LLM EXPLORER 60,645 MODELS INDEXED

K2 Horizon MoVA 36B A4B GPTQ Int4 by Siladrim

By Siladrim · 30 downloads
HF Repo ↗ Copy URL

K2 Horizon MoVA 36B A4B GPTQ Int4 is an open-source language model by Siladrim. Features: 36b LLM, VRAM: 21.8GB, Context: 512K, License: apache-2.0, Quantized, LLM Explorer Score: 0.29.

  4-bit Base model:ifm/k2-horizon-mova... Base model:quantized:ifm/k2-ho...   Conversational   Custom code   En   Gptq   Gptqmodel   Int4   K2-horizon   K2 horizon   Moe   Mova   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Siladrim/K2-Horizon-MoVA-36B-A4B-GPTQ-Int4 

K2 Horizon MoVA 36B A4B GPTQ Int4 Parameters and Internals

LLM NameK2 Horizon MoVA 36B A4B GPTQ Int4
Repository 🤗https://huggingface.co/Siladrim/K2-Horizon-MoVA-36B-A4B-GPTQ-Int4 
Base Model(s)  K2 Horizon MoVA 36B A4B   IFM/K2-Horizon-MoVA-36B-A4B
Model Size36b
Required VRAM21.8 GB
Updated2026-09-07
MaintainerSiladrim
Model Typek2_horizon
Model Files  4.3 GB: 1-of-6   4.3 GB: 2-of-6   4.3 GB: 3-of-6   4.3 GB: 4-of-6   4.3 GB: 5-of-6   0.3 GB: 6-of-6
Supported Languagesen
GPTQ QuantizationYes
Quantization Typegptq
Model ArchitectureK2HorizonForCausalLM
Licenseapache-2.0
Context Length524288
Model Max Length524288
Transformers Version5.16.1
Tokenizer ClassTokenizersBackend
Padding Token<|ifm|endoftext|>
Vocabulary Size250624

Best Alternatives to K2 Horizon MoVA 36B A4B GPTQ Int4

Best Alternatives
Context / RAM
Downloads
Likes
K2 Horizon MoVA 36B A4B512K / 63 GB433139
K2 Horizon MoVA 36B A4B FP8512K / 40.6 GB1296
Note: green Score (e.g. "73.2") means that the model is better than Siladrim/K2-Horizon-MoVA-36B-A4B-GPTQ-Int4.