A100 SXM 40GB cloud pricing, November 2026

Listed A100 SXM 40GB rates (40 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
Lowest tracked listed rate: $0.867/GPU-hour (spot) at Verda. 1× GPU · A100 SXM4 40GB · $0.867/instance-hour · Availability not checked
Provider Tier $/hr per GPU Source configuration Instance charge Availability
Verda spot $0.867 1× GPU · A100 SXM4 40GB $0.867/instance-hour Availability not checked
RunPod community $1.00 Source GPU SKU · NVIDIA A100-SXM4-40GB Instance charge not supplied Availability not checked Check provider
Verda on-demand $1.732 8× GPU · A100 SXM4 40GB $13.86/instance-hour Availability not checked

What fits on a single A100 SXM 40GB

Models from our tracked open-weight set that fit in 40 GB, with KV-cache headroom included. Bigger models need multi-GPU nodes (math in the calculator).

ModelParamsFits atVRAM neededCheapest API $/1M out
Qwen3.8 27B 27.8B FP8 39 GB compare →
Qwen3.6 27B 27.8B FP8 39 GB compare →
Qwen3.5 27B 27.8B FP8 39 GB compare →
Mistral Small 3.1 24B FP8 33 GB
IBM Granite 4.1 8B 8.8B FP8 13 GB compare →
GPT-OSS 20B 21B FP8 29 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 →
GLM-4.7 Flash 31B INT4 22 GB compare →
Qwen3.6 35B A3B 36B INT4 25 GB compare →
Qwen3.5 35B A3B 36B INT4 25 GB compare →
Qwen3 32B 32.8B INT4 23 GB compare →
Qwen3 30B A3B 30.5B INT4 21 GB compare →
Nemotron 3 Nano 30B INT4 21 GB compare →
IBM Granite 4.1 30B 30B INT4 21 GB
Mixtral 8x7B 46.7B INT4 33 GB compare →
DeepSeek R1 Distill Qwen 32B 32.8B INT4 23 GB compare →

Can't buy a A100 SXM 40GB? The desk-side alternatives

Compare local hardware or estimate rental costs in the calculator.

GMKtec EVO-X2 (128GB unified)

Ryzen AI Max+ 395 · 128GB unified memory

The $/GB winner: runs 70B-class and quantized big-MoE (V4 Flash tier) that no consumer GPU fits

NVIDIA RTX 5090 (32GB)

32GB GDDR7 · ~1.8TB/s bandwidth

Bandwidth-per-dollar king for the A3B-MoE and 27-32B dense workhorses

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 A100 SXM 40GB?

The lowest listed rate in our tracked snapshot is $0.867/GPU-hour (spot, Verda), observed 2026-11-22. Source configuration: 1× GPU · A100 SXM4 40GB. $0.867/instance-hour. Availability not checked. This is a normalized comparison, not a provider-wide minimum or a confirmed bookable offer.

What can you run on a A100 SXM 40GB?

With 40 GB of VRAM, a single A100 SXM 40GB fits models up to roughly 28B parameters at FP8 or 57B at INT4 quantization, including KV-cache headroom.

Cite this snapshot

Lowest tracked listed A100 SXM 40GB rate: $0.867/GPU-hour, Verda (spot), 1× GPU · A100 SXM4 40GB. $0.867/instance-hour. Availability not checked. Observed 2026-11-22 (llmhosting.ai). Provider data terms apply; a link back does not grant redistribution rights.

Daily A100 SXM 40GB price history →