NVIDIAHopper (Grace Hopper)

Best AI Models for NVIDIA GH200 Grace Hopper Superchip (144.0GB)

VRAM:144.0 GB HBM3e·Bandwidth:4900.0 GB/s·CUDA Cores:16,896·TDP:1000W

Grace Hopper superchip: 144 GB HBM3e GPU pool plus a large NVLink-coherent LPDDR5X extension. Server/cloud part, listed for comparison.

With 144 GB of memory, this is a high-end configuration for local AI. You can comfortably run most open-source LLMs including large 70B parameter models at good quantization levels, making it one of the best setups for serious local AI work.

At this memory tier, nearly every popular open-source model is within reach. You can run Llama 3 70B at Q4_K_M or even Q5_K_M quantization with room to spare, handle coding assistants like DeepSeek Coder 33B at high quality, and easily run any 7B–30B model at full or near-full precision. Context windows remain generous even with larger models, so multi-turn conversations and long-document processing work smoothly.

Runs Well

  • 70B models (Llama 3 70B, Qwen 72B) at Q4–Q5
  • 30B models at Q6–Q8 quality
  • 7B–14B models at full FP16 precision
  • Vision models (LLaVA, CogVLM) without compromise

Challenging

  • Mixture-of-experts models like Mixtral 8x22B at higher quants
  • 120B+ models still require lower quantizations

What LLMs Can NVIDIA GH200 Grace Hopper Superchip Run?

127 models · 9 good

Showing compatibility for NVIDIA GH200 Grace Hopper Superchip

LLM models compatible with NVIDIA GH200 Grace Hopper Superchip — ranked by performance
ModelVRAMGrade
GPT OSS 120B120.4B
Q4_K_M·43.8 t/s tok/s·131K ctx·GOOD FIT
72.7 GBA65
Q4_K_M·42.7 t/s tok/s·262K ctx·GOOD FIT
74.7 GBA67
Q4_K_M·37.4 t/s tok/s·66K ctx·GOOD FIT
85.1 GBA75
Q4_K_M·44.4 t/s tok/s·GOOD FIT
71.7 GBA65
Q4_K_M·37.4 t/s tok/s·66K ctx·GOOD FIT
85.1 GBA75
DeepSeek v2235.7B
Q3_K_M·27.1 t/s tok/s·164K ctx·GOOD FIT
117.7 GBA80
Q3_K_M·27.1 t/s tok/s·164K ctx·GOOD FIT
117.7 GBA80
GLM 4.5 Air110.5B
Q4_K_M·47.7 t/s tok/s·131K ctx·FAIR FIT
66.7 GBB61
IQ2_XXS·26.2 t/s tok/s·GOOD FIT
121.5 GBA73
Q4_K_M·43.5 t/s tok/s·GOOD FIT
73.3 GBA66
GLM 4.6V107.7B
Q4_K_M·49.0 t/s tok/s·131K ctx·FAIR FIT
65.1 GBB60
Q4_K_M·64.7 t/s tok/s·262K ctx·FAIR FIT
49.2 GBB49
Q4_K_M·68.4 t/s tok/s·131K ctx·FAIR FIT
46.6 GBB47
Q4_K_M·68.4 t/s tok/s·131K ctx·FAIR FIT
46.6 GBB47
Q4_K_M·71.4 t/s tok/s·33K ctx·FAIR FIT
44.6 GBB46
Q4_K_M·64.7 t/s tok/s·262K ctx·FAIR FIT
49.2 GBB49

NVIDIA GH200 Grace Hopper Superchip Specifications

Brand
NVIDIA
Architecture
Hopper (Grace Hopper)
Compute Capability
9.0 (CUDA SM version)
VRAM
144.0 GB HBM3e
Memory Bandwidth
4900.0 GB/s
CUDA Cores
16,896
Tensor Cores
528
FP16 Performance
989.50 TFLOPS
TDP
1000W
Release Date
2024-01-01

Get Started

Ollama (Recommended)

$curl -fsSL https://ollama.com/install.sh | sh
$ollama run llama3:8b

LM Studio

LM Studio

Download LM Studio, search for a model, and run it with one click.

GPUs to Consider Over NVIDIA GH200 Grace Hopper Superchip

Similar GPUs and upgrades with more VRAM or higher bandwidth for AI

Frequently Asked Questions

Can NVIDIA GH200 Grace Hopper Superchip run GPT OSS 120B?

Yes, the NVIDIA GH200 Grace Hopper Superchip with 144 GB can run GPT OSS 120B, NVIDIA Nemotron 3 Super 120B A12B BF16, WizardLM 2 8x22B, and 1423 other models. 2 models run at excellent quality, and 37 at good quality. Check the compatibility table above for the full list with VRAM usage and estimated speed.

Is NVIDIA GH200 Grace Hopper Superchip good for AI?

The NVIDIA GH200 Grace Hopper Superchip has 144 GB of HBM3e, making it excellent for running local AI models. It supports 39 models at good quality or better. With 4900.0 GB/s memory bandwidth, it delivers fast token generation speeds. This is an enthusiast-grade GPU that handles most popular open-source LLMs.

How many parameters can NVIDIA GH200 Grace Hopper Superchip handle?

With 144 GB, the NVIDIA GH200 Grace Hopper Superchip supports models from 3B to 70B+ parameters depending on quantization level. At Q4_K_M (the recommended sweet spot), you can fit roughly 240B parameters. This means 7B models at high quality (Q6/Q8) or 30B+ models at Q4.

What quantization should I use on NVIDIA GH200 Grace Hopper Superchip?

For the best balance of quality and speed on the NVIDIA GH200 Grace Hopper Superchip, start with Q4_K_M — it preserves ~85% of the original model quality while keeping VRAM usage reasonable. With 24+ GB, you have the headroom to run 7B models at Q5_K_M or even Q6_K for noticeably better output quality. For larger 30B models, Q4_K_M remains the sweet spot.

How fast is NVIDIA GH200 Grace Hopper Superchip for AI inference?

With 4900.0 GB/s memory bandwidth, the NVIDIA GH200 Grace Hopper Superchip achieves approximately 708 tokens/sec on a 7B model at Q4_K_M — that's very fast, well above conversational speed. A 14B model runs at ~354 tok/s. Token generation speed scales inversely with model size — smaller models are significantly faster.

tok/s = (4900 GB/s ÷ model GB) × efficiency

Smaller models = faster inference. Memory bandwidth is the main bottleneck for token generation speed.

Estimated speed on NVIDIA GH200 Grace Hopper Superchip

Real-world results typically within ±20%. Speed depends on quantization kernel, batch size, and software stack.

Learn more about tok/s estimation →

What's the best model for NVIDIA GH200 Grace Hopper Superchip?

The top-rated models for the NVIDIA GH200 Grace Hopper Superchip are GPT OSS 120B, NVIDIA Nemotron 3 Super 120B A12B BF16, WizardLM 2 8x22B. The best choice depends on your use case: coding assistants benefit from code-tuned models, while general chat works well with instruction-tuned models like Llama or Qwen.

What power supply and cooling does NVIDIA GH200 Grace Hopper Superchip need?

The NVIDIA GH200 Grace Hopper Superchip has a TDP of 1000 W. A good rule of thumb is to provide at least double the GPU's TDP to cover the rest of the system — that means a 1600 W PSU or larger. At this power level, a high-airflow case matters: aim for at least two front intake fans and one rear exhaust, with tidy cabling so hot air isn't trapped around the card. LLM inference sustains full GPU load continuously — longer and more consistently than most gaming workloads — so also make sure your CPU cooler can keep up under combined load.

Anything to watch out for with NVIDIA GH200 Grace Hopper Superchip?

Grace Hopper superchip: 144 GB HBM3e GPU pool plus a large NVLink-coherent LPDDR5X extension. Server/cloud part, listed for comparison.