GMKtec EVO-X2 (128GB unified)
The $/GB winner: runs 70B-class and quantized big-MoE (V4 Flash tier) that no consumer GPU fits
B200 cloud pricing, August 2026
Live B200 quotes (180 GB VRAM) across the providers we track, cheapest first. Marketplace prices are real asks from the Vast.ai order book; secure/on-demand tiers carry datacenter SLAs (what the tiers mean).
Quotes refreshed 2026-08-23
Price floor: $3.06/hr (spot) at
Verda.
| Provider | Tier | $/hr per GPU | Median $/hr | Live offers | |
|---|---|---|---|---|---|
| Verda | spot | $3.06 | - | - | |
| Vast.ai | marketplace | $3.99 | $7.25 | 18 | Rent |
| RunPod | community | $5.98 | - | - | Rent |
| Verda | on-demand | $6.11 | - | - | |
| RunPod | secure | $6.79 | - | - | Rent |
Need 8-128 of these? Get a cluster quote →, or
hand us the workload for a ranked deployment plan, free while in beta.
What fits on a single B200
Models from our tracked open-weight set that fit in 180 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 |
|---|---|---|---|---|
| GLM-4.7 Flash | 31B | FP8 | 43 GB | compare → |
| GLM-4.5 Air | 106B | FP8 | 146 GB | compare → |
| Qwen3.6 35B A3B | 36B | FP8 | 50 GB | compare → |
| Qwen3.6 27B | 27.8B | FP8 | 39 GB | compare → |
| Qwen3.5 35B A3B | 36B | FP8 | 50 GB | compare → |
| Qwen3.5 27B | 27.8B | FP8 | 39 GB | compare → |
| Qwen3 32B | 32.8B | FP8 | 46 GB | compare → |
| Qwen3 30B A3B | 30.5B | FP8 | 42 GB | compare → |
| Mistral Medium 3.5 | 128B | FP8 | 176 GB | compare → |
| Mistral Small 4 | 119.4B | FP8 | 165 GB | |
| Leanstral 1.5 | 119B | FP8 | 164 GB | |
| Mistral Small 3.1 | 24B | FP8 | 33 GB | |
| Nemotron 3 Super | 120B | FP8 | 165 GB | compare → |
| Nemotron 3 Nano | 30B | FP8 | 42 GB | compare → |
| IBM Granite 4.1 30B | 30B | FP8 | 42 GB | |
| IBM Granite 4.1 8B | 8.8B | FP8 | 13 GB | compare → |
| GPT-OSS 120B | 117B | FP8 | 161 GB | compare → |
| GPT-OSS 20B | 21B | FP8 | 29 GB | compare → |
| Llama 4 Scout | 109B | FP8 | 150 GB | compare → |
| Llama 3.3 70B | 70B | FP8 | 97 GB | compare → |
| Llama 3.1 8B | 8B | FP8 | 11 GB | compare → |
| Llama 3.2 3B | 3.2B | FP8 | 5 GB | compare → |
| Gemma 3 27B | 27B | FP8 | 38 GB | compare → |
| Gemma 3 12B | 12B | FP8 | 17 GB | compare → |
| Phi-4 | 14.7B | FP8 | 21 GB | compare → |
| Mixtral 8x7B | 46.7B | FP8 | 65 GB | compare → |
| DeepSeek R1 Distill Llama 70B | 70B | FP8 | 97 GB | compare → |
| DeepSeek R1 Distill Qwen 32B | 32.8B | FP8 | 46 GB | compare → |
| MiniMax M2.7 | 229B | INT4 | 158 GB | compare → |
| MiniMax M2.5 | 229B | INT4 | 158 GB | compare → |
| MiniMax M2.1 | 229B | INT4 | 158 GB | compare → |
| MiniMax M2 | 229B | INT4 | 158 GB | compare → |
| Qwen3 235B A22B | 235B | INT4 | 162 GB | compare → |
Can't buy a B200? The desk-side alternatives
B200 cards only ship in servers, but the "own your inference box" itch has real answers: run the economics in the calculator, then look at what this audience actually buys:
NVIDIA RTX 5090 (32GB)
Bandwidth-per-dollar king for the A3B-MoE and 27-32B dense workhorses
NVIDIA RTX PRO 6000 Blackwell (96GB)
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
FAQ
How much does it cost to rent a B200?
As of 2026-08-23, B200 rentals start at $3.06/hr (spot tier at Verda). Datacenter capacity with SLAs typically costs more than community or marketplace hardware.
What can you run on a B200?
With 180 GB of VRAM, a single B200 fits models up to roughly 128B parameters at FP8 or 257B at INT4 quantization, including KV-cache headroom.
Cite or embed today's floor
Live badge for a README. It updates itself with every daily refresh:
[](https://llmhosting.ai/gpus/b200)
Citation: B200 rental floor $3.06/hr (llmhosting.ai, 2026-08-23). Free to reuse with a link back.