LLM EXPLORER 59,598 MODELS INDEXED

Ecu Pilot Fp16 by mach-kernel

By mach-kernel · 6 downloads
HF Repo ↗ Copy URL

Ecu Pilot Fp16 is an open-source language model by mach-kernel. Features: 35b LLM, VRAM: 72.3GB, License: apache-2.0, Quantized, LLM Explorer Score: 0.23.

  Arxiv:2510.00186 Base model:adapter:qwen/qwen3.... Base model:qwen/qwen3.5-35b-a3...   Dbt   Finetuned   Fp16   Lora   Mcp   Quantized   Qwen3 5 moe   Region:us   Safetensors   Sharded   Tensorflow   Tool-calling
Model Card on HF 🤗: https://huggingface.co/mach-kernel/ecu-pilot-fp16 

Ecu Pilot Fp16 Parameters and Internals

LLM NameEcu Pilot Fp16
Repository 🤗https://huggingface.co/mach-kernel/ecu-pilot-fp16 
Model Nameunsloth/Qwen3.5-35B-A3B-Base
Base Model(s)  Qwen/Qwen3.5-35B-A3B-Base   Qwen/Qwen3.5-35B-A3B-Base
Model Size35b
Required VRAM72.3 GB
Updated2026-05-21
Maintainermach-kernel
Model Typeqwen3_5_moe
Model Files  5.4 GB: 1-of-14   5.4 GB: 2-of-14   5.4 GB: 3-of-14   5.4 GB: 4-of-14   5.4 GB: 5-of-14   5.4 GB: 6-of-14   5.4 GB: 7-of-14   5.4 GB: 8-of-14   5.3 GB: 9-of-14   5.4 GB: 10-of-14   5.4 GB: 11-of-14   5.4 GB: 12-of-14   5.4 GB: 13-of-14   2.2 GB: 14-of-14
Quantization Typefp16
Model ArchitectureQwen3_5MoeForConditionalGeneration
Licenseapache-2.0
Model Max Length262144
Tokenizer ClassTokenizersBackend
Padding Token<|vision_pad|>
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to Ecu Pilot Fp16

Best Alternatives
Context / RAM
Downloads
Likes
Qwen3.6 35B A3B MLX 4bit0K / 20.5 GB5131936
Qwen3.6 35B A3B MLX 6bit0K / 28.9 GB4785922
Qwen3.6 35B A3B MLX 8bit0K / 37.8 GB4735371
Qwen3.6 35B A3B UD MLX 4bit0K / 21.6 GB15720112
Qwen3.6 35B A3B MLX 8bit0K / 37.8 GB386241
Nail Qwen3.6 35B A3B MLX 5bit0K / 27.5 GB831
Qwen3.6 35B A3B 6bit0K / 28.9 GB27428
Qwen3.6 35B A3B UD MLX 3bit0K / 17.3 GB229213
Qwen3.6 35B A3B 5bit0K / 24.7 GB16285
Ornith 1.5 35B A3B MLX 4bit0K / 19.5 GB582922
Note: green Score (e.g. "73.2") means that the model is better than mach-kernel/ecu-pilot-fp16.