Open-weight model
Qwen3.8-Flash-Next-EXL3-SAGE-4.77bpw
by Victor Cruz vcruz305/Qwen3.8-Flash-Next-EXL3-SAGE-4.77bpw
Qwen3.8-Flash-Next-EXL3-SAGE-4.77bpw is an open-weight model from Victor Cruz. It has 262,144-token context. Its published files total 86.5 GB.
Parameters—
Context262,144
Weights86.5 GB
License—
AccessOpen weights
Monthly Downloads—
Model Card
The publisher has not written a card for this model.
Configuration
- Architecture
- Qwen4ExpForConditionalGeneration
- Context length (tokens)
- 262,144
- Layers
- 48
- Hidden size
- 2,560
- Attention heads
- 24
- Key/value heads
- 2
- Head dimension
- 256
- Vocabulary size
- 248,320
- Experts
- 512
- Experts active per token
- 10
- Model type
- qwen4_exp
Identity and Version
- Repository
- vcruz305/Qwen3.8-Flash-Next-EXL3-SAGE-4.77bpw
- Publisher
- Victor Cruz
- 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
- e206edfa2c76381a292d5135695b8a3247b45824
- First published
- 2026-10-18
- Last updated
- 2026-10-18
Files and Weights
48 files, 86.5 GB in total. The weights are 40 files totalling 86.5 GB in safetensors.
Weights40 files · 86.5 GB
Configuration4 files · 5.7 KB
Tokenizer2 files · 12.8 MB
Other1 file · 9.0 KB
Repository1 file · 1.6 KB
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| ngram_embedding.safetensors | Weights | 26.2 GB | 725fad6622d0 |
| qtensors/hc_expand.safetensors | Weights | 10 B | 411a485216e4 |
| qtensors/model.language_model.embed_tokens.safetensors | Weights | 1.3 GB | 0d8f9d97bb42 |
| qtensors/model.language_model.layers.0.safetensors | Weights | 1.9 GB | ce5a1503ab42 |
| qtensors/model.language_model.layers.1.ple.safetensors | Weights | 65.7 MB | 71ebdf4b0ff6 |
| qtensors/model.language_model.layers.1.safetensors | Weights | 2.2 GB | 9468f7461561 |
| qtensors/model.language_model.layers.10.safetensors | Weights | 1.9 GB | 1fb22b83c1ca |
| qtensors/model.language_model.layers.11.safetensors | Weights | 2.0 GB | b11baee35044 |
| qtensors/model.language_model.layers.12.safetensors | Weights | 1.7 GB | 71089489e851 |
| qtensors/model.language_model.layers.13.safetensors | Weights | 1.9 GB | 6c25be2a0de1 |
| qtensors/model.language_model.layers.14.safetensors | Weights | 1.7 GB | 1cb94c8efc05 |
| qtensors/model.language_model.layers.15.safetensors | Weights | 1.5 GB | 06426c8007a0 |
| qtensors/model.language_model.layers.16.safetensors | Weights | 1.7 GB | 74aa75a48454 |
| qtensors/model.language_model.layers.17.safetensors | Weights | 1.7 GB | fdb443859582 |
| qtensors/model.language_model.layers.18.safetensors | Weights | 1.7 GB | 8f021ac9ba22 |
| qtensors/model.language_model.layers.19.safetensors | Weights | 1.7 GB | 0e83200d10a0 |
| qtensors/model.language_model.layers.2.safetensors | Weights | 2.1 GB | d47964593665 |
| qtensors/model.language_model.layers.20.safetensors | Weights | 1.3 GB | 18f546225dbf |
| qtensors/model.language_model.layers.21.safetensors | Weights | 1.3 GB | 81cedd58563d |
| qtensors/model.language_model.layers.22.safetensors | Weights | 1.3 GB | c8c0448232b9 |
| qtensors/model.language_model.layers.23.safetensors | Weights | 1.3 GB | 7979a8ba352e |
| qtensors/model.language_model.layers.24.safetensors | Weights | 1.7 GB | 4c98a6745927 |
| qtensors/model.language_model.layers.25.safetensors | Weights | 1.7 GB | 5ddd858f9d57 |
| qtensors/model.language_model.layers.26.safetensors | Weights | 1.7 GB | 4967ac8994f1 |
| qtensors/model.language_model.layers.27.safetensors | Weights | 1.7 GB | 51e9e8ce7470 |
| qtensors/model.language_model.layers.28.safetensors | Weights | 1.7 GB | a422ba09a24a |
| qtensors/model.language_model.layers.29.safetensors | Weights | 1.3 GB | 5501c2f90874 |
| qtensors/model.language_model.layers.3.safetensors | Weights | 1.7 GB | cebb2538313b |
| qtensors/model.language_model.layers.30.safetensors | Weights | 1.3 GB | 26b9dc478ab1 |
| qtensors/model.language_model.layers.31.safetensors | Weights | 1.3 GB | 03519d67b6d9 |
| qtensors/model.language_model.layers.32.safetensors | Weights | 1.3 GB | 8df0e5d6ec5f |
| qtensors/model.language_model.layers.33.safetensors | Weights | 1.3 GB | 2a70ed1de631 |
| qtensors/model.language_model.layers.34.safetensors | Weights | 1.3 GB | 1e64ebc882f4 |
| qtensors/model.language_model.layers.35.safetensors | Weights | 1.3 GB | 35e46f2e67bf |
| qtensors/model.language_model.layers.4.safetensors | Weights | 1.7 GB | 3d6ebe91c178 |
| qtensors/model.language_model.layers.5.safetensors | Weights | 1.9 GB | 379f247f9612 |
| qtensors/model.language_model.layers.6.safetensors | Weights | 1.7 GB | 5c6acf8b60ed |
| qtensors/model.language_model.layers.7.safetensors | Weights | 1.8 GB | 8e662d1672d6 |
| qtensors/model.language_model.layers.8.safetensors | Weights | 1.8 GB | fc86cd493330 |
| qtensors/model.language_model.layers.9.safetensors | Weights | 1.7 GB | 6962fc2ff1d9 |
| config.json | Configuration | 4.7 KB | — |
| generation_config.json | Configuration | 202 B | — |
| preprocessor_config.json | Configuration | 390 B | — |
| video_preprocessor_config.json | Configuration | 385 B | — |
| chat_template.jinja | Other | 9.0 KB | — |
| .gitattributes | Repository | 1.6 KB | — |
| tokenizer.json | Tokenizer | 12.8 MB | 0997f410c57a |
| tokenizer_config.json | Tokenizer | 17.9 KB | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 86.5 GB
Download from Victor Cruz
Released by Victor Cruz through its official repository on Hugging Face.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 86.5 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About Qwen3.8-Flash-Next-EXL3-SAGE-4.77bpw
What is Qwen3.8-Flash-Next-EXL3-SAGE-4.77bpw's context length?
262,144 tokens, from the maximum position embeddings in its published configuration.