Stream Qwen3.5 27B is an open-source language model by JonasGeiping. Features: 27b LLM, VRAM: 53.6GB, Context: 256K, License: apache-2.0.
Base model:finetune:qwen/qwen3... Base model:qwen/qwen3.5-27b Custom code Dataset:jonasgeiping/stream-da... Deltanet En Monitorability Multi-stream Parallel-cognition Qwen3.5 Qwen3 5 text Region:us Safetensors Sharded Stream-llm Tensorflow
Model Card on HF 🤗: https://huggingface.co/JonasGeiping/stream-qwen3.5-27b
Stream Qwen3.5 27B Parameters and Internals
| LLM Name | Stream Qwen3.5 27B |
| Repository 🤗 | https://huggingface.co/JonasGeiping/stream-qwen3.5-27b |
| Base Model(s) | |
| Model Size | 27b |
| Required VRAM | 53.6 GB |
| Updated | 2026-05-14 |
| Maintainer | JonasGeiping |
| Model Type | qwen3_5_text |
| Model Files | |
| Supported Languages | en |
| Model Architecture | StreamQwen3_5ForCausalLM |
| License | apache-2.0 |
| Context Length | 262144 |
| Model Max Length | 262144 |
| Transformers Version | 5.3.0 |
| Tokenizer Class | TokenizersBackend |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 248320 |
| Torch Data Type | bfloat16 |
| Errors | replace |
Rank the Stream Qwen3.5 27B 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? 53666 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