Can I run DeepSeek V4 Pro 0813 locally?
DeepSeek V4 Pro 0813 by deepseek-ai has 1.65T parameters (102B active per token, 384 experts, 6 used per token). At 4-bit with an 8K context it needs about 941 GB of GPU memory. It fits on 0 of 65 GPUs and Macs we track.
This model uses a newer compressed or sparse attention design. Our KV-cache numbers use the standard formula, so treat long-context figures as an upper bound.
Memory needed by quant and context length
GB of GPU memory = weights + KV cache (FP16) + runtime overhead. Weights use real file sizes from qtum/DeepSeek-V4-Pro-0813-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 | 548 GB | 549 GB | 552 GB | 565 GB |
| 3-bit (Q3_K_M) • | usable | 712 GB | 713 GB | 716 GB | 729 GB |
| 4-bit (Q4_K_M) | good, most popular | 941 GB | 941 GB | 945 GB | 957 GB |
| 5-bit (Q5_K_M) | very good | 1096 GB | 1097 GB | 1100 GB | 1113 GB |
| 6-bit (Q6_K) | near lossless | 1262 GB | 1262 GB | 1265 GB | 1278 GB |
| 8-bit (Q8_0) | effectively lossless | 1634 GB | 1635 GB | 1638 GB | 1651 GB |
| 16-bit (F16/BF16) | original weights | 3075 GB | 3076 GB | 3079 GB | 3092 GB |
Which GPUs and Macs run DeepSeek V4 Pro 0813?
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 V4 Pro 0813 is on OpenRouter at $0.111 per 1M input tokens and $4.44 per 1M output tokens. Price details and history →
Questions
How much VRAM does DeepSeek V4 Pro 0813 need?
About 941 GB at 4-bit (Q4_K_M) with an 8K context: 940 GB of weights (estimated), 1.1 GB of KV cache and 0.6 GB of runtime overhead. At 8-bit it needs about 1635 GB.
What is the smallest GPU that runs DeepSeek V4 Pro 0813?
No single consumer GPU in our table fits it at Q4_K_M with 8K context.
Can I run DeepSeek V4 Pro 0813 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.
Model facts
| Hugging Face repo | deepseek-ai/DeepSeek-V4-Pro-0813 |
| Parameters | 1,650,497,936,906 (1.65T) · ~102B active (computed from config) |
| Layers / hidden size | 61 / 7168 |
| Attention | GQA; 128 heads, 1 KV heads, head dim 512 |
| KV cache per token (FP16) | 137.3 KiB |
| Max context | 1,048,576 tokens |
| License | mit |
| Released on HF | Aug 13, 2026 |
| Downloads (30d) / likes | 50,410 / 917 |
Sources: Hugging Face model API · config.json (deepseek-ai/DeepSeek-V4-Pro-0813) · GGUF files · GPU specs from vendor pages (list). Data fetched Nov 17, 2026. Spot an error? Report it.