DeepSeek-V4-Flash-0731 VRAM Requirements & Cheapest Live GPU Rates

Exact VRAM math for DeepSeek-V4-Flash-0731 at FP16, FP8 and INT4 across 8K to 131K context, matched with live RunPod and Vast.ai rates for the cheapest fitting GPU rigs.

Architecture truth card — DeepSeek-V4-Flash-0731

Exact safetensors params304,180,418,494 (304.2B)
Hidden layers43
KV heads (GQA)1
Head dim512
Data snapshot (UTC)2026-11-18T18:29:13+00:00
Snapshot SHA-256d89025de2d15…

← Open the interactive VRAM & cost calculator on the homepage

Exact VRAM matrix — 3 precisions × 3 context lengths

Precision8192 tokens ctx32768 tokens ctx131072 tokens ctx
FP16/BF16 16-bit566.58 / 0.67 / 29.83
Total 597.08 GiB
566.58 / 2.69 / 29.83
Total 599.10 GiB
566.58 / 10.75 / 29.83
Total 607.16 GiB
FP8/INT8 8-bit283.29 / 0.67 / 15.66
Total 299.63 GiB
283.29 / 2.69 / 15.66
Total 301.64 GiB
283.29 / 10.75 / 15.66
Total 309.70 GiB
INT4/AWQ 4.5-bit159.35 / 0.67 / 9.47
Total 169.49 GiB
159.35 / 2.69 / 9.47
Total 171.51 GiB
159.35 / 10.75 / 9.47
Total 179.57 GiB

Each cell: Weights GiB / GQA KV Cache GiB / Runtime Overhead GiB; bold line = Total VRAM GiB. Concurrency = 1, FP16 KV cache (2 bytes), overhead = 1.5 + 0.05 × weights GiB.

Terminal speed-math — no install needed

Re-run this exact sizing from your own terminal:

curl -fsSL https://gpuvram.pages.dev/vram-cli.py | python3 - deepseek-v4-flash-0731 --ctx 32768

Live cheapest GPU configurations

ScenarioCheapest fitting rig (top 3)Total VRAMLowest $/hr730 h/moDeploy
INT4 @ 32K ctx1x MI300X 192GB192 GiB$0.50$365.00Deploy on RunPodCheck Vast.ai Verified
INT4 @ 32K ctx2x H200 NVL 143GB286 GiB$1.00$730.00Deploy on RunPodCheck Vast.ai Verified
INT4 @ 32K ctx2x MI300X 192GB384 GiB$1.00$730.00Deploy on RunPodCheck Vast.ai Verified
FP8 @ 32K ctx2x MI300X 192GB384 GiB$1.00$730.00Deploy on RunPodCheck Vast.ai Verified
FP8 @ 32K ctx4x H200 NVL 143GB572 GiB$2.00$1460.00Deploy on RunPodCheck Vast.ai Verified
FP8 @ 32K ctx4x MI300X 192GB768 GiB$2.00$1460.00Deploy on RunPodCheck Vast.ai Verified
FP16 @ 32K ctx4x MI300X 192GB768 GiB$2.00$1460.00Deploy on RunPodCheck Vast.ai Verified
FP16 @ 32K ctx8x H200 NVL 143GB1144 GiB$4.00$2920.00Deploy on RunPodCheck Vast.ai Verified
FP16 @ 32K ctx8x MI300X 192GB1536 GiB$4.00$2920.00Deploy on RunPodCheck Vast.ai Verified

What over-provisioning costs you

Running DeepSeek-V4-Flash-0731 production traffic at INT4 / 32K context on the cheapest fitting rig (1x MI300X 192GB) bills $365.00 per month (730 h). Defaulting to full FP16 forces a larger rig — 4x MI300X 192GB at $1460.00/mo. Paying $1460.00 instead of $365.00 every single month is the price of skipping 4-bit AWQ quantization; if your quality budget allows INT4, that gap is pure waste.