRouter per-token inference | $0.66 per million input tokens; $1 per million output tokens | The OpenRouter listing reports a 32,768-token context window. |

Checked 2026-11-18

### Sources

- https://huggingface.co/Qwen/Qwen2.5-Coder-32B-Instruct (fetched 2026-11-18)
- https://openrouter.ai/qwen/qwen-2.5-coder-32b-instruct (fetched 2026-11-18)

## Top alternatives

1. [Qwen3.8 27B](https://rankshark.pro/tools/qwen38-27b) — SharkScore 67.1. Qwen3.8 27B is an open-weight dense vision-language model from Qwen.
2. [Qwen3.6 35B A3B](https://rankshark.pro/tools/qwen36-35b-a3b) — SharkScore 65.5. Qwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with 35 billion total parameters and 3 billion active parameters per t
3. [Qwen3.8 Flash](https://rankshark.pro/tools/qwen38-flash) — SharkScore 64.7. Qwen3.8 Flash is a multimodal reasoning model from Alibaba.
4. [Qwen3.6 27B](https://rankshark.pro/tools/qwen36-27b) — SharkScore 64.3. Qwen3.6 27B is a dense 27-billion-parameter language model from the Qwen Team at Alibaba, released in April 2026.
5. [gpt-oss](https://rankshark.pro/tools/gpt-oss) — SharkScore 63.5. OpenAI's open-weight reasoning models.

---
Source: https://rankshark.pro/tools/qwen-25-coder-32b-instruct · Method v2026-11-18.2: https://rankshark.pro/how-ranking-works · Payment never changes a rank.
