LLM EXPLORER 63,069 MODELS INDEXED

Qwen3.8 35B A3B Distill MLX APEX MiniPlus Abliterated by IsValorum

By IsValorum · 1176 downloads

Qwen3.8 35B A3B Distill MLX APEX MiniPlus Abliterated is an open-source language model by IsValorum. Features: 35b LLM, VRAM: 20GB, License: apache-2.0, LLM Explorer Score: 0.34.

  4-bit   Abliterated   Apex Base model:empero-ai/qwen3.8-3... Base model:quantized:empero-ai...   Conversational   Miniplus   Mlx   Moe   Quantized   Qwen3.8   Qwen3 5 moe   Region:us   Safetensors   Sharded   Tensorflow   Uncensored

Qwen3.8 35B A3B Distill MLX APEX MiniPlus Abliterated Parameters and Internals

LLM NameQwen3.8 35B A3B Distill MLX APEX MiniPlus Abliterated
Repository πŸ€—https://huggingface.co/IsValorum/Qwen3.8-35B-A3B-Distill-MLX-APEX-MiniPlus-Abliterated 
Base Model(s)  empero-ai/Qwen3.8-35B-A3B-Distill   empero-ai/Qwen3.8-35B-A3B-Distill
Model Size35b
Required VRAM20 GB
Updated2026-10-05
MaintainerIsValorum
Model Typeqwen3_5_moe
Model Files  5.3 GB: 1-of-4   5.3 GB: 2-of-4   5.3 GB: 3-of-4   4.1 GB: 4-of-4
Model ArchitectureQwen3_5MoeForConditionalGeneration
Licenseapache-2.0
Model Max Length262144
Transformers Version5.18.0
Tokenizer ClassQwen3_5Tokenizer
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to Qwen3.8 35B A3B Distill MLX APEX MiniPlus Abliterated

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 /  GB971
Qwen3.6 35B A3B NPU2256K /  GB1080
Qwen3.6 35B A3B0K / 72.2 GB55408552648
Qwen3.5 35B A3B0K / 72.3 GB21585111482
Qwen3.6 35B A3B NVFP40K / 23.4 GB8788684482
Ornith 1.0 35B0K / 70.4 GB1465715506
Qwen3.6 35B A3B FP80K / 0.8 GB8984811343
Qwen AgentWorld 35B A3B0K / 69.2 GB66155665
Note: green Score (e.g. "73.2") means that the model is better than IsValorum/Qwen3.8-35B-A3B-Distill-MLX-APEX-MiniPlus-Abliterated.