LLM EXPLORER 62,696 MODELS INDEXED

K2 Horizon MoVA 36B A4B 8bit by mlx-community

By mlx-community · 126 downloads
HF Repo ↗ Copy URL

K2 Horizon MoVA 36B A4B 8bit is an open-source language model by mlx-community. Features: 36b LLM, VRAM: 39.8GB, Context: 512K, License: apache-2.0, Quantized, LLM Explorer Score: 0.3.

  8-bit   8bit Base model:ifm/k2-horizon-mova... Base model:quantized:ifm/k2-ho...   Conversational   K2-horizon   K2 horizon   Mlx   Moe   Mova   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/mlx-community/K2-Horizon-MoVA-36B-A4B-8bit 

K2 Horizon MoVA 36B A4B 8bit Parameters and Internals

LLM NameK2 Horizon MoVA 36B A4B 8bit
Repository 🤗https://huggingface.co/mlx-community/K2-Horizon-MoVA-36B-A4B-8bit 
Base Model(s)  K2 Horizon MoVA 36B A4B   IFM/K2-Horizon-MoVA-36B-A4B
Model Size36b
Required VRAM39.8 GB
Updated2026-10-01
Maintainermlx-community
Model Typek2_horizon
Model Files  5.2 GB: 1-of-8   5.3 GB: 2-of-8   5.3 GB: 3-of-8   5.3 GB: 4-of-8   5.3 GB: 5-of-8   5.3 GB: 6-of-8   5.3 GB: 7-of-8   2.8 GB: 8-of-8
Quantization Type8bit
Model ArchitectureK2HorizonForCausalLM
Licenseapache-2.0
Context Length524288
Model Max Length524288
Transformers Version5.13.0
Tokenizer ClassTokenizersBackend
Vocabulary Size250624

Best Alternatives to K2 Horizon MoVA 36B A4B 8bit

Best Alternatives
Context / RAM
Downloads
Likes
K2 Horizon MoVA 36B A4B 4bit512K / 26.5 GB3153
... Horizon MoVA 36B A4B MLX 4bit512K / 15.6 GB6923
K2 Horizon MoVA 36B A4B512K / 63 GB433139
...zon MoVA 36B A4B DERISKED BF16512K / 64.6 GB4193
K2 Horizon MoVA 36B A4B OQ4e512K / 22 GB10982
...on MoVA 36B A4B DERISKED NVFP4512K / 33.8 GB2071
...2 Horizon MoVA 36B A4B Heretic512K / 74.9 GB2101
K2 Horizon MoVA 36B A4B FP8512K / 40.6 GB1296
...n MoVA 36B A4B Mixed NVFP4 FP8512K / 44.5 GB811
...Horizon MoVA 36B A4B GPTQ Int4512K / 21.8 GB301
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/K2-Horizon-MoVA-36B-A4B-8bit.