HuggingFaceBio/Carbon-X-Base
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.
Carbon-X-Base is a 14.8B-parameter decoder-only language model trained jointly on DNA sequences and natural-language text. Dense, 15B params. Context: 40K tokens (config). License: apache-2.0.
- Org
- HuggingFaceBio
- Released
- 2026-10-26
- Status
- just landed · new, unvetted
- License
- apache-2.0 (permissive)
- Parameters
- 14.8B
- Architecture
- dense · Qwen3ForCausalLM
- Context
- 40,960 tokens
- Task
- text-generation · text
- Signal
- 10 HF likes · 64 downloads
Runs on
mixed: real files + estimate; need = weights + FP16 KV cache for 8K tokens + 1GB. A sizing calculation, not tested.
- Q4 ~11.2 GB (estimated size): 16GB GPU (5060 Ti / 4060 Ti / 4080 / 5080), 16GB GPU (7800 XT / 9070 XT), Mac 16GB
- Q8 ~18.0 GB (estimated size): 24GB GPU (3090 / 4090), 32GB GPU (5090), 24GB GPU (7900 XTX), Arc B60 24GB, Arc B70 32GB, Mac 24GB, Mac 36GB, CPU only, 32GB RAM (slow)
- FP16 ~31.9 GB: 48GB GPU (RTX 6000 Ada / A6000), 96GB GPU (RTX Pro 6000 Blackwell), 1× DGX Spark (128GB), 2× DGX Spark (256GB), Strix Halo 128GB unified (~96GB usable), Mac 48GB, Mac 64GB (M1 Max), Mac 96GB, Mac 128GB, Mac 192GB, Mac 256GB, Mac 512GB, CPU only, 64GB RAM (slow), CPU only, 128GB RAM (slow), CPU only, 256GB RAM (slow)
Links
First published here 2026-10-26 · updated 2026-11-02 · markdown · JSON