Qwen3.6 28B REAP is an open-source language model by 0xSero. Features: 28.2b LLM, VRAM: 56.5GB, Context: 256K, License: apache-2.0, MoE, LLM Explorer Score: 0.39.
Arxiv:2510.13999 Base model:finetune:qwen/qwen3... Base model:qwen/qwen3.6-35b-a3... Conversational Endpoints compatible Expert-pruning Mixture-of-experts Moe Pruned Qwen3.6 Qwen3 5 moe Qwen3 5 moe text Reap Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/0xSero/Qwen3.6-28B-REAP
Qwen3.6 28B REAP Benchmarks
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
What is the LLM Explorer Rank (Score)
Qwen3.6 28B REAP Parameters and Internals
| LLM Name | Qwen3.6 28B REAP |
| Repository 🤗 | https://huggingface.co/0xSero/Qwen3.6-28B-REAP |
| Base Model(s) | |
| Model Size | 28.2b |
| Required VRAM | 56.5 GB |
| Updated | 2026-04-19 |
| Maintainer | 0xSero |
| Model Type | qwen3_5_moe_text |
| Model Files | |
| Model Architecture | Qwen3_5MoeForCausalLM |
| License | apache-2.0 |
| Context Length | 262144 |
| Model Max Length | 262144 |
| Transformers Version | 5.5.4 |
| Tokenizer Class | TokenizersBackend |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 248320 |
| Errors | replace |
Rank the Qwen3.6 28B REAP 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? 53026 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