LLM EXPLORER 59,071 MODELS INDEXED

Qwen3.5 18B REAP A3B Coding by Flagstone8878

By Flagstone8878 · 108 downloads

Qwen3.5 18B REAP A3B Coding is an open-source language model by Flagstone8878. Features: 18.5b LLM, VRAM: 37.3GB, Context: 256K, License: apache-2.0, MoE, LLM Explorer Score: 0.23.

  18b Base model:finetune:qwen/qwen3... Base model:qwen/qwen3.5-35b-a3... Dataset:0xsero/glm47-reap-cali...   Moe   Qwen3 5 moe text   Reap   Region:us   Safetensors   Sharded   Tensorflow

Qwen3.5 18B REAP A3B Coding Parameters and Internals

LLM NameQwen3.5 18B REAP A3B Coding
Repository πŸ€—https://huggingface.co/Flagstone8878/Qwen3.5-18B-REAP-A3B-Coding 
Base Model(s)  Qwen/Qwen3.5-35B-A3B   Qwen/Qwen3.5-35B-A3B
Model Size18.5b
Required VRAM37.3 GB
Updated2026-08-08
MaintainerFlagstone8878
Model Typeqwen3_5_moe_text
Model Files  5.4 GB: 1-of-7   5.4 GB: 2-of-7   5.4 GB: 3-of-7   5.4 GB: 4-of-7   5.4 GB: 5-of-7   5.4 GB: 6-of-7   4.9 GB: 7-of-7
Model ArchitectureQwen3_5MoeForConditionalGeneration
Licenseapache-2.0
Context Length262144
Model Max Length262144
Transformers Version5.2.0
Tokenizer ClassTokenizersBackend
Padding Token<|endoftext|>
Vocabulary Size248320
Errorsreplace