Can you run DeepSeek V4 Pro locally?
DeepSeek V4 family · Apr 2026 (preview) · 1.6T parameters (49B activated per token) · Hugging Face model card
DeepSeek V4-Pro is a mixture-of-experts model with 1.6T total parameters and 49B activated per token (official README table; MIT). Config (deepseek-ai/DeepSeek-V4-Pro@b5968e9190ef611bbf34a7229255be88a0e937c1) is model_type=deepseek_v4, 61 layers, hidden_size=7168, 128 attention heads, 1 KV head, head_dim=512, 384 routed experts × 6 per token + 1 shared, native context 1,048,576, sliding_window=128, YaRN rope_scaling factor 16. Shipped precision is FP4+FP8 mixed. Resident Q4_K_M needs about 1056 GB (T08 documented calculation from 1.6T total). Data-center only. Measured tok/s: not published here.
Minimum: Multi-node / ~1056 GB at Q4_K_M (calculated from 1.6T resident; T08) · Recommended: Multi-node data-center; not a single unified-memory Mac/Strix fit
How much VRAM does DeepSeek V4 Pro need at each quantization?
DeepSeek V4 Pro needs 1,056.5 GB of VRAM at Q4_K_M. The table below lists weights-only size and total VRAM including overhead for each common quantization level with 4k and 32k token contexts.
| Quantization | Bits / weight | Weights only | Total + KV @4k ctx | Total + KV @32k ctx |
|---|---|---|---|---|
| Q4_K_M | 4.8 | 960.0 GB | 1,056.5 GB | 1,060.1 GB |
| Q5_K_M | 5.7 | 1,140.0 GB | 1,254.5 GB | 1,258.1 GB |
| Q6_K | 6.6 | 1,320.0 GB | 1,452.5 GB | 1,456.1 GB |
| Q8_0 | 8.5 | 1,700.0 GB | 1,870.5 GB | 1,874.1 GB |
| FP16 | 16 | 3,200.0 GB | 3,520.5 GB | 3,524.1 GB |
Same V4 hybrid CSA+HCA family. Config: num_key_value_heads=1, head_dim=512, sliding_window=128. VRAM floor follows 1.6T resident weights, not 49B active.
Method: weights = parameters × bits-per-weight (Q4_K_M ≈ 4.8, Q5_K_M ≈ 5.7, Q6_K ≈ 6.6, Q8_0 ≈ 8.5, FP16 = 16), plus 10% loading overhead, plus KV cache from the verified architecture config (61 layers, 1 KV heads, 512 head dim). Source: HF-verified 2026-09-21 via api (gated=false private=false safetensors.total=1598839674782) + config.json repo=deepseek-ai/DeepSeek-V4-Pro@b5968e9190ef611bbf34a7229255be88a0e937c1 model_type=deepseek_v4 layers=61 hidden=7168 heads=128 kv_heads=1 head_dim=512 ctx=1048576 n_routed_experts=384 num_experts_per_tok=6 n_shared_experts=1 sliding_window=128 license=mit. Vendor README table: total=1600B active=49B precision=fp4_fp8_mixed. VRAM GB are T08 documented calculations from resident total, not measurements. No tok/s invented.
Which GPUs can run DeepSeek V4 Pro locally?
At Q4_K_M with a 4k context, DeepSeek V4 Pro needs 1,056.5 GB of VRAM. The lists below are computed live from our GPU database and grouped by how much headroom the card has. Disclosure: CompareAIHardware.com participates in the Amazon Associates program and earns from qualifying purchases through links on this page. Affiliate relationships do not influence our recommendations.
No single consumer GPU in our database runs DeepSeek V4 Pro at Q4_K_M. The 1,056.5 GB requirement exceeds every listed consumer card; see the Mac and data center options above and below.