PRO 6000 MIG 48GB
The PRO 6000 MIG 48GB is a cloud GPU with 48 GB of memory. It is currently available from 1 provider starting at $1.00/hr, with a market median of $3.00/hr across 4 offerings.
Best deal
Hardware specifications
- Architecture
- Blackwell
- VRAM
- 48 GB
Same across all providers.
Market comparison
Offerings
| Provider | Cloud | Count | vCPU | RAM | Region | Per GPU hr | SPOT | Total/hr | |
|---|---|---|---|---|---|---|---|---|---|
HardwareHQ 0.0% 30dReferral link | — | ×1 | — | — | — | $1.00/hr | — | $1.00/hr | Launch ↗ |
HardwareHQ 0.0% 30dReferral link | — | ×2 | — | — | — | $1.00/hr | — | $2.00/hr | Launch ↗ |
HardwareHQ 0.0% 30dReferral link | — | ×4 | — | — | — | $1.00/hr | — | $4.00/hr | Launch ↗ |
HardwareHQ 0.0% 30dReferral link | — | ×8 | — | — | — | $1.00/hr | — | $8.00/hr | Launch ↗ |
LLMs that fit
| Model | Params | 16-bit | 8-bit | 4-bit |
|---|---|---|---|---|
DeepSeek V4 Flash DeepSeek | 284B | Not released | Not released | Barely fits on 5× |
Solar Open2 250B Upstage | 250B 15B active | Needs >8 GPUs | Needs >8 GPUs | Barely fits on 5× |
Qwen3 235B-A22B Alibaba | 235B 22B active | Needs >8 GPUs | Barely fits on 8× | Barely fits on 5× |
Laguna-S 2.1 Poolside | 118B 8B active | Barely fits on 8× | Barely fits on 4× | 3× · 36 GB free |
gpt-oss-120b OpenAI | 117B 5.1B active | Not released | Not released | Barely fits on 2× |
Llama 3.1 70B Meta | 70B | Barely fits on 4× | Barely fits on 2× | 2× · 42 GB free |
Qwen3.6 35B-A3B Alibaba | 35B 3B active | 3× · 40.8 GB free | 2× · 39.6 GB free | 1× · 14.4 GB free |
Qwen3 32B Alibaba | 32.8B | Barely fits on 2× | 2× · 44.4 GB free | 1× · 18 GB free |
Qwen2.5 14B Alibaba | 14B | 1× · 12.6 GB free | 1× · 28.7 GB free | 1× · 36.6 GB free |
Llama 3.1 8B Meta | 8B | 1× · 27.1 GB free | 1× · 36.6 GB free | 1× · 41.3 GB free |
Mistral 7B Mistral AI | 7B | 1× · 29.8 GB free | 1× · 38 GB free | 1× · 42.1 GB free |
Qwen3 4B Alibaba | 4B | 1× · 36.4 GB free | 1× · 41.6 GB free | 1× · 44.3 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
See more GPUs like this in
Frequently asked questions
How much does the PRO 6000 MIG 48GB cost per hour?
The cheapest PRO 6000 MIG 48GB offering starts at $1.00/hr, and the market median is $3.00/hr.
Which cloud providers offer the PRO 6000 MIG 48GB?
We track PRO 6000 MIG 48GB offerings from HardwareHQ.
How much VRAM does the PRO 6000 MIG 48GB have?
The PRO 6000 MIG 48GB has 48 GB of VRAM.
What LLMs can run on the PRO 6000 MIG 48GB?
With 48 GB of VRAM, the PRO 6000 MIG 48GB can run 12 of our tracked models in 4-bit quantization, including DeepSeek V4 Flash, Solar Open2 250B, Qwen3 235B-A22B. 8 models fit in 16-bit precision.
What's the biggest LLM I can run on multiple PRO 6000 MIG 48GBs?
With 8× PRO 6000 MIG 48GB (384 GB total), the largest tracked model that fits in 16-bit is Qwen3.6 35B-A3B (35B params), which needs 3× GPUs.
Where is the PRO 6000 MIG 48GB cheapest?
The cheapest PRO 6000 MIG 48GB offering in our catalog is HardwareHQ at $1.00/hr per GPU-hour (×1).