ReadyArt/Minimax-M3-jablit
archived · low-signalmodel
Image text to text model from ReadyArt (HF pipeline tag; the card has no one-line description). Mixture-of-experts, 427B total (128 experts, 4 per token). Context: 1M tokens (config). License: minimax-community.
- Org
- ReadyArt
- Released
- 2026-11-09
- Status
- archived · low-signal
- License
- minimax-community (restricted)
- Parameters
- 427.0B
- Architecture
- MoE · 128 experts, 4/token · MiniMaxM3SparseForConditionalGeneration
- Context
- 1,048,576 tokens (config.json)
- Task
- image-text-to-text · vision
- Signal
- 3 HF likes · 113 downloads
- Archived
- 2026-11-12 (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 ~271.7 GB: Mac 512GB
- Q8 ~455.6 GB: no listed device
- FP16 ~856.2 GB: no listed device
Links
First published here 2026-11-09 · updated 2026-11-12 · markdown · JSON