GLM 4.5 on 4× RTX PRO 6000 Blackwell: VRAM, speed and fit
GLM 4.5 at 8-bit runs on the 4× RTX PRO 6000 Blackwell with 20K of context at about 28 tokens a second.
Text generation · Chat · Ollama / LM Studio
Runs comfortably · on 4× RTX PRO 6000 Blackwell · 8-bit (Q8_0) · Ollama / LM Studio · Chat
- GPU memory
- 365 GB
- of 384 GB
- Context
- 20K
- auto
- Speed
- 28 tok/s
- Fast
- First reply
- 0.6 s
- 2K prompt
Where the memory goes
- Model
- 355 GB
- Context
- 7.2 GB
- Overhead
- 2.9 GB
- OS
- 0.0 GB
- Free
- 19.3 GB
- Memory
- 365 GB of 384 GB
- Context
- 20K tokens · auto
- Speed
- 28 tok/s · fast
- First reply
- 0.6 s for a 2K prompt
- Running cost
- $33/mo at home · $574/mo on a cloud 8× A40
Validation: Validated
| Check | Target | Result | Status |
|---|---|---|---|
| Fits in GPU memory | 384 GB usable | 365 GB needed | Pass |
| Headroom | 5% free | 19.3 GB free (5%) | Pass |
| Context for chat | 16K or more | 20K | Pass |
| Writing speed | 15 tok/s or more | 28 tok/s | Pass |
| First reply | under 3 s, 2K prompt | 0.6 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 4.5
- Parameters
- 358B, 35.6B active
- Precision
- 8-bit (Q8_0)
- Context
- 20K, auto
- Chats at once
- 1
- Use
- Chat
- Runs in
- Ollama / LM Studio
- Hardware
- 4× RTX PRO 6000 Blackwell
- GPU can use
- 384 GB of 384 GB
Worth trying
- 8-bit cache: Room for 36K context
Running cost
- At home
- $33/mo
- 1520 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 22, 2026.
How to run it
- llama.cpp
llama-server -hf unsloth/GLM-4.5-GGUF- vLLM
vllm serve zai-org/GLM-4.5- MLX (Mac)
mlx_lm.chat --model mlx-community/GLM-4.5-4bit- Model card
- huggingface.co/zai-org/GLM-4.5
GLM 4.5 on similar machines
- DGX SparkJust misses
- Dual DGX SparkRuns
- DGX Station GB300Runs
- 2× RTX PRO 6000 BlackwellRuns
- 8× RTX PRO 6000 BlackwellRuns
- A100 80 GB SXMToo big
- H100 SXMToo big
- 4× H200 NVLRuns
All machines: GLM 4.5 VRAM requirements. Everything that runs here: what can the 4× RTX PRO 6000 Blackwell run?
Other models that run on 4× RTX PRO 6000 Blackwell
Questions
Can GLM 4.5 run on 4× RTX PRO 6000 Blackwell?
GLM 4.5 at 8-bit runs on the 4× RTX PRO 6000 Blackwell with 20K of context at about 28 tokens a second.
Report VR-0LBSZI4, calculated Nov 22, 2026 from published specs, not benchmarked.