ByteShape Blog company blog
Shapelearn Qwen 3.8 27B (13.1 GB VRAM)
ByteShape's full ShapeLearn release of Qwen 3.8 27B: five GGUF models on the quality-speed frontier across six GPUs. GPU-5 is the default wherever it fits, at 99.63% of BF16. GPU-4 stays very competitive in a much smaller file.
- Points
- 104
- HN comments
- 39
- Submissions
- 1
- Cited by
- 0 commenters
AI & Machine LearningHardware & Electronics2026
On Hacker News
| Submitted | Title on HN | Points | Comments |
|---|---|---|---|
| Sep 18, 2026 | Shapelearn Qwen 3.8 27B (13.1 GB VRAM) by syntaxing | 104 | 39 |
