qwen3.5 is an open-weight model from Priva Studio. It has 262,144-token context. Its published files total 3.4 GB.
Parameters—
Context262,144
Weights3.4 GB
License—
AccessOpen weights
Monthly Downloads—
Model Card
The publisher has not written a card for this model.
Configuration
- Architecture
- Qwen3_5ForConditionalGeneration
- Context length (tokens)
- 262,144
- Layers
- 32
- Hidden size
- 2,560
- Feed-forward size
- 9,216
- Attention heads
- 16
- Key/value heads
- 4
- Head dimension
- 256
- Vocabulary size
- 248,320
- Model type
- qwen3_5
Identity and Version
- Repository
- privastudio/qwen3.5
- Publisher
- Priva Studio
- Task
- Not stated by the source
- Modality
- Other
- Library
- Not stated by the source
- Parameters
- Not stated by the source
- Languages
- Not stated by the source
- Revision
- 4177d9fc5c413f6b621f73f6cc41f20ca573c792
- First published
- 2026-10-02
- Last updated
- 2026-10-02
Files and Weights
10 files, 3.4 GB in total. The weights are 2 files totalling 3.4 GB in gguf.
Weights2 files · 3.4 GB
Configuration3 files · 3.9 KB
Tokenizer3 files · 19.5 MB
Documentation1 file · 11.5 KB
Repository1 file · 1.7 KB
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| Qwen3.5-4B-Q4_K_M.gguf | Weights | 2.7 GB | 00fe7986ff5f |
| mmproj-BF16.gguf | Weights | 675.6 MB | 302b92d56508 |
| config.json | Configuration | 3.2 KB | — |
| preprocessor_config.json | Configuration | 390 B | — |
| video_preprocessor_config.json | Configuration | 385 B | — |
| LICENSE | Documentation | 11.5 KB | — |
| .gitattributes | Repository | 1.7 KB | — |
| tokenizer.json | Tokenizer | 12.8 MB | 5f9e4d4901a9 |
| tokenizer_config.json | Tokenizer | 16.6 KB | — |
| vocab.json | Tokenizer | 6.7 MB | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 3.4 GB
Download from Priva Studio
Released by Priva Studio through its official repository on Hugging Face.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 3.4 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About qwen3.5
What is qwen3.5's context length?
262,144 tokens, from the maximum position embeddings in its published configuration.