LLM EXPLORER 68,069 MODELS INDEXED

Qwen3.8 27B Pi Adapted MLX 8bit by netprojects

By netprojects · 236 downloads

Qwen3.8 27B Pi Adapted MLX 8bit is an open-source language model by netprojects. Features: 27b LLM, VRAM: 29.4GB, License: apache-2.0, Quantized, LLM Explorer Score: 0.33.

  8-bit   8bit   Agents   Apple-silicon Base model:harness-hub/qwen3.8... Base model:quantized:harness-h...   Coding-agent   Conversational   Image-text-to-text   Lora   Mlx   Pi   Quantized   Qwen3 5   Region:us   Safetensors   Sharded   Tensorflow

Qwen3.8 27B Pi Adapted MLX 8bit Parameters and Internals

LLM NameQwen3.8 27B Pi Adapted MLX 8bit
Repository πŸ€—https://huggingface.co/netprojects/Qwen3.8-27B-pi-adapted-MLX-8bit 
Base Model(s)  harness-hub/Qwen3.8-27B-pi-adapted   harness-hub/Qwen3.8-27B-pi-adapted
Model Size27b
Required VRAM29.4 GB
Updated2026-11-20
Maintainernetprojects
Model Typeqwen3_5
Model Files  5.3 GB: 1-of-6   5.3 GB: 2-of-6   5.3 GB: 3-of-6   5.3 GB: 4-of-6   5.3 GB: 5-of-6   2.9 GB: 6-of-6   0.5 GB
Quantization Type8bit
Model ArchitectureQwen3_5ForConditionalGeneration
Licenseapache-2.0
Model Max Length262144
Transformers Version5.8.0.dev0
Tokenizer ClassQwen3_5Tokenizer
Padding Token<|endoftext|>
LoRA ModelYes
Errorsreplace

Best Alternatives to Qwen3.8 27B Pi Adapted MLX 8bit

Best Alternatives
Context / RAM
Downloads
Likes
Qwen3.6 27B OptiQ 4bit256K / 18.7 GB1306559
Qwopus3.8 27B Coder Flash 8bit0K / 29.4 GB4453
Qwopus3.8 27B Coder Flash 4bit0K / 16 GB3742
Qwopus3.8 27B Coder Flash 6bit0K / 22.7 GB3322
Qwen3.8 27B MLX 5bit0K / 19.5 GB46750442
Bonsai 27B Mlx 1bit0K / 5.1 GB809309205
Ternary Bonsai 27B Mlx 2bit0K / 8.5 GB809024168
Qwen3.6 27B MLX 8bit0K / 29.4 GB87914514
Qwen3.6 27B MLX 6bit0K / 22.7 GB8129772
Qwen3.6 27B MLX 4bit0K / 16 GB84686116
Note: green Score (e.g. "73.2") means that the model is better than netprojects/Qwen3.8-27B-pi-adapted-MLX-8bit.