diffusiongemma-26B-A4B-it VRAM Requirements & Cheapest Live GPU Rates

Exact VRAM math for diffusiongemma-26B-A4B-it 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 — diffusiongemma-26B-A4B-it

Exact safetensors params25,823,778,864 (25.8B)
Hidden layers30
KV heads (GQA)8
Head dim256
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-bit48.10 / 1.88 / 3.91
Total 53.88 GiB
48.10 / 7.50 / 3.91
Total 59.51 GiB
48.10 / 30.00 / 3.91
Total 82.01 GiB
FP8/INT8 8-bit24.05 / 1.88 / 2.70
Total 28.63 GiB
24.05 / 7.50 / 2.70
Total 34.25 GiB
24.05 / 30.00 / 2.70
Total 56.75 GiB
INT4/AWQ 4.5-bit13.53 / 1.88 / 2.18
Total 17.58 GiB
13.53 / 7.50 / 2.18
Total 23.20 GiB
13.53 / 30.00 / 2.18
Total 45.70 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 - diffusiongemma-26b-a4b-it --ctx 32768

Live cheapest GPU configurations

ScenarioCheapest fitting rig (top 3)Total VRAMLowest $/hr730 h/moDeploy
INT4 @ 32K ctx1x RTX A5000 24GB24 GiB$0.16$116.80Deploy on RunPodCheck Vast.ai Verified
INT4 @ 32K ctx2x RTX A4000 16GB32 GiB$0.18$129.94Deploy on RunPodCheck Vast.ai Verified
INT4 @ 32K ctx1x RTX 3090 24GB24 GiB$0.22$160.60Deploy on RunPodCheck Vast.ai Verified
FP8 @ 32K ctx2x RTX A5000 24GB48 GiB$0.32$233.60Deploy on RunPodCheck Vast.ai Verified
FP8 @ 32K ctx1x RTX A6000 48GB48 GiB$0.33$240.90Deploy on RunPodCheck Vast.ai Verified
FP8 @ 32K ctx1x A40 48GB48 GiB$0.35$255.50Deploy on RunPodCheck Vast.ai Verified
FP16 @ 32K ctx4x RTX A4000 16GB64 GiB$0.36$259.88Deploy on RunPodCheck Vast.ai Verified
FP16 @ 32K ctx1x H200 NVL 143GB143 GiB$0.50$365.00Deploy on RunPodCheck Vast.ai Verified
FP16 @ 32K ctx1x MI300X 192GB192 GiB$0.50$365.00Deploy on RunPodCheck Vast.ai Verified

What over-provisioning costs you

Running diffusiongemma-26B-A4B-it production traffic at INT4 / 32K context on the cheapest fitting rig (1x RTX A5000 24GB) bills $116.80 per month (730 h). Defaulting to full FP16 forces a larger rig — 4x RTX A4000 16GB at $259.88/mo. Paying $259.88 instead of $116.80 every single month is the price of skipping 4-bit AWQ quantization; if your quality budget allows INT4, that gap is pure waste.