Model index / Other / Ternary-Bonsai-2-27B-Uncensored-Heretic-v2
Other / MODEL PROFILE
Ternary-Bonsai-2-27B-Uncensored-Heretic-v2
OS-Software · Published release · Heretic · GGUF / MLX
Model source
Published by OS-Software on Hugging Face. This index organizes public repository metadata for discovery and comparison. Refer to the publisher and independent testing for actual model behavior.
Declared base model
prism-ml/Ternary-Bonsai-2-27B-gguf ↗
Hardware and context
Estimated at 16.5 GB VRAM for 27B parameters with 4-bit weights, including 15% weight overhead and 1 GB of baseline headroom. KV cache, context length, multimodal components and concurrency increase actual memory usage.The parameter count was parsed from the model name and has not been independently verified.
Context length: Not stated in public metadata. Please consult the model card.
Download sources and quantized variants
5 repositories| HUGGING FACE REPOSITORY | Format | 30-day downloads | Declared license |
|---|---|---|---|
| OS-Software/Ternary-Bonsai-2-27B-Uncensored-Heretic-v2-GGUF ↗ | GGUF | 51.7K | apache-2.0 |
| 3hs4n/Ternary-Bonsai-2-27B-Uncensored-Heretic-v2-mlx-2bit-compact ↗ | MLX | 2.6K | apache-2.0 |
| 3hs4n/Ternary-Bonsai-2-27B-Uncensored-Heretic-v2-mlx-2bit ↗ | GGUF | 1.9K | apache-2.0 |
| 3hs4n/Ternary-Bonsai-2-27B-Uncensored-Heretic-v2-mlx-2bit-DFlash2 ↗ | MLX | 1.7K | apache-2.0 |
| 3hs4n/Ternary-Bonsai-2-27B-Uncensored-Heretic-v2-mlx-2bit-compact-DFlash2 ↗ | MLX | 1.4K | apache-2.0 |
Uncensored is a publisher description, not a guarantee of zero refusals, capability, accuracy or safety. This index does not measure refusal rates or performance benchmarks.
More from this family
More Other →Other4B ↗
Spark-x2.5-4B-Heretic-jp
soyaakinohara
↓ 296.8K ♡ 18~3.3 GB ↗
Other27B ↗
Ternary-Bonsai-2-27B-Uncensored-Heretic
OS-Software
↓ 203.9K ♡ 183~16.5 GB ↗
Other24B ↗
LFM2.5-24B-A2B-Uncensored
AtomicChat
↓ 150.5K ♡ 69~14.8 GB ↗
OtherSize not stated ↗
LTX-2.3-uncensored-v1.4
ChrisColeTech
↓ 110K ♡ 310VRAM unknown ↗