DeepSeek V4 Models — Hardware Requirements

12 DeepSeek V4 models from DeepSeek and the community, from the smallest that runs in 14.6 GB of VRAM up to 1650.5B parameters. Every row links to full quantization tables and GPU compatibility.

All DeepSeek V4 Models by Size

ModelParamsContext
DeepSeek V4 Flash JANG CRACK33.5B1049K
Deepseek V4 Flash 0731 Spark60.3B1049K
DeepSeek V4 Flash 162B92.2B1049K
DeepSeek V4 Flash 180B101.6B1049K
DeepSeek V4 Flash 0731 Reap 150B150.1B1049K
DeepSeek V4 Flash DSpark165.3B1049K
DeepSeek V4 Flash DSpark Abliterated Uncensored165.3B—
DeepSeek V4 Flash290.9B1049K
DeepSeek V4 Flash 0731304.2B1049K
Keys DeepSeekV4 Flash GA 0731 Dspark Abliterated Anchored Tensors304.2B—
DeepSeek V4 Flash Vision Exp304.6B1049K
DeepSeek V4 Flash Vision Uncensored304.6B—
DeepSeek V4 Flash 0731 Abliterated305.7B1049K
SuperDeepseek V4 Flash Abliterated MQ 2xDGX306.3B1049K
DeepSeek V4.1 Flash763.2B1049K
DeepSeek V4 Pro1598.8B1049K
DeepSeek V4 Pro 08131650.5B1049K
DeepSeek V4 Pro DSpark1650.5B1049K

How DeepSeek V4 Compares — Benchmark Rating

DeepSeek V4.1 Flash is the highest-rated DeepSeek V4 model with an overall benchmark rating of 65.8/100 — #4 among 78 open models. The top proprietary model, Claude Fable 5 (high), scores 87.8. Click a model to see its full benchmark breakdown.

Claude Fable 5 (high) · proprietary87.8
Claude Opus 4.7 · proprietary86.4
Claude Fable 5 Max · proprietary82.4
GPT 6 Astra (high) · proprietary82.4
GPT 6 Astra Max · proprietary82.4
GLM 565.9
Composite of normalized public benchmark scores (methodology) · ■ DeepSeek V4 · ■ other models

Frequently Asked Questions

How much VRAM do I need to run a DeepSeek V4 model?
The smallest DeepSeek V4 model, DeepSeek V4 Flash JANG CRACK, runs from 14.6 GB of VRAM at an aggressive quantization. Larger family members need proportionally more — see the table above for every model.
Which DeepSeek V4 models can I run on a 16 GB GPU?
1 of 18 DeepSeek V4 models fit in 16 GB of VRAM at some quantization, including DeepSeek V4 Flash JANG CRACK.
What is the most popular DeepSeek V4 model to run locally?
DeepSeek V4 Flash is the most downloaded DeepSeek V4 model in local-friendly quantized formats. It runs from 124.0 GB of VRAM.
How do DeepSeek V4 models score on benchmarks?
DeepSeek V4.1 Flash leads the family with an overall benchmark rating of 65.8/100, ranking #4 among 78 open models, while the top proprietary model, Claude Fable 5 (high), scores 87.8. See the comparison chart above for the full standings.