DeepSeek V3 Models — Hardware Requirements
9 DeepSeek V3 models from DeepSeek and the community, from the smallest that runs in 412.1 GB of VRAM at Q4 up to 685.4B parameters. Every row links to full quantization tables and GPU compatibility.
All DeepSeek V3 Models by Size
| Model | Params | Runs from (Q4) | Context | Publisher | Quant downloads |
|---|---|---|---|---|---|
| DeepSeek v3 | 684.5B | 412.1 GB | 164K | ||
| DeepSeek v3 0324 | 684.5B | 412.2 GB | 164K | ||
| DeepSeek V3.1 | 684.5B | 412.2 GB | 164K | ||
| DeepSeek V3.1 Terminus | 684.5B | 412.2 GB | 164K | ||
| DeepSeek V3.2 | 685.4B | 412.7 GB | 164K | ||
| DeepSeek V3.2 Exp | 685.4B | 412.7 GB | 164K | ||
| DeepSeek V3.2 Speciale | 685.4B | 412.7 GB | 164K |
How DeepSeek V3 Compares — llmrun Composite Score
DeepSeek V3.2 is the highest-scoring DeepSeek V3 model with an llmrun Composite Score of 110.4 — #31 among 106 open models. The top proprietary model, Gemini 4 Carbon, scores 158.6. Click a model to see its full benchmark breakdown.
Gemini 4 Carbon · proprietary158.6
GPT 6 Astra · proprietary156.2
Claude Opus 5.5 · proprietary153.0
GPT 6.1 Sol · proprietary151.7
GPT 6.1 Terra · proprietary150.1
Kimi K3.1 Pro142.8
MiMo V2.6 Pro RL133.3
Kimi K3132.7
MiMo V2.6 Flash RL131.9
GLM 5.3130.1
DeepSeek V4.1 Flash129.4
DeepSeek V4 Pro 0813129.2
DeepSeek V3.2110.4
DeepSeek V3.2 Exp109.0
DeepSeek V3.1100.2
DeepSeek v3 032493.9
DeepSeek v389.0
Frequently Asked Questions
- How much VRAM do I need to run a DeepSeek V3 model?
- The smallest DeepSeek V3 model, DeepSeek v3, runs from 412.1 GB of VRAM at Q4_K_M (smaller low-bit quantizations start at 192.1 GB with a noticeable quality loss). Larger family members need proportionally more — see the table above for every model.
- Which DeepSeek V3 models can I run on a 16 GB GPU?
- No DeepSeek V3 model currently fits in 16 GB of VRAM — the family starts at 412.1 GB.
- What is the most popular DeepSeek V3 model to run locally?
- DeepSeek v3 0324 is the most downloaded DeepSeek V3 model in local-friendly quantized formats. It runs from 412.2 GB of VRAM at Q4_K_M.
- How do DeepSeek V3 models score on benchmarks?
- DeepSeek V3.2 leads the family with an llmrun Composite Score of 110.4, ranking #31 among 106 open models, while the top proprietary model, Gemini 4 Carbon, scores 158.6. See the comparison chart above for the full standings.