DeepSeek V3-0324 is the March 24, 2025 refresh — same 685 B / 37 B-active MoE architecture as base V3, retrained with R1-style reasoning distillation and an MIT license (a meaningful upgrade from the original V3's bespoke DeepSeek license). On MATH-500, AIME, GPQA, and LiveCodeBench it lands between base V3 and R1 while still producing direct answers (no <think> trace). VRAM math is the same as base V3: ~1370 GB FP16, ~378 GB Q4_K_M — so 8x H100 or 8x B200 is the floor. For Lagos and Istanbul builders this is a cloud-API model, not a homelab one. See our [MoE architecture](/glossary/moe) glossary entry for why only 37 B of the 685 B is touched per token.
DeepSeek V3-0324 needs at minimum 414.4 GB of VRAM at Q4_K_M quantization (1507 GB at FP16). The cheapest GPU that comfortably fits with KV-cache headroom is the NVIDIA GH200 Grace Hopper (576 GB VRAM, $65,000 MSRP). Community benchmark submissions are open. This model exceeds 48 GB at Q4, so plan for a 2-or-more-GPU split.
Weights only. Add ~20-30% for KV cache at typical context lengths.
| Quant | VRAM | Quality | Notes |
|---|---|---|---|
| FP16 | 1507.0 GB | Reference | Training-precision weights |
| Q8_0 | 753.5 GB | Near-lossless | 8-bit, ~0.1% perplexity hit |
| Q6_K | 610.3 GB | Very high | 6-bit, near Q8 quality |
| Q5_K_M | 519.9 GB | High | Strong middle ground |
| Q4_K_M | 414.4 GB | Balanced (recommended) | Default for local deployments |
| Q4_0 | 423.8 GB | Legacy 4-bit | Older GGUF, kept for compatibility |
| Q3_K_M | 324.0 GB | Lossy | When VRAM is very tight |
| Q2_K | 241.1 GB | Extreme | Rescue option, quality degrades visibly |
Filtered from MyAIHardware's GPU database. FP16 needs 1507.0 GB; Q4_K_M needs 414.4 GB.
| GPU | Per-card VRAM | 2x | 4x | 8x |
|---|---|---|---|---|
| AMD Instinct MI355X [VERIFY] | 288 GB | 576 | 1152 | 2304 |
| AMD Instinct MI325X | 256 GB | 512 | 1024 | 2048 |
| Apple Mac Studio (M3 Ultra, 256 GB) | 256 GB | 512 | 1024 | 2048 |
| AMD Instinct MI300X | 192 GB | 384 | 768 | 1536 |
| Apple Mac Studio (M2 Ultra, 192 GB) | 192 GB | 384 | 768 | 1536 |
| Apple Mac Pro (M2 Ultra, 192 GB) | 192 GB | 384 | 768 | 1536 |
We don't have community benchmarks for this exact model yet.
Official weights + popular runtime tags.
ollama pull deepseek-v3:0324Step-by-step guides that use this model.
Models in a similar size or capability class.
Use these in papers, blog posts, or internal docs.
@misc{deepseek-v3-0324-2025,
title={DeepSeek V3-0324},
author={DeepSeek AI},
year={2025},
url={https://huggingface.co/deepseek-ai/DeepSeek-V3-0324}
}DeepSeek AI (2025). DeepSeek V3-0324 [Model card]. Hugging Face. https://huggingface.co/deepseek-ai/DeepSeek-V3-0324
DeepSeek V3-0324 (DeepSeek V3, DeepSeek AI, 2025). Available at https://huggingface.co/deepseek-ai/DeepSeek-V3-0324.