Skip to content
AI Atlas
ModelActive

DeepSeek-V4-Flash-Base

DeepSeekhuggingface.co/deepseek-ai/DeepSeek-V4-Flash-Bas

Open in Graph
data quality50

Updated 6 h ago · first seen 11 Sept 2026

model_01M294Y7HXJW48RT7FTNJZA2TF

Overview

Identity

Identity block not returned by the API for this entity.

Openness

Openness not classified yet — no sourced evidence to place this model in the ontology.

Key facts

Release date

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 12 h agomedium

Architecture

Architecture

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 12 h agomedium

Model type

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 12 h agomedium

Parameters

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 12 h agomedium

Weights dtype

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 12 h agomedium

File size

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 12 h agomedium

Hugging Face repo

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 12 h agomedium

Hardware fit37

Estimated

7 of 37 device × quantization combinations fit.

Run locally: your machine →
Estimated hardware fit
HardwareQuantizationDevice memoryEst. memoryFits
Apple M3 Ultra4bit168.4 GB est.Yes
Mac Studio (Apple M5 Ultra)4bit168.4 GB est.Yes
Apple M2 Ultra4bit168.4 GB est.Yes
NVIDIA B2004bit180 GB168.4 GB est.Yes
AMD Instinct MI300X4bit192 GB168.4 GB est.Yes
AMD Instinct MI325X4bit256 GB168.4 GB est.Yes
NVIDIA DGX B2004bit1,440 GB168.4 GB est.Yes
Apple M1 Ultra4bit168.4 GB est.No
Apple M3 Max4bit168.4 GB est.No
Apple M4 Max4bit168.4 GB est.No
Mac Studio (Apple M5 Max)4bit168.4 GB est.No
MacBook Pro (Apple M5 Max)4bit168.4 GB est.No
Apple M2 Max4bit168.4 GB est.No
Apple M1 Max4bit168.4 GB est.No
Apple M4 Pro4bit168.4 GB est.No
Mac mini (Apple M5 Pro)4bit168.4 GB est.No
MacBook Pro (Apple M5 Pro)4bit168.4 GB est.No
Apple M3 Pro4bit168.4 GB est.No
Apple M1 Pro4bit168.4 GB est.No
Apple M2 Pro4bit168.4 GB est.No
Apple M44bit168.4 GB est.No
iMac (Apple M4)4bit168.4 GB est.No
Mac mini (Apple M6)4bit168.4 GB est.No
MacBook Air (Apple M5)4bit168.4 GB est.No
MacBook Pro (Apple M5)4bit168.4 GB est.No
Apple M24bit168.4 GB est.No
Apple M34bit168.4 GB est.No
Apple M14bit168.4 GB est.No
NVIDIA GeForce RTX 30904bit24 GB168.4 GB est.No
NVIDIA GeForce RTX 40904bit24 GB168.4 GB est.No
NVIDIA GeForce RTX 50904bit32 GB168.4 GB est.No
NVIDIA A100 80GB4bit80 GB168.4 GB est.No
NVIDIA H100 SXM4bit80 GB168.4 GB est.No
NVIDIA H100 NVL4bit94 GB168.4 GB est.No
NVIDIA DGX Spark4bit128 GB168.4 GB est.No
NVIDIA H2004bit141 GB168.4 GB est.No
NVIDIA H200 NVL4bit141 GB168.4 GB est.No
Assumptions (6)
  • Estimated, not measured: weights = parameters × bytes/param × 1.15 runtime overhead.
  • bytes/param: 4bit = 0.5, 8bit = 1.0, fp16 = 2.0 (uniform quantization, no per-layer exceptions).
  • KV cache approximated at 0.5 GB per 8 192 tokens of context, independent of architecture (GQA/MLA models need less).
  • A model 'fits' when the estimate is at most the device memory minus 2 GB reserved for the OS and framework.
  • Mixture-of-experts models are estimated on total parameters (all experts must be resident); active parameters are ignored.
  • Device memory uses the largest configuration when several are listed (e.g. Apple silicon tiers).

Change history17

Temporal, append-only claims: a new observation closes the previous claim instead of overwriting it. Rewind the record with the as-of picker.

Viewing AI Atlas as of 12 Sept 2026 — attributes exactly as the atlas knew them on that day; later corrections are not shown.

Back to today →

Attributes as of 12 Sept 2026 18 claims in force

Release date
22 Apr 2026
Openness
open-weights
Architecture
DeepseekV4ForCausalLM
Parameters
292B
Quantization format
fp8
File size
294.7 GB
Hugging Face repo
deepseek-ai/DeepSeek-V4-Flash-Base
Downloads
551,449
Likes
314
Gated
No
Is quantized
Yes
Last modified
2026-04-27T06:51:43+00:00
Downloads all time
1,108,069
Model type
deepseek_v4
Tags
safetensors, deepseek_v4, fp8
Weights available
Yes
Weights dtype
BF16, F32, F8_E4M3, I64
17 claims · 17 properties

Release daterelease_date1

Claim history for Release date
ValueValid from → toStatusSourceConfidenceExtractor
22 Apr 2026currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Opennessopenness1

Claim history for Openness
ValueValid from → toStatusSourceConfidenceExtractor
open-weightscurrentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Architecturearchitecture1

Claim history for Architecture
ValueValid from → toStatusSourceConfidenceExtractor
DeepseekV4ForCausalLMcurrentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Parametersparameter_count1

Claim history for Parameters
ValueValid from → toStatusSourceConfidenceExtractor
292BcurrentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Quantization formatquant_format1

Claim history for Quantization format
ValueValid from → toStatusSourceConfidenceExtractor
fp8currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

File sizefile_size_gb1

Claim history for File size
ValueValid from → toStatusSourceConfidenceExtractor
294.7 GBcurrentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Hugging Face repohf_repo1

Claim history for Hugging Face repo
ValueValid from → toStatusSourceConfidenceExtractor
deepseek-ai/DeepSeek-V4-Flash-BasecurrentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Model cardmodel_card_url1

Claim history for Model card
ValueValid from → toStatusSourceConfidenceExtractor
https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash-BasecurrentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Downloadsmetric.downloads1

Claim history for Downloads
ValueValid from → toStatusSourceConfidenceExtractor
551,449currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Likesmetric.likes1

Claim history for Likes
ValueValid from → toStatusSourceConfidenceExtractor
314currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Gatedgated1

Claim history for Gated
ValueValid from → toStatusSourceConfidenceExtractor
NocurrentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Is quantizedis_quantized1

Claim history for Is quantized
ValueValid from → toStatusSourceConfidenceExtractor
YescurrentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Last modifiedlast_modified1

Claim history for Last modified
ValueValid from → toStatusSourceConfidenceExtractor
2026-04-27T06:51:43+00:00currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Downloads all timemetric.downloads_all_time1

Claim history for Downloads all time
ValueValid from → toStatusSourceConfidenceExtractor
1,108,069currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Model typemodel_type1

Claim history for Model type
ValueValid from → toStatusSourceConfidenceExtractor
deepseek_v4currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Tagstags1

Claim history for Tags
ValueValid from → toStatusSourceConfidenceExtractor
safetensors, deepseek_v4, fp8currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Weights dtypeweights_dtype1

Claim history for Weights dtype
ValueValid from → toStatusSourceConfidenceExtractor
BF16, F32, F8_E4M3, I64currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Claims are temporal and append-only: a new observation closes the previous claim (valid_to) instead of overwriting it. Conflicting claims from different sources are kept side by side and flagged — never averaged. Methodology →

Provenance

Attributed facts

17

Source tiers

T217

Freshest observation

6 h ago

Conflicts

None

Source documents 2

Source documents
SourceDocumentTypeTierLast observedSnapshots
Hugging Face Hub (public pages, model cards, papers)huggingface.co/deepseek-ai/DeepSeek-V4-Flash-Base model_pageT2· Quality secondary6 h ago4
Hugging Face Hub (public pages, model cards, papers)huggingface.co/models?author=deepseek-ai&p=0&sort=downloads listingT2· Quality secondary6 h ago6

Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.

Data quality (50/100) measures how well AI Atlas knows this entity — completeness, primary-source ratio, freshness, conflicts — never how good the model is. Methodology →