GLM-5.3 Flash on 8× H200 NVL: VRAM, speed and fit
GLM-5.3 Flash at FP8 runs on the 8× H200 NVL with 1M of context at about 122 tokens a second.
Text generation · Chat · Ollama / LM Studio
Runs comfortably · on 8× H200 NVL · FP8 · Ollama / LM Studio · Chat
- GPU memory
- 324 GB
- of 1,128 GB
- Context
- 1M
- auto
- Speed
- 122 tok/s
- 82 when full
- First reply
- 0.1 s
- 2K prompt
Where the memory goes
- Model
- 306 GB
- Context
- 12.5 GB
- Overhead
- 5.5 GB
- OS
- 0.0 GB
- Free
- 804 GB
- Memory
- 324 GB of 1,128 GB
- Context
- 1M tokens · auto
- Speed
- 122 tok/s · 82 when full
- First reply
- 0.1 s for a 2K prompt
- Running cost
- $65/mo at home · $574/mo on a cloud 8× A40
Validation: Validated
| Check | Target | Result | Status |
|---|---|---|---|
| Fits in GPU memory | 1,128 GB usable | 324 GB needed | Pass |
| Headroom | 5% free | 804 GB free (71%) | Pass |
| Context for chat | 16K or more | 1M | Pass |
| Writing speed | 15 tok/s or more | 122 tok/s | Pass |
| First reply | under 3 s, 2K prompt | 0.1 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
- GLM-5.3 Flash
- Parameters
- 321B, 18B active
- Precision
- FP8
- Context
- 1M, auto
- Chats at once
- 1
- Use
- Chat
- Runs in
- Ollama / LM Studio
- Hardware
- 8× H200 NVL
- GPU can use
- 1,128 GB of 1,128 GB
Running cost
- At home
- $65/mo
- 2960 W at the wall
- Renting instead
- $574/mo
- 8× A40 at $4.72/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
- llama.cpp
llama-server -hf unsloth/GLM-5.3-Flash-GGUF- vLLM
vllm serve zai-org/GLM-5.3-Flash- MLX (Mac)
mlx_lm.chat --model mlx-community/GLM-5.3-Flash-4bit- Model card
- huggingface.co/zai-org/GLM-5.3-Flash
GLM-5.3 Flash on similar machines
- 8× RTX PRO 6000 BlackwellRuns
- A100 80 GB SXMToo big
- H100 SXMToo big
- 4× H200 NVLRuns
All machines: GLM-5.3 Flash VRAM requirements. Everything that runs here: what can the 8× H200 NVL run?
Other models that run on 8× H200 NVL
Questions
Can GLM-5.3 Flash run on 8× H200 NVL?
GLM-5.3 Flash at FP8 runs on the 8× H200 NVL with 1M of context at about 122 tokens a second.
Report VR-1JBI0W2, calculated Nov 22, 2026 from published specs, not benchmarked.