DeepSeek

DeepSeek V4 Flash

Name: DeepSeek V4 Flash
Rating: 96 (8 reviews)
Author: DeepSeek

Frontier

HuggingFace

3.4MDownloads1.3KLikesApr 2026Veröffentlicht1.0M TokenKontextMITLizenz98 HerausragendQualität

DeepSeek V4 Flash (284B parameters) requires approximately 160.8 GB of VRAM with NVFP4 quantization. As a Mixture of Experts model with 13B active parameters, it uses less memory than its total parameter count suggests. For the best balance of quality and speed, we recommend hardware with at least 185 GB of VRAM.

Loslegen

— kopieren & einfügen, um lokal auszuführen

Copy-paste commands to run DeepSeek V4 Flash on your machine.

Run

docker run --rm -it ghcr.io/ggerganov/llama.cpp:full \
  --hf-repo "deepseek-ai/DeepSeek-V4-Flash" \
  --hf-file "DeepSeek-V4-Flash-NVFP4.gguf" \
  -c 4096 -ngl 99

Quick specs

Parameters284B (13B active)

Architecturemoe (MoE)

Context1.0M tokens

Modalitytext

Min RAM110.8 GB

Rec. RAM159 GB (NVFP4)

LicenseMIT

FamilyDeepSeek

✓ Code✓ Reasoning

About this model

DeepSeek V4 Flash is the lighter 284B-parameter sparse MoE sibling of V4 Pro (13B active, 256 routed + 1 shared expert) with the same 1M-token context. Experts ship natively in FP4, so the real on-disk footprint is roughly 158 GB rather than the FP16 size — it fits a single 192 GB unified-memory machine or a 2-4 GPU server while keeping near-frontier reasoning and coding quality.

•284B total / 13B active sparse MoE — 256 routed + 1 shared expert
•Native FP4 experts: ~158 GB on disk
•1M-token context with near-frontier coding quality
•Runs on a single 192 GB unified-memory box or a small GPU server

Verwandte Modelle

Schnellauswahl

Bestes BudgetS

AMD Instinct MI350X 288GB~$8,000 — 126 tok/s

Beste GesamtwahlS

AMD Instinct MI325X 256GB~$20,000 — 94 tok/s

Beste Hardware

Top-Empfehlungen für DeepSeek V4 Flash

AMD Instinct MI325X 256GBS

256 GB

AMD Instinct MI350X 288GBS

Dieses Modell ausführen

DeepSeek V4 Flash on AMD Instinct MI325X 256GB DeepSeek V4 Flash on AMD Instinct MI350X 288GB DeepSeek V4 Flash on NVIDIA B200 180GB

Quantisierungsoptionen

VRAM-Schätzungen nach Quantisierungsstufe

No hardware detected — fit column shows raw VRAM estimates

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	110.8 GB	Low	—
Q3_K_S	3	139.2 GB	Low	—
NVFP4	4	159.0 GB	Medium	—
Q4_K_M	4	173.2 GB	Medium	—
Q5_K_M	5	204.5 GB	High	—
Q6_K	6	232.9 GB	High	—
Q8_0	8	303.9 GB	Very High	—
F16	16	582.2 GB	Maximum	—

Quality benchmarks

DeepSeek V4 Flash benchmark scores

Benchmark verified

Coding

SWE-bench Verified—

HumanEval+—

Aider Polyglot—

LiveCodeBench91.6%

Reasoning

MMLU-Pro86.2%

GPQA Diamond—

MATH-500—

ARC Challenge—

Source: vendor-reported · 2026-04-24

Hardware-Kompatibilität

Eignungsschätzungen für alle Hardware

Rechner öffnen

Computing compatibility...

Speicheraufschlüsselung

Reference: RTX 2060 6GB

Weights158.0 GB

KV Cache1.3 GB

Runtime0.9 GB

Headroom0.6 GB

Häufig gestellte Fragen

FAQ — DeepSeek V4 Flash

Siehe auch

Quantisierungsleitfaden Bewertungsmethodik Rechner öffnen