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.
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
Model Card on HF 🤗: https://huggingface.co/Flagstone8878/Qwen3.5-18B-REAP-A3B-Coding
Qwen3.5 18B REAP A3B Coding Parameters and Internals
| LLM Name | Qwen3.5 18B REAP A3B Coding |
| Repository 🤗 | https://huggingface.co/Flagstone8878/Qwen3.5-18B-REAP-A3B-Coding |
| Base Model(s) | |
| Model Size | 18.5b |
| Required VRAM | 37.3 GB |
| Updated | 2026-04-01 |
| Maintainer | Flagstone8878 |
| Model Type | qwen3_5_moe_text |
| Model Files | |
| Model Architecture | Qwen3_5MoeForConditionalGeneration |
| License | apache-2.0 |
| Context Length | 262144 |
| Model Max Length | 262144 |
| Transformers Version | 5.2.0 |
| Tokenizer Class | TokenizersBackend |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 248320 |
| Errors | replace |
Rank the Qwen3.5 18B REAP A3B Coding Capabilities
🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟
What open-source LLMs or SLMs are you in search of? 52394 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a