LLM EXPLORER 58,608 MODELS INDEXED

Qwen3.8 27B Tq3 Mini G64 by manjunathshiva

By manjunathshiva · 139 downloads
HF Repo ↗ Copy URL

Qwen3.8 27B Tq3 Mini G64 is an open-source language model by manjunathshiva. Features: 27b LLM, VRAM: 12.5GB, License: apache-2.0.

  3-bit Base model:finetune:qwen/qwen3...   Base model:qwen/qwen3.8-27b   Conversational   Gated-deltanet   Image-text-to-text   Mlx   Multimodal   Qwen3 5   Region:us   Safetensors   Sharded   Tensorflow   Turboquant   Vlm
Model Card on HF 🤗: https://huggingface.co/manjunathshiva/Qwen3.8-27B-tq3-mini-g64 

Qwen3.8 27B Tq3 Mini G64 Parameters and Internals

LLM NameQwen3.8 27B Tq3 Mini G64
Repository 🤗https://huggingface.co/manjunathshiva/Qwen3.8-27B-tq3-mini-g64 
Base Model(s)  Qwen/Qwen3.8-27B   Qwen/Qwen3.8-27B
Model Size27b
Required VRAM12.5 GB
Updated2026-08-17
Maintainermanjunathshiva
Model Typeqwen3_5
Model Files  5.4 GB: 1-of-3   5.4 GB: 2-of-3   1.7 GB: 3-of-3
Model ArchitectureQwen3_5ForConditionalGeneration
Licenseapache-2.0
Model Max Length262144
Transformers Version5.8.0.dev0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to Qwen3.8 27B Tq3 Mini G64

Best Alternatives
Context / RAM
Downloads
Likes
Qwen3.8 27B FP80K / 0.4 GB123157416
Qwen3.8 27B0K / 55.6 GB28753
Qwen3.6 27B0K / 55.4 GB67281382197
Qwen3.6 27B NVFP40K / 22 GB1887525419
...n3.8 27B MTPLX Optimized Speed0K / 19.6 GB698950
ThinkingCap Qwen3.6 27B0K / 54.7 GB35947614
Qwen3.6 27B FP80K / 0.4 GB7740472342
Qwen3.5 27B0K / 55.2 GB25362941028
Qwen3.5 27B0K / 55.2 GB811516
Qwen3.8 27B NVFP40K / 22 GB3012214
Note: green Score (e.g. "73.2") means that the model is better than manjunathshiva/Qwen3.8-27B-tq3-mini-g64.