← Back to all offerings

H20

141 GB VRAM1 providers1 offerings1 regions

The H20 is a cloud GPU with 141 GB of memory. It is currently available from 1 provider starting at $1.04/hr, with a market median of $1.04/hr across 1 offering.

$1.04/hr
Cheapest
on AutoDL
$1.04/hr
Median
across 1 offerings
$1.04/hr
Most expensive
0.0%
90-day trend

Hardware specifications

Architecture
Hopper
VRAM
141 GB
Memory type
HBM3

Same across all providers.

Market comparison

$1.04/hr
Our median / hr
$3.79/hr
gpus.io median / hr
1
Our providers
2
gpus.io providers

View source on gpus.io

Offerings

All ×N×1×2×4×8In stock only · Partners only

No offerings found

Try clearing the spot filter or check back later.

LLMs that fit

ModelParams16-bit8-bit4-bit
Kimi K2.5
Moonshot AI
1T 32B activeNot releasedNot released7× · 13.2% spare
GLM-5.2
Z.ai
753BNeeds >8 GPUsNeeds >8 GPUsBarely fits on 5×
DeepSeek R1
DeepSeek
671B 37B activeNot releasedBarely fits on 8×5× · 127.8 GB free
DeepSeek V4 Flash
DeepSeek
284BNot releasedNot released2× · 51.6 GB free
Solar Open2 250B
Upstage
250B 15B active6× · 14.8% spareBarely fits on 3×2× · 51.6 GB free
Qwen3 235B-A22B
Alibaba
235B 22B activeBarely fits on 5×Barely fits on 3×2× · 64.8 GB free
Laguna-S 2.1
Poolside
118B 8B active3× · 84.6 GB free2× · 96 GB free1× · 33 GB free
gpt-oss-120b
OpenAI
117B 5.1B activeNot releasedNot released1× · 47.4 GB free
Llama 3.1 70B
Meta
70B2× · 114 GB free1× · 49.2 GB free1× · 87 GB free
Qwen3.6 35B-A3B
Alibaba
35B 3B active1× · 37.8 GB free1× · 84.6 GB free1× · 107.4 GB free
Qwen3 32B
Alibaba
32.8B1× · 46.2 GB free1× · 89.4 GB free1× · 111 GB free
Qwen2.5 14B
Alibaba
14B1× · 105.6 GB free1× · 121.7 GB free1× · 129.6 GB free

Estimates: model weights plus 20% for KV cache and runtime overhead, at short context lengths. Long contexts and large batches need more. Rows marked “tight” hold the weights but not that full margin. A ×N figure is the total VRAM across N of these GPUs and makes no claim about interconnect throughput.

Similar GPUs

Frequently asked questions

How much does the H20 cost per hour?

The cheapest H20 offering starts at $1.04/hr, and the market median is $1.04/hr.

Which cloud providers offer the H20?

No providers currently list the H20 in our catalog.

How much VRAM does the H20 have?

The H20 has 141 GB of VRAM.

What LLMs can run on the H20?

With 141 GB of VRAM, the H20 can run 15 of our tracked models in 4-bit quantization, including Kimi K2.5, GLM-5.2, DeepSeek R1. 10 models fit in 16-bit precision.

What's the biggest LLM I can run on multiple H20s?

With 8× H20 (1128 GB total), the largest tracked model that fits in 16-bit is Solar Open2 250B (250B params), which needs 6× GPUs.