👁 DeepSeek
DeepSeek
DeepSeek V3 671B
Current
1.1MDownloads4.1KLikesDec 2024Released131K tokensContextDeepSeekLicense75 StrongQuality
DeepSeek V3 671B (671B parameters) requires approximately 470.4 GB of VRAM with Q4_K_M quantization. As a Mixture of Experts model with 37B 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 541 GB of VRAM.
Get started
— copy & paste to run locallyCopy-paste commands to run DeepSeek V3 671B on your machine.
Run
ollama run deepseek-v3Quick specs
Parameters671B (37B active)
Architecturemoe (MoE)
Context131K tokens
Modalitytext
Min RAM261.7 GB
Rec. RAM409.3 GB (Q4_K_M)
LicenseDeepSeek
FamilyDeepSeek
✓ Chat✓ Reasoning
About this model
- •On top of the efficient architecture of DeepSeek-V2, we pioneer an auxiliary-loss-free strategy for load balancing, which minimizes the...
- •We investigate a Multi-Token Prediction (MTP) objective and prove it beneficial to model performance
Related models
Your hardware
Detecting...
Quantization options
VRAM estimates by quant level
No hardware detected — fit column shows raw VRAM estimates
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 261.7 GB | Low | — |
Q3_K_S | 3 | 328.8 GB | Low | — |
NVFP4 | 4 | 375.8 GB | Medium | — |
Q4_K_M | 4 | 409.3 GB | Medium | — |
Q5_K_M | 5 | 483.1 GB | High | — |
Q6_K | 6 | 550.2 GB | High | — |
Q8_0 | 8 | 718.0 GB | Very High | — |
F16 | 16 | 1375.6 GB | Maximum | — |
Quality benchmarks
DeepSeek V3 671B benchmark scores
Coding
SWE-bench Verified42.0%
HumanEval+82.6%
Aider Polyglot49.6%
LiveCodeBench37.6%
Reasoning
MMLU-Pro75.9%
GPQA Diamond59.1%
MATH-50090.2%
ARC Challenge—
General
Chatbot Arena—
IFEval86.1%
Source: official · 2024-12-26
Hardware compatibility
Fit estimates across all hardware
Computing compatibility...
Memory breakdown
Reference: RTX 2060 6GB
Weights409.3 GB
KV Cache59.6 GB
Runtime0.9 GB
Headroom0.6 GB
Frequently asked questions
FAQ — DeepSeek V3 671B
See also