LLM EXPLORER 67,078 MODELS INDEXED

TranNhiem DeepCompression Qwen3.6 35B A3B by trannhiem

By trannhiem · 122 downloads
HF Repo ↗ Copy URL

TranNhiem DeepCompression Qwen3.6 35B A3B is an open-source language model by trannhiem. Features: 35b LLM, VRAM: 22.8GB, License: apache-2.0, LLM Explorer Score: 0.33.

  8-bit Base model:quantized:qwen/qwen... Base model:qwen/qwen3.6-35b-a3...   Compressed   Conversational   Endpoints compatible   Expert-pruning   Image-text-to-text   Mixture-of-experts   Modelopt   Nvfp4   Qwen3.6   Qwen3 5 moe   Region:us   Safetensors   Sharded   Tensorflow   Vision   Vision-language   Vllm
Model Card on HF 🤗: https://huggingface.co/trannhiem/TranNhiem-DeepCompression-Qwen3.6-35B-A3B 

TranNhiem DeepCompression Qwen3.6 35B A3B Parameters and Internals

LLM NameTranNhiem DeepCompression Qwen3.6 35B A3B
Repository 🤗https://huggingface.co/trannhiem/TranNhiem-DeepCompression-Qwen3.6-35B-A3B 
Base Model(s)  Qwen/Qwen3.6-35B-A3B   Qwen/Qwen3.6-35B-A3B
Model Size35b
Required VRAM22.8 GB
Updated2026-11-10
Maintainertrannhiem
Model Typeqwen3_5_moe
Model Files  10.0 GB: 1-of-3   10.0 GB: 2-of-3   2.8 GB: 3-of-3
Model ArchitectureQwen3_5MoeForConditionalGeneration
Licenseapache-2.0
Model Max Length262144
Transformers Version5.9.0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to TranNhiem DeepCompression Qwen3.6 35B A3B

Best Alternatives
Context / RAM
Downloads
Likes
....5 35B A3B Sceptic V3 1M W4A161024K / 26.1 GB2230
...AgentWorld 35B A3B Abliterated256K / 69.2 GB96218
Ornith 1.5 35B A3B NPU2256K /  GB580
Qwen3.6 35B A3B NPU2256K /  GB820
Qwen3.6 35B A3B0K / 72.2 GB55408552648
Qwen3.5 35B A3B0K / 72.3 GB21585111482
JEV 35B0K / 72.3 GB713162403
Qwen3.6 35B A3B NVFP40K / 23.4 GB8788684482
Ornith 1.0 35B0K / 70.4 GB1476171519
Qwen3.6 35B A3B FP80K / 0.8 GB8984811343
Note: green Score (e.g. "73.2") means that the model is better than trannhiem/TranNhiem-DeepCompression-Qwen3.6-35B-A3B.