Modelsby GlyphQwen3 14b specs, prices, where it runs and its benchmark standing
open weights · top 10 on 0 of 1 · released Apr 28, 2025
Facts
- Provider
- Alibaba
- Hardware
- Estimate: about 30 GB of weights as published (BF16), about 15 GB at 8-bit, about 7.4 GB at 4-bit, plus memory for the context
- Hugging Face config
- Weights
- Open weights
- Benchmarks
- 1 board captured
| Rank | Board | Score | |||
|---|---|---|---|---|---|
| 33 | Agents and tools | 41.0% | 81 |
Versions and release history
21 versions in this line since Sep 17, 2024, from Pricing, OpenRouter and the boards.
| Version | Released | |
|---|---|---|
| Qwen3.5-35B-A3B | Feb 24, 20268 months ago | Boards |
| Qwen3.5 397B A17B | Feb 13, 20268 months ago | Boards |
| Qwen3 30B A3B | Jul 30, 20251 year ago | Boards |
| Qwen3-235B-A22B-Thinking (Jul 2025) | Jul 25, 20251 year ago | Boards |
| Qwen3 32B | Apr 29, 20251 year ago | Boards |
| Qwen3 14Bthis model | Apr 28, 20251 year ago | Pricing |
| Qwen3 8B | Apr 28, 20251 year ago | Pricing |
| Qwen3 0.6B | Apr 27, 20251 year ago | Hugging Face |
| Qwen3 1.7B | Apr 27, 20251 year ago | Hugging Face |
| Qwen3 4B | Apr 27, 20251 year ago | Hugging Face |
| Qwen2.5 7B Instruct | Oct 16, 20242 years ago | Pricing |
| Qwen2.5 72B | Sep 19, 20242 years ago | Pricing |
Category ranks, more models and catalog changes
Rank in each category
More from Alibaba
Catalog changes, newest first (kept for good)
- context: 131,072 tokens to 40,960 tokensOct 12, 2026 4 weeks ago