All models
Alibaba (Qwen)
Qwen2.5 72B Instruct fastruns locally
alibaba/qwen-2-5-72b
Qwen2.5 72B is the latest series of Qwen large language models. Qwen2.5 brings the following improvements upon Qwen2: - Significantly more knowledge and has greatly improved capabilities in coding and...
Input / 1M
$0.36
USD per million tokens
Output / 1M
$0.40
USD per million tokens
Est. cost / token
$0.00000037
$0.37 per 1M, 3:1 mix
Context window
33K
max output 16K
Major features
Open weightsJSON schemaTools
Task suitability (heuristic 1–5, not a benchmark)
- coding3
- reasoning2
- math2
- summarization4
- extraction4
- classification4
- chat3
- creative3
- translation4
- vision1
- long context2
- agentic3
Run it locally
Will it run on my machine? →ollama run qwen2.5:72b| Quantization | Quality | Memory needed (8K ctx) |
|---|---|---|
| Q2_K | poor | 35.3 GB |
| Q3_K_M | fair | 40.6 GB |
| Q4_K_Mrecommended | good | 50 GB |
| Q5_K_M | very good | 57.6 GB |
| Q6_K | excellent | 65.9 GB |
| Q8_0 | near-lossless | 84.4 GB |
| F16 | lossless | 156 GB |
Estimates.
Price history
| Recorded | Input | Output | Cached | Source |
|---|---|---|---|---|
| 2026-11-05 03:20 | $0.36 | $0.40 | — | openrouter |
A row is added whenever a sync detects a price change. Vendor pricing source
Pricing (USD per 1M tokens)
- Input
- $0.36
- Output
- $0.40
- Blended (3:1)
- $0.37
Details
- Company
- Alibaba (Qwen)
- Version
- 2.5
- Family
- Qwen
- Released
- 2024-09-19
- Parameters
- 72.7B
- Max output
- 16K
- Open weights
- Yes
- Inputs
- text
- Last synced
- 25 min ago