NVIDIA H200 141GB: Specs & Local-AI Compatibility
141GB HBM3e — headroom for very large single-card serving.
Specs
- Memory
- 141 GB
- Memory type
- HBM3e
- Bandwidth
- 4,800 GB/s
- Approx FP16
- 990 TFLOPS
- Architecture
- Hopper
- Process
- TSMC 4N
- Power
- 700 W
- Launch
- 2024
Models this chip can run
Open models graded for a single NVIDIA H200 141GB, best fit first.
- Qwen2.5 72BQwen · ~72B · 128K ctx · Qwen License
Fits at Q8_0 (~78GB) with ~46.1GB headroom — about 1 concurrent instance.
Q8_0 · ~78GBRuns well - Llama 3.1 70BLlama · ~70B · 128K ctx · Llama Community License
Fits at Q8_0 (~75GB) with ~49.1GB headroom — about 1 concurrent instance.
Q8_0 · ~75GBRuns well - Llama 3.3 70BLlama · ~70B · 128K ctx · Llama Community License
Fits at Q8_0 (~75GB) with ~49.1GB headroom — about 1 concurrent instance.
Q8_0 · ~75GBRuns well - DeepSeek-R1 Distill Llama 70BDeepSeek · ~70B · 128K ctx · MIT
Fits at Q8_0 (~75GB) with ~49.1GB headroom — about 1 concurrent instance.
Q8_0 · ~75GBRuns well - Mixtral 8x7B (MoE)Mistral · ~47B · 32K ctx · Apache-2.0
Fits at FP16 (~90GB) with ~34.1GB headroom — about 1 concurrent instance.
FP16 · ~90GBRuns well - CodeLlama 34BCodeLlama · ~34B · 16K ctx · Llama Community License
Fits at FP16 (~68GB) with ~56.1GB headroom — about 1 concurrent instance.
FP16 · ~68GBRuns well - Qwen2.5 32BQwen · ~32B · 128K ctx · Apache-2.0
Fits at FP16 (~64GB) with ~60.1GB headroom — about 1 concurrent instance.
FP16 · ~64GBRuns well - Qwen3 32BQwen · ~32B · 128K ctx · Apache-2.0
Fits at FP16 (~64GB) with ~60.1GB headroom — about 1 concurrent instance.
FP16 · ~64GBRuns well
Devices built on this chip
Build a private AI Business OS on NVIDIA H200 141GB
Run your own AI agents on hardware you control — private by design, no per-seat data leaving your premises. BrainOutput helps you pick the right machine and turn it into a working AI Business OS.
Explore the AI Business OS