higa2515/Qwen3.8-27B-QSA-BF16
archived · low-signalmodel
Image text to text model from higa2515 (HF pipeline tag; the card has no one-line description). Dense, 28B params. Context: 256K tokens (config). License: apache-2.0.
- Org
- higa2515
- Released
- 2026-11-04
- Status
- archived · low-signal
- License
- apache-2.0 (permissive)
- Parameters
- 27.8B
- Architecture
- dense · QSAQwen3_5ForConditionalGeneration
- Context
- 262,144 tokens (config.json)
- Task
- image-text-to-text · vision
- Signal
- 9 HF likes · 193 downloads
- Archived
- 2026-11-07 (no longer listed by the collector; stats as last seen)
Runs on
real quant files; need = weights + FP16 KV cache for 8K tokens + 1GB. A sizing calculation, not tested.
- Q4 ~19.8 GB: 24GB GPU (3090 / 4090), 32GB GPU (5090), 24GB GPU (7900 XTX), Mac 36GB, CPU only, 32GB RAM (slow)
- Q8 ~32.4 GB: 48GB GPU (RTX 6000 Ada / A6000), Mac 48GB, Mac 64GB (M1 Max), CPU only, 64GB RAM (slow)
- FP16 ~58.9 GB: 96GB GPU (RTX Pro 6000 Blackwell), 1× DGX Spark (128GB), 2× DGX Spark (256GB), Strix Halo 128GB unified (~96GB usable), Mac 96GB, Mac 128GB, Mac 192GB, Mac 256GB, Mac 512GB, CPU only, 128GB RAM (slow), CPU only, 256GB RAM (slow)
Links
First published here 2026-11-04 · updated 2026-11-07 · markdown · JSON