Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
EnsueAI
/
DeepSeek-V4-Flash-Base-INT4
like
6
Follow
EnsueAI
6
quantization
int4
Mixture of Experts
deepseek
License:
deepseek-v4-flash-base-license
Model card
Files
Files and versions
xet
Community
1
Copy to bucket
new
main
DeepSeek-V4-Flash-Base-INT4
186 GB
Ctrl+K
Ctrl+K
1 contributor
History:
4 commits
zyan1deOG
Reframe as first INT4 release; hero metrics + verification at top
76de289
verified
2 months ago
.gitattributes
Safe
1.52 kB
initial commit
2 months ago
README.md
5.12 kB
Reframe as first INT4 release; hero metrics + verification at top
2 months ago
model0-mp4.safetensors
46.6 GB
xet
V4-Flash-Base INT4 Tier-A overlay (~70% coverage, MMLU Δ 0.8 pp, ~90 GiB on-disk savings)
2 months ago
model1-mp4.safetensors
46.6 GB
xet
V4-Flash-Base INT4 Tier-A overlay (~70% coverage, MMLU Δ 0.8 pp, ~90 GiB on-disk savings)
2 months ago
model2-mp4.safetensors
46.6 GB
xet
V4-Flash-Base INT4 Tier-A overlay (~70% coverage, MMLU Δ 0.8 pp, ~90 GiB on-disk savings)
2 months ago
model3-mp4.safetensors
46.6 GB
xet
V4-Flash-Base INT4 Tier-A overlay (~70% coverage, MMLU Δ 0.8 pp, ~90 GiB on-disk savings)
2 months ago
per_linear_quant.json
4.08 MB
V4-Flash-Base INT4 Tier-A overlay (~70% coverage, MMLU Δ 0.8 pp, ~90 GiB on-disk savings)
2 months ago
quant_metadata.json
1.03 kB
V4-Flash-Base INT4 Tier-A overlay (~70% coverage, MMLU Δ 0.8 pp, ~90 GiB on-disk savings)
2 months ago
recipe.yaml
1.08 kB
V4-Flash-Base INT4 Tier-A overlay (~70% coverage, MMLU Δ 0.8 pp, ~90 GiB on-disk savings)
2 months ago
tokenizer.json
Safe
6.37 MB
V4-Flash-Base INT4 Tier-A overlay (~70% coverage, MMLU Δ 0.8 pp, ~90 GiB on-disk savings)
2 months ago
tokenizer_config.json
Safe
801 Bytes
V4-Flash-Base INT4 Tier-A overlay (~70% coverage, MMLU Δ 0.8 pp, ~90 GiB on-disk savings)
2 months ago