ZelligeAI/Tessera-27B-B-CJK-RL

archived · low-signalmodel

Tessera-27B-B-CJK-RL is a coding-agent model built on Qwen3.8-27B. Dense, 28B params. Context: 256K tokens (config). License: apache-2.0.

Org: ZelligeAI
Released: 2026-11-04
Status: archived · low-signal
License: apache-2.0 (permissive)
Parameters: 27.8B
Architecture: dense · Qwen3_5ForConditionalGeneration
Context: 262,144 tokens (config.json)
Task: image-text-to-text · vision
Signal: 3 HF likes · 35 downloads
Archived: 2026-11-10 (no longer listed by the collector; stats as last seen)

Runs on

mixed: real files + estimate; need = weights + FP16 KV cache for 8K tokens + 1GB. A sizing calculation, not tested.

Q4 ~20.7 GB: 24GB GPU (3090 / 4090), 32GB GPU (5090), 24GB GPU (7900 XTX), Mac 36GB, CPU only, 32GB RAM (slow)
Q8 ~32.6 GB (estimated size): 48GB GPU (RTX 6000 Ada / A6000), Mac 48GB, Mac 64GB (M1 Max), CPU only, 64GB RAM (slow)
FP16 ~57.8 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)