Specification

Release date: 22 Apr 2026
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
Openness: open-weights
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
Architecture: DeepseekV4ForCausalLM
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
Parameters: 292B
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
Quantization format: fp8
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
File size: 294.7 GB
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
Hugging Face repo: deepseek-ai/DeepSeek-V4-Flash-Base
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
Model card: huggingface.co/deepseek-ai/DeepSeek-V4-Flash-Base
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
Downloads: 551,449
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 13 min agomedium
Likes: 314
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 13 min agomedium
Gated: No
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
Is quantized: Yes
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
Last modified: 2026-04-27T06:51:43+00:00
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
Downloads all time: 1,108,069
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
Model type: deepseek_v4
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
Tags: safetensors, deepseek_v4, fp8
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
Weights dtype: BF16, F32, F8_E4M3, I64
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium

Each value shows its source, tier and observation time. Conflicting claims are kept side by side and flagged — never averaged. How AI Atlas records facts →

Provenance

Attributed facts

17

Source tiers

T217

Freshest observation

13 min ago

Conflicts

None

Modalities

Modalities unavailable.

Capabilities

Tool calling
Unavailable
Structured output
Unavailable
Reasoning
Unavailable
Vision
Unavailable
Audio
Unavailable
Fine-tuning available
Unavailable

No capability flags have been observed from a source yet — we do not infer them.

No structured attributes yet.

No benchmark results recorded

Results appear when a tier 1–3 source publishes them; we never copy scores without a source.

Current prices

No current prices recorded

Prices appear when a provider publishes a public pricing page we crawl.

Price history

Estimated

Memory need = bytes per parameter (4-bit ≈ 0.5 × 1.15 overhead, 8-bit 1.0, fp16 2.0) + a KV-cache allowance. Not a measurement.

Estimated hardware fit
Hardware	Quantization	Memory	Est. need	Fits
NVIDIA DGX B200	4bit	1,440 GB	168.4 GB	Yes
Apple M3 Ultra	4bit	—	168.4 GB	Yes
Mac Studio (Apple M5 Ultra)	4bit	—	168.4 GB	Yes
AMD Instinct MI325X	4bit	256 GB	168.4 GB	Yes
AMD Instinct MI300X	4bit	192 GB	168.4 GB	Yes
Apple M2 Ultra	4bit	—	168.4 GB	Yes
NVIDIA B200	4bit	180 GB	168.4 GB	Yes
NVIDIA H200	4bit	141 GB	168.4 GB	No
NVIDIA H200 NVL	4bit	141 GB	168.4 GB	No
Apple M1 Ultra	4bit	—	168.4 GB	No
Apple M3 Max	4bit	—	168.4 GB	No
Apple M4 Max	4bit	—	168.4 GB	No
Mac Studio (Apple M5 Max)	4bit	—	168.4 GB	No
MacBook Pro (Apple M5 Max)	4bit	—	168.4 GB	No
NVIDIA DGX Spark	4bit	128 GB	168.4 GB	No
Apple M2 Max	4bit	—	168.4 GB	No
NVIDIA H100 NVL	4bit	94 GB	168.4 GB	No
NVIDIA A100 80GB	4bit	80 GB	168.4 GB	No
NVIDIA H100 SXM	4bit	80 GB	168.4 GB	No
Apple M1 Max	4bit	—	168.4 GB	No
Apple M4 Pro	4bit	—	168.4 GB	No
Mac mini (Apple M5 Pro)	4bit	—	168.4 GB	No
MacBook Pro (Apple M5 Pro)	4bit	—	168.4 GB	No
Apple M3 Pro	4bit	—	168.4 GB	No
Apple M1 Pro	4bit	—	168.4 GB	No
Apple M2 Pro	4bit	—	168.4 GB	No
Apple M4	4bit	—	168.4 GB	No
iMac (Apple M4)	4bit	—	168.4 GB	No
Mac mini (Apple M6)	4bit	—	168.4 GB	No
MacBook Air (Apple M5)	4bit	—	168.4 GB	No
MacBook Pro (Apple M5)	4bit	—	168.4 GB	No
NVIDIA GeForce RTX 5090	4bit	32 GB	168.4 GB	No
Apple M2	4bit	—	168.4 GB	No
Apple M3	4bit	—	168.4 GB	No
NVIDIA GeForce RTX 3090	4bit	24 GB	168.4 GB	No
NVIDIA GeForce RTX 4090	4bit	24 GB	168.4 GB	No
Apple M1	4bit	—	168.4 GB	No

No lineage recorded

Lineage comes from explicit `derived_from`, `fine_tuned_from`, `distilled_from` and `quantized_from` relations stated by sources.

Papers 0

No papers linked yet.

Repositories 0

No repositories linked yet.

As of

Rewind the record: see this entity's attributes exactly as AI Atlas knew them on a given day.

Claim history · Last modified

1 claims · 1 propertiesShow all properties

Last modifiedlast_modified1

Claim history for Last modified
Value	Valid from → to	Status	Source	Confidence	Extractor
2026-04-27T06:51:43+00:00	11 Sept 2026 21:10 UTC → current	current	Hugging Face Hub (public pages, model cards, papers)T2	medium	deterministic

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 →

11 Sept 2026
New modelModelDeepSeek-V4-Flash-BaseDeepSeek
New model: DeepSeek-V4-Flash-Base (DeepSeek)
huggingface
huggingface.co

Full timeline →

Source documents
Source	Document	Type	Tier	Last observed	Snapshots
Hugging Face Hub (public pages, model cards, papers)	huggingface.co/models?author=deepseek-ai&p=0&sort=downloads	listing	T2· Quality secondary	13 min ago	3
Hugging Face Hub (public pages, model cards, papers)	huggingface.co/deepseek-ai/DeepSeek-V4-Flash-Base	model_page	T2· Quality secondary	2 h ago	1

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