Model index / Other / K2-Horizon-32B-heretic
Other / MODEL PROFILE

K2-Horizon-32B-heretic

soyaakinohara · Published release · Heretic · GGUF / Transformers

Model familyOther
Parameters32B
Estimated Q4 VRAMAbout 19.4 GB
30-day downloads7.3K
Declared licenseapache-2.0
Source repositories4

Model source

Published by soyaakinohara 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

IFM/K2-Horizon-32B ↗

Hardware and context

Estimated at 19.4 GB VRAM for 32B 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

4 repositories
HUGGING FACE REPOSITORYFormat30-day downloadsDeclared license
mradermacher/K2-Horizon-32B-heretic-i1-GGUF ↗GGUF5.8Kapache-2.0
mradermacher/K2-Horizon-32B-heretic-GGUF ↗GGUF1.1Kapache-2.0
soyaakinohara/K2-Horizon-32B-heretic-gguf ↗GGUF267apache-2.0
soyaakinohara/K2-Horizon-32B-heretic ↗Transformers104apache-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 →