1
A 30B Qwen model walks into a Raspberry Pi and runs in real time
ByteShape's device-optimized release showing superior TPS-quality tradeoffs across edge and datacenter hardware.
ByteShape Blog
Quantized LLMs, VLMs, and image models for real hardware, with public builds and published measurements.
- Popular posts
- 2
- Total points
- 467
- HN comments
- 174
- Rank
- #2,891 company
Visit byteshape.com → On Hacker News Jan 2026 – Sep 2026
2
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.