LLM EXPLORER 64,561 MODELS INDEXED

MarChat V1 27B by DoHorizon

By DoHorizon · 58 downloads
HF Repo ↗ Copy URL

MarChat V1 27B is an open-source language model by DoHorizon. Features: 27b LLM, VRAM: 54.8GB, License: cc-by-nc-sa-4.0, LLM Explorer Score: 0.25.

Base model:finetune:qwen/qwen3...   Base model:qwen/qwen3.5-27b   Conversational   Doi:10.57967/hf/10027   Endpoints compatible   Image-text-to-text   Lora   Pytorch   Qwen3 5   Region:us   Roleplay   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/DoHorizon/MarChat-V1-27B 

MarChat V1 27B Parameters and Internals

LLM NameMarChat V1 27B
Repository 🤗https://huggingface.co/DoHorizon/MarChat-V1-27B 
Base Model(s)  Qwen/Qwen3.5-27B   Qwen/Qwen3.5-27B
Model Size27b
Required VRAM54.8 GB
Updated2026-09-03
MaintainerDoHorizon
Model Typeqwen3_5
Model Files  2.5 GB: 1-of-15   3.9 GB: 2-of-15   4.0 GB: 3-of-15   4.0 GB: 4-of-15   3.9 GB: 5-of-15   4.0 GB: 6-of-15   4.0 GB: 7-of-15   3.8 GB: 8-of-15   4.0 GB: 9-of-15   4.0 GB: 10-of-15   3.8 GB: 11-of-15   4.0 GB: 12-of-15   4.0 GB: 13-of-15   4.0 GB: 14-of-15   0.9 GB: 15-of-15
Model ArchitectureQwen3_5ForConditionalGeneration
Licensecc-by-nc-sa-4.0
Model Max Length262144
Transformers Version5.6.0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to MarChat V1 27B

Best Alternatives
Context / RAM
Downloads
Likes
...wopus3.8 27B Flash Mlx OQ4e 1M1024K / 16.9 GB2111
Agens Pilot1024K / 54.7 GB953
Qwen3.8 27B NPU2256K /  GB2524
JEV 27B VL0K / 55.6 GB1525286966
Clef0K / 54.7 GB201602194
Qwen3.6 27B0K / 55.4 GB67281382197
Qwen3.8 27B0K / 55.6 GB28753
Qwen3.8 27B0K / 55.6 GB272721
Qwen3.8 27B MLX0K / 16 GB141118
Qwen3.6 27B NVFP40K / 22 GB1887525419
Note: green Score (e.g. "73.2") means that the model is better than DoHorizon/MarChat-V1-27B.