Skip to page content
SAVRN
Search Plan a project

Open-weight model

DSV4.1-Flash-1017-SAGE-EXL3-1.62bpw

by Victor Cruz vcruz305/DSV4.1-Flash-1017-SAGE-EXL3-1.62bpw

DSV4.1-Flash-1017-SAGE-EXL3-1.62bpw is an open-weight model from Victor Cruz. It has 1,048,576-token context. Its published files total 360.4 GB.

Parameters—
Context1,048,576
Weights360.4 GB
License—
AccessOpen weights
Monthly Downloads—

Model Card

The publisher has not written a card for this model.

Configuration

Architecture
DeepseekV41ForCausalLM
Context length (tokens)
1,048,576
Layers
40
Hidden size
5,120
Attention heads
64
Key/value heads
1
Head dimension
512
Vocabulary size
129,280
Routed experts
384
Experts active per token
6
Sliding window (tokens)
128
RoPE base
10,000
Model type
deepseek_v41
Quantization
fp8

Identity and Version

Repository
vcruz305/DSV4.1-Flash-1017-SAGE-EXL3-1.62bpw
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
58294fac90a302883fb6383082ef3c87262a7698
First published
2026-10-18
Last updated
2026-10-18

Files and Weights

68 files, 360.4 GB in total. The weights are 38 files totalling 360.4 GB in safetensors.

Weights38 files · 360.4 GB
Configuration27 files · 9.5 KB
Tokenizer2 files · 6.4 MB
Repository1 file · 1.5 KB
Every file
FileTypeSizeSHA-256
layers/layer-00.safetensorsWeights2.7 GB 12a0f5e955fe
layers/layer-01.safetensorsWeights2.6 GB 82821e04e202
layers/layer-02.safetensorsWeights2.5 GB 913aaef6e95d
layers/layer-03.safetensorsWeights2.5 GB be81ea8dfcd8
layers/layer-04.safetensorsWeights2.6 GB 8059be278fc9
layers/layer-05.safetensorsWeights2.6 GB 63baa5f5fae5
layers/layer-06.safetensorsWeights2.6 GB 55f42a8471cb
layers/layer-07.safetensorsWeights2.7 GB 85414f8a2faf
layers/layer-08.safetensorsWeights2.9 GB 73b230fe0ad3
layers/layer-09.safetensorsWeights2.8 GB e52389d0e84b
layers/layer-10.safetensorsWeights2.8 GB bf588417d949
layers/layer-11.safetensorsWeights3.0 GB fec80c1ab60b
layers/layer-12.safetensorsWeights3.0 GB ffbfc8eff1ec
layers/layer-13.safetensorsWeights3.1 GB 5fe7718165ac
layers/layer-14.safetensorsWeights2.9 GB 86176b37c3f0
layers/layer-15.safetensorsWeights3.3 GB 38c796d645f9
layers/layer-16.safetensorsWeights3.0 GB cb03001abac9
layers/layer-17.safetensorsWeights3.1 GB a58ec04c7b4b
layers/layer-18.safetensorsWeights3.0 GB 079176067422
layers/layer-19.safetensorsWeights3.3 GB a73272805a08
layers/layer-20.safetensorsWeights3.1 GB 5578bdaa9e27
layers/layer-21.safetensorsWeights3.1 GB 99ed6a75ca91
layers/layer-22.safetensorsWeights3.1 GB 7ac1c181f57f
layers/layer-23.safetensorsWeights3.2 GB f3567a4ca175
layers/layer-27.safetensorsWeights3.0 GB acadbfa95dfe
layers/layer-31.safetensorsWeights2.7 GB a081316c3e6d
model-00001-of-00017.safetensorsWeights8.2 GB b3d88b94ed2b
model-00002-of-00017.safetensorsWeights8.2 GB 4d98ef7853e4
model-00003-of-00017.safetensorsWeights8.2 GB 4bc7abb085f3
model-00004-of-00017.safetensorsWeights8.2 GB 750b63f33ba0
model-00005-of-00017.safetensorsWeights8.2 GB d07944af2fcd
model-00006-of-00017.safetensorsWeights8.2 GB e2230f10f724
model-00007-of-00017.safetensorsWeights8.2 GB 586fb16aa30a
model-00008-of-00017.safetensorsWeights8.2 GB 3763618a7abe
model-00009-of-00017.safetensorsWeights8.2 GB b056c60dfb80
model-00010-of-00017.safetensorsWeights8.2 GB 7ad3326d83d8
model-00016-of-00017.safetensorsWeights101.5 GB 76a05106ece2
model-00017-of-00017.safetensorsWeights101.5 GB 9dc51433e195
config.jsonConfiguration3.3 KB —
layers/layer-00.manifest.jsonConfiguration242 B —
layers/layer-01.manifest.jsonConfiguration242 B —
layers/layer-02.manifest.jsonConfiguration229 B —
layers/layer-03.manifest.jsonConfiguration242 B —
layers/layer-04.manifest.jsonConfiguration242 B —
layers/layer-05.manifest.jsonConfiguration242 B —
layers/layer-06.manifest.jsonConfiguration242 B —
layers/layer-07.manifest.jsonConfiguration242 B —
layers/layer-08.manifest.jsonConfiguration241 B —
layers/layer-09.manifest.jsonConfiguration230 B —
layers/layer-10.manifest.jsonConfiguration242 B —
layers/layer-11.manifest.jsonConfiguration243 B —
layers/layer-12.manifest.jsonConfiguration231 B —
layers/layer-13.manifest.jsonConfiguration231 B —
layers/layer-14.manifest.jsonConfiguration231 B —
layers/layer-15.manifest.jsonConfiguration256 B —
layers/layer-16.manifest.jsonConfiguration243 B —
layers/layer-17.manifest.jsonConfiguration231 B —
layers/layer-18.manifest.jsonConfiguration231 B —
layers/layer-19.manifest.jsonConfiguration243 B —
layers/layer-20.manifest.jsonConfiguration243 B —
layers/layer-21.manifest.jsonConfiguration243 B —
layers/layer-22.manifest.jsonConfiguration243 B —
layers/layer-23.manifest.jsonConfiguration231 B —
layers/layer-27.manifest.jsonConfiguration231 B —
layers/layer-31.manifest.jsonConfiguration231 B —
.gitattributesRepository1.5 KB —
tokenizer.jsonTokenizer6.4 MB —
tokenizer_config.jsonTokenizer801 B —

License and Download

License
Not stated by the source
Access
Open weights, no gate
Download size
360.4 GB
Download from Victor Cruz

Released by Victor Cruz through its official repository on Hugging Face.

Memory Requirements

PrecisionWeights in memory
As published360.4 GB

Weights only, from the published parameter count; the key-value cache and runtime add to this.

Questions About DSV4.1-Flash-1017-SAGE-EXL3-1.62bpw

What is DSV4.1-Flash-1017-SAGE-EXL3-1.62bpw's context length?

1,048,576 tokens, from the maximum position embeddings in its published configuration.