logic65/Whittle-Qwen-3.8-45B-A3B
just landed · new, unvettedmodel
New, unvetted: created or first seen in the last few days, not from a trusted org and not past the signal threshold yet.
Text generation model from logic65 (HF pipeline tag; the card has no one-line description). Mixture-of-experts, 45B total, 3B active (256 experts, 8 per token). Context: 256K tokens (config). License: apache-2.0.
- Org
- logic65
- Released
- 2026-10-05
- Status
- just landed · new, unvetted
- License
- apache-2.0 (permissive)
- Parameters
- 45.1B total, 3.0B active
- Architecture
- MoE · 256 experts, 8/token · Qwen4ExpForCausalLM
- Context
- 262,144 tokens
- Task
- text-generation · text
- Signal
- 6 HF likes · 539 downloads
Runs on
mixed: real files + estimate; need = weights + FP16 KV cache for 8K tokens + 1GB. A sizing calculation, not tested.
- Q4 ~28.8 GB: 32GB GPU (5090), 48GB GPU (RTX 6000 Ada / A6000), Mac 48GB, Mac 64GB (M1 Max)
- Q8 ~49.7 GB: Mac 96GB, CPU only, 64GB RAM (slow)
- FP16 ~92.0 GB (estimated size): 96GB GPU (RTX Pro 6000 Blackwell), 1× DGX Spark (128GB), 2× DGX Spark (256GB), Strix Halo 128GB unified (~96GB usable), Mac 128GB, Mac 192GB, Mac 256GB, Mac 512GB, CPU only, 128GB RAM (slow), CPU only, 256GB RAM (slow)
Links
First published here 2026-10-05 · updated 2026-10-28 · markdown · JSON