Can I run DeepSeek V3 0324 locally?
DeepSeek V3 0324 by deepseek-ai has 685B parameters (40B active per token, 256 experts, 8 used per token). At 4-bit with an 8K context it needs about 378 GB of GPU memory. It fits on 1 of 65 GPUs and Macs we track.
Memory needed by quant and context length
GB of GPU memory = weights + KV cache (FP16) + runtime overhead. Weights use real file sizes from unsloth/DeepSeek-V3-0324-GGUF where available (marked •), otherwise parameter count × bits per weight. How we calculate.
| Quant | Quality | 4K ctx | 8K ctx | 32K ctx | 128K ctx |
|---|---|---|---|---|---|
| 2-bit (Q2_K) • | rough | 228 GB | 228 GB | 230 GB | 236 GB |
| 3-bit (Q3_K_M) • | usable | 298 GB | 298 GB | 300 GB | 307 GB |
| 4-bit (Q4_K_M) • | good, most popular | 378 GB | 378 GB | 379 GB | 386 GB |
| 5-bit (Q5_K_M) • | very good | 444 GB | 444 GB | 446 GB | 452 GB |
| 6-bit (Q6_K) • | near lossless | 514 GB | 514 GB | 516 GB | 522 GB |
| 8-bit (Q8_0) • | effectively lossless | 665 GB | 665 GB | 667 GB | 674 GB |
| 16-bit (F16/BF16) • | original weights | 1251 GB | 1251 GB | 1253 GB | 1259 GB |
Which GPUs and Macs run DeepSeek V3 0324?
Best quality quant that fits at 8K context. "Tight" = within 10% of usable memory. Speed is a ceiling from memory bandwidth (real speed is typically 50–80% of it).
Prefer an API?
DeepSeek: DeepSeek V3 0324 is on OpenRouter at $0.29 per 1M input tokens and $1.14 per 1M output tokens. Price details and history →
Questions
How much VRAM does DeepSeek V3 0324 need?
About 378 GB at 4-bit (Q4_K_M) with an 8K context: 377 GB of weights (real GGUF file size), 0.5 GB of KV cache and 0.6 GB of runtime overhead. At 8-bit it needs about 665 GB.
What is the smallest GPU that runs DeepSeek V3 0324?
No single consumer GPU in our table fits it at Q4_K_M with 8K context.
Can I run DeepSeek V3 0324 on a Mac?
Not at Q4_K_M with 8K context on any Mac in our table, even a 512 GB Mac Studio, using the default GPU memory limit.
Similar models
Same family or a similar parameter count, with the VRAM each needs at Q4_K_M and 8K context.
DeepSeek V3.1
685B · 379 GB at 4-bitDeepSeek R1 0528
685B · 378 GB at 4-bitDeepSeek R1
684B · 378 GB at 4-bitGLM 5.3
753B · 430 GB at 4-bitGLM 5.2
753B · 435 GB at 4-bitGLM 5
754B · 426 GB at 4-bitModel facts
| Hugging Face repo | deepseek-ai/DeepSeek-V3-0324 |
| Parameters | 684,531,386,000 (685B) · ~40B active (computed from config) |
| Layers / hidden size | 61 / 7168 |
| Attention | MLA; 128 heads, 128 KV heads, head dim 56 |
| KV cache per token (FP16) | 68.6 KiB |
| Max context | 163,840 tokens |
| License | mit |
| Released on HF | Mar 24, 2025 |
| Downloads (30d) / likes | 145,593 / 3,223 |
Sources: Hugging Face model API · config.json (deepseek-ai/DeepSeek-V3-0324) · GGUF files · GPU specs from vendor pages (list). Data fetched Nov 17, 2026. Spot an error? Report it.