Question 1

What AI models can run on B100?

Accepted Answer

The B100 (192 GB VRAM) can run models including MediPhi-Instruct, Llama-3.2-3B-Instruct-QLORA_INT4_EO8, Llama-3.2-1B-Instruct-QLORA_INT4_EO8, Llama-3.2-1B-Instruct-SpinQuant_INT4_EO8, Llama-2-13b and more — 10 compatible models indexed so far. Compatible models are determined by whether the model's memory footprint fits within the GPU's 192 GB VRAM, potentially using quantization (Q8, Q6, or Q4) to reduce memory usage.

Question 2

What is the cheapest cloud option for B100?

Accepted Answer

We don't currently have cloud pricing data for the B100. This GPU may not be widely available from major cloud providers, or pricing data hasn't been synced yet.

Question 3

Is B100 good for fine-tuning?

Accepted Answer

Yes, the B100 is excellent for fine-tuning. With 192 GB of VRAM, it can handle full fine-tuning of models up to ~30B parameters and LoRA/QLoRA fine-tuning of much larger models. It's a top-tier choice for training workloads.

Question 4

How much VRAM does B100 have?

Accepted Answer

The B100 has 192 GB of VRAM (HBM3e). It also offers 8000 GB/s memory bandwidth, 1,750 TFLOPS of FP16 compute, FP8 support for efficient inference.

Question 5

What quantization formats work on B100?

Accepted Answer

The B100 supports the following quantization formats: FP16 (full precision), FP8, Q8 (8-bit), Q6 (6-bit), Q4 (4-bit). FP16 works for models up to ~40B parameters. FP8 halves memory vs FP16 with minimal quality loss. Q4 quantization lets models up to ~652B parameters (by VRAM estimate) fit on the B100.

B100

Specifications

Cloud pricing

Compatible models

Compare this GPU

Frequently asked questions

VRAM	192 GB
Memory type	HBM3e
Bandwidth	8000 GB/s
FP16 TFLOPS	1,750
FP8 support	Yes