GMKtec EVO-X2 (128GB unified)
The $/GB winner: runs 70B-class and quantized big-MoE (V4 Flash tier) that no consumer GPU fits
Listed RTX 5080 rates (16 GB VRAM) from tracked provider APIs, sorted per GPU-hour. Source configurations may contain several GPUs or different editions. Availability is not checked; confirm the configuration and total charge with the provider.
Quotes refreshed 2026-11-22| Provider | Tier | $/hr per GPU | Source configuration | Instance charge | Availability | |
|---|---|---|---|---|---|---|
| RunPod | community | $0.39 | Source GPU SKU · NVIDIA GeForce RTX 5080 | Instance charge not supplied | Availability not checked | Check provider |
| RunPod | secure | $0.59 | Source GPU SKU · NVIDIA GeForce RTX 5080 | Instance charge not supplied | Availability not checked | Check provider |
Models from our tracked open-weight set that fit in 16 GB, with KV-cache headroom included. Bigger models need multi-GPU nodes (math in the calculator).
| Model | Params | Fits at | VRAM needed | Cheapest API $/1M out |
|---|---|---|---|---|
| IBM Granite 4.1 8B | 8.8B | FP8 | 13 GB | compare → |
| Llama 3.1 8B | 8B | FP8 | 11 GB | compare → |
| Llama 3.2 3B | 3.2B | FP8 | 5 GB | compare → |
| GPT-OSS 20B | 21B | INT4 | 15 GB | compare → |
| Gemma 3 12B | 12B | INT4 | 9 GB | compare → |
| Phi-4 | 14.7B | INT4 | 11 GB | compare → |
Compare local hardware or estimate rental costs in the calculator.
The $/GB winner: runs 70B-class and quantized big-MoE (V4 Flash tier) that no consumer GPU fits
Bandwidth-per-dollar king for the A3B-MoE and 27-32B dense workhorses
The startup standard: only sub-$10K single card that runs 70B+ comfortably
As an Amazon Associate we earn from qualifying purchases · hardware links may be referral links · picks are editorial, not paid · disclosure
The lowest listed rate in our tracked snapshot is $0.39/GPU-hour (community, RunPod), observed 2026-11-22. Source configuration: Source GPU SKU · NVIDIA GeForce RTX 5080. Instance charge not supplied. Availability not checked. This is a normalized comparison, not a provider-wide minimum or a confirmed bookable offer.
With 16 GB of VRAM, a single RTX 5080 fits models up to roughly 11B parameters at FP8 or 22B at INT4 quantization, including KV-cache headroom.
Lowest tracked listed RTX 5080 rate: $0.39/GPU-hour, RunPod (community), Source GPU SKU · NVIDIA GeForce RTX 5080. Instance charge not supplied. Availability not checked. Observed 2026-11-22 (llmhosting.ai). Provider data terms apply; a link back does not grant redistribution rights.