Llama 3.3 70B on H100 SXM: VRAM, speed and fit
Llama 3.3 70B at 8-bit runs on the H100 SXM with 16K of context at about 30 tokens a second.
Text generation · Chat · Ollama / LM Studio
Runs comfortably · on H100 SXM · 8-bit (Q8_0) · Ollama / LM Studio · Chat
- GPU memory
- 75.8 GB
- of 80.0 GB
- Context
- 16K
- auto
- Speed
- 30 tok/s
- Fast
- First reply
- 1.0 s
- 2K prompt
Where the memory goes
- Model
- 69.8 GB
- Context
- 5.0 GB
- Overhead
- 967 MB
- OS
- 0.0 GB
- Free
- 4.2 GB
- Memory
- 75.8 GB of 80.0 GB
- Context
- 16K tokens · auto
- Speed
- 30 tok/s · fast
- First reply
- 1.0 s for a 2K prompt
- Running cost
- $11/mo at home · $122/mo on a cloud 4× RTX A4500
Validation: Validated
| Check | Target | Result | Status |
|---|---|---|---|
| Fits in GPU memory | 80.0 GB usable | 75.8 GB needed | Pass |
| Headroom | 5% free | 4.2 GB free (5%) | Pass |
| Context for chat | 16K or more | 16K | Pass |
| Writing speed | 15 tok/s or more | 30 tok/s | Pass |
| First reply | under 3 s, 2K prompt | 1.0 s | Pass |
Targets: a reply you can read along with, a first reply the use case tolerates, and 5% of memory left free. Calculated from published specs, not benchmarked.
The setup
- Model
- Llama 3.3 70B
- Parameters
- 70.5B
- Precision
- 8-bit (Q8_0)
- Context
- 16K, auto
- Chats at once
- 1
- Use
- Chat
- Runs in
- Ollama / LM Studio
- Hardware
- H100 SXM
- GPU can use
- 80.0 GB of 80.0 GB
Worth trying
- 8-bit cache: Room for 28K context
Running cost
- At home
- $11/mo
- 500 W at the wall
- Renting instead
- $122/mo
- 4× RTX A4500 at $1.00/h
4 h a day, power at $0.18 per kWh, cloud at RunPod on-demand prices as of Nov 21, 2026.
How to run it
- Ollama
ollama run llama3.3:70b- llama.cpp
llama-server -hf unsloth/Llama-3.3-70B-Instruct-GGUF- vLLM
vllm serve meta-llama/Llama-3.3-70B-Instruct- MLX (Mac)
mlx_lm.chat --model mlx-community/Llama-3.3-70B-Instruct-4bit
Llama 3.3 70B on similar machines
- 2× RTX PRO 6000 BlackwellRuns
- 4× RTX PRO 6000 BlackwellRuns
- 8× RTX PRO 6000 BlackwellRuns
- A100 80 GB SXMRuns
- 4× H200 NVLRuns
- 8× H200 NVLRuns
All machines: Llama 3.3 70B VRAM requirements. Everything that runs here: what can the H100 SXM run?
Other models that run on H100 SXM
Questions
Can Llama 3.3 70B run on H100 SXM?
Llama 3.3 70B at 8-bit runs on the H100 SXM with 16K of context at about 30 tokens a second.
Report VR-153JYUT, calculated Nov 22, 2026 from published specs, not benchmarked.