autotrust/JEV-35B
archivedmodel
JEV-35B is a decision model only: it does not chat or generate text. Mixture-of-experts, 36B total, 3B active (256 experts, 8 per token). Context: 256K tokens (config). License: apache-2.0.
- Org
- autotrust
- Released
- 2026-10-11
- Status
- archived
- License
- apache-2.0 (permissive)
- Parameters
- 36.0B total, 3.0B active
- Architecture
- MoE · 256 experts, 8/token · Qwen3_5MoeForConditionalGeneration
- Context
- 262,144 tokens
- Task
- text-classification · text
- Signal
- 2819 HF likes · 454857 downloads
- Archived
- 2026-10-19 (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 ~23.4 GB: 32GB GPU (5090), Mac 36GB, Mac 48GB, CPU only, 32GB RAM (slow)
- Q8 ~40.1 GB: 48GB GPU (RTX 6000 Ada / A6000), Mac 64GB (M1 Max), Mac 96GB, CPU only, 64GB RAM (slow)
- FP16 ~73.6 GB: 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 2026-10-11 · updated 2026-10-19 · markdown · JSON