FitMyLLM
DeepSeek/Mixture of Experts

DeepSeekDeepSeek V4 Flash

We present a preview version of DeepSeek-V4 series, including two strong Mixture-of-Experts (MoE) language models — DeepSeek-V4-Pro with 1.6T parameters (49B activated) and DeepSeek-V4-Flash with 284B parameters (13B activated) — both supporting a...

chatcodingreasoningmultilingualmathagentictool_use
284B
Parameters (13B active)
1024K
Context length
14
Benchmarks
17
Quantizations
97K
HF downloads
Architecture
MoE
Released
2026-04-24
Layers
43
KV Heads
1
Head Dim
512
Family
deepseek

Quantization Options

QuantBitsVRAMQuality
IQ2_XXS2.3885.0 GBlow
IQ2_M2.93104.5 GBlow
Q2_K3.16112.7 GBlow
IQ3_XXS3.25115.9 GBlow
IQ3_XS3.5124.7 GBlow
Q3_K_S3.64129.7 GBlow
IQ3_M3.76134.0 GBlow
Q3_K_M4142.5 GBlow
Q3_K_L4.3153.1 GBmoderate
IQ4_XS4.46158.8 GBmoderate
Q4_K_S4.67166.3 GBmoderate
Q4_K_M4.89174.1 GBgood
Q5_K_S5.57198.2 GBgood
Q5_K_M5.7202.8 GBgood
Q6_K6.56233.4 GBexcellent
Q8_08.5302.2 GBlossless
FP1616568.5 GBlossless

Select your GPU above to see speed estimates and compatibility for each quantization.

▸ READY TO RUN THIS?RENT BY THE HOUR

RENT A GPU AND RUN DEEPSEEK V4 FLASH NOW

Rent on RunPod →Or Vast.ai →

Spin up an A100 / H100 / 4090 in ~60s. Pay by the second. Cancel anytime.

Community Ratings

Loading ratings...

Benchmarks (14)

τ²-Bench94.4
LiveCodeBench91.6
GPQA Diamond88.1
MMLU-PRO86.2
SWE-bench79.0
HumanEval69.5
Terminal-Bench56.9
IFBench47.2
BigCodeBench40.4
SciCode37.3
AA Intelligence36.5
AA Coding35.2
HLE34.8
AA Long Context33.3

Run this model

▸Easiest way to get started·Beginners
DOCS ↗
curl -fsSL https://ollama.com/install.sh | sh
$ollama run deepseek:284b-q4_K_M

Tag may need adjustment — check ollama.com/library/deepseek for available tags.

▸ SETUP GUIDE
>_

Auto-setup with fitmyllm CLI

Detects your GPU, recommends the best model, downloads it, and starts chatting — zero config. Benchmarks your speed and contributes anonymous data to improve predictions.

pip install fitmyllmthen run fitmyllmLearn more
Auto-detect GPULive tok/s in chatSpeed benchmarks9 inference engines
HuggingFaceGGUF DownloadsBuild Hardware

GPUs that can run this model

At Q4_K_M quantization. Sorted by minimum VRAM.

AMD Instinct MI300X
192 GB VRAM • 5300 GB/s
AMD
$15000
Apple M2 Ultra (192GB)
192 GB VRAM • 800 GB/s
APPLE
$5499
Apple M3 Ultra (192GB)
192 GB VRAM • 800 GB/s
APPLE
$6999
Apple M4 Ultra (192GB)
192 GB VRAM • 1092 GB/s
APPLE
$7499
AMD Radeon Instinct MI300A
192 GB VRAM • 10300 GB/s
AMD
$12000
AMD Radeon Instinct MI300X
192 GB VRAM • 10300 GB/s
AMD
$15000
AMD Radeon Instinct MI308X
192 GB VRAM • 10300 GB/s
AMD
$12000
Apple M5 Ultra (192GB)
192 GB VRAM • 1228 GB/s
APPLE
AMD Radeon Instinct MI325X
288 GB VRAM • 10300 GB/s
AMD
$20000
AMD Radeon Instinct MI350X
288 GB VRAM • 8190 GB/s
AMD
$25000
AMD Radeon Instinct MI355X
288 GB VRAM • 8190 GB/s
AMD
$30000
Apple M4 Ultra (384GB)
384 GB VRAM • 1092 GB/s
APPLE
$9999
Apple M5 Ultra (384GB)
384 GB VRAM • 1228 GB/s
APPLE

Find the best GPU for DeepSeek V4 Flash

Build Hardware for DeepSeek V4 Flash
▸ SPEC SHEET

DeepSeek V4 Flash — 284B MoE.

▸ SPECIFICATIONS
PARAMETERS
284B (13B active)
ARCHITECTURE
Mixture of Experts
CONTEXT LENGTH
1024K tokens
CAPABILITIES
chat, coding, reasoning, multilingual, math, agentic, tool_use
RELEASE DATE
2026-04-24
PROVIDER
DeepSeek
FAMILY
deepseek
▸ VRAM REQUIREMENTS
QUANTBPWVRAMQUALITY
IQ2_XXS2.3885.0 GB65%
IQ2_M2.93104.5 GB75%
Q2_K3.16112.7 GB78%
IQ3_XXS3.25115.9 GB82%
IQ3_XS3.5124.7 GB84%
Q3_K_S3.64129.7 GB85%
IQ3_M3.76134.0 GB86%
Q3_K_M4142.5 GB88%
Q3_K_L4.3153.1 GB90%
IQ4_XS4.46158.8 GB92%
Q4_K_S4.67166.3 GB93%
Q4_K_M4.89174.1 GB94%
Q5_K_S5.57198.2 GB96%
Q5_K_M5.7202.8 GB96%
Q6_K6.56233.4 GB97%
Q8_08.5302.2 GB100%
FP1616568.5 GB100%
§ 01BENCHMARK SCORES
HumanEval69.5
MMLU-PRO86.2
BigCodeBench40.4
GPQA Diamond88.1
LiveCodeBench91.6
HLE34.8
AA Intelligence36.5
AA Coding35.2
aa_ifbench47.2
aa_terminal_bench56.9
aa_tau294.4
aa_scicode37.3
aa_lcr33.3
SWE-bench79.0
§ 03COMPATIBLE GPUs
13 @ Q4_K_M
AMD Instinct MI300X
192 GB · 5300 GB/s
Apple M2 Ultra (192GB)
192 GB · 800 GB/s
Apple M3 Ultra (192GB)
192 GB · 800 GB/s
Apple M4 Ultra (192GB)
192 GB · 1092 GB/s
AMD Radeon Instinct MI300A
192 GB · 10300 GB/s
AMD Radeon Instinct MI300X
192 GB · 10300 GB/s
AMD Radeon Instinct MI308X
192 GB · 10300 GB/s
Apple M5 Ultra (192GB)
192 GB · 1228 GB/s
AMD Radeon Instinct MI325X
288 GB · 10300 GB/s
AMD Radeon Instinct MI350X
288 GB · 8190 GB/s
AMD Radeon Instinct MI355X
288 GB · 8190 GB/s
Apple M4 Ultra (384GB)
384 GB · 1092 GB/s
Apple M5 Ultra (384GB)
384 GB · 1228 GB/s