amazon/LAR-27B
main boardmodel
Dense, 27B params. Context: 256K tokens (config). License: apache-2.0.
- Org
- amazon
- Released
- 2026-10-14
- Status
- main board
- License
- apache-2.0 (permissive)
- Parameters
- 26.9B
- Architecture
- dense · Qwen3_5ForConditionalGeneration
- Context
- 262,144 tokens
- Signal
- 8 HF likes · 82 downloads
Runs on
real quant files; need = weights + FP16 KV cache for 8K tokens + 1GB. A sizing calculation, not tested.
- Q4 ~19.6 GB: 24GB GPU (3090 / 4090), 32GB GPU (5090), 24GB GPU (7900 XTX), Mac 36GB, CPU only, 32GB RAM (slow)
- Q8 ~31.7 GB: 48GB GPU (RTX 6000 Ada / A6000), Mac 48GB, Mac 64GB (M1 Max), CPU only, 64GB RAM (slow)
- FP16 ~56.9 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 2026-10-14 · updated 2026-10-14 · markdown · JSON