GLM 4.5 Air on RTX PRO 5000 Blackwell 48 GB: VRAM, speed and fit
GLM 4.5 Air at 2-bit runs on the RTX PRO 5000 Blackwell 48 GB with 32K of context at about 115 tokens a second.
Text generation · Chat · Ollama / LM Studio
Runs comfortably · on RTX PRO 5000 Blackwell 48 GB · 2-bit (Q2_K) · Ollama / LM Studio · Chat
- GPU memory
- 45.2 GB
- of 48.0 GB
- Context
- 32K
- auto
- Speed
- 115 tok/s
- 65 when full
- First reply
- 1.5 s
- 2K prompt
Where the memory goes
- Model
- 38.6 GB
- Context
- 5.8 GB
- Overhead
- 885 MB
- OS
- 0.0 GB
- Free
- 2.8 GB
- Memory
- 45.2 GB of 48.0 GB
- Context
- 32K tokens · auto
- Speed
- 115 tok/s · 65 when full
- First reply
- 1.5 s for a 2K prompt
- Running cost
- $5.69/mo at home · $66/mo on a cloud 2× RTX A5000
Validation: Validated
| Check | Target | Result | Status |
|---|---|---|---|
| Fits in GPU memory | 48.0 GB usable | 45.2 GB needed | Pass |
| Headroom | 5% free | 2.8 GB free (6%) | Pass |
| Context for chat | 16K or more | 32K | Pass |
| Writing speed | 15 tok/s or more | 115 tok/s | Pass |
| First reply | under 3 s, 2K prompt | 1.5 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 Air
- Parameters
- 110B, 15B active
- Precision
- 2-bit (Q2_K)
- Context
- 32K, auto
- Chats at once
- 1
- Use
- Chat
- Runs in
- Ollama / LM Studio
- Hardware
- RTX PRO 5000 Blackwell 48 GB
- GPU can use
- 48.0 GB of 48.0 GB
Worth trying
- 8-bit cache: Room for 64K context
Running cost
- At home
- $5.69/mo
- 260 W at the wall
- Renting instead
- $66/mo
- 2× RTX A5000 at $0.54/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-4.5-Air-GGUF- vLLM
vllm serve zai-org/GLM-4.5-Air- MLX (Mac)
mlx_lm.chat --model mlx-community/GLM-4.5-Air-4bit- Model card
- huggingface.co/zai-org/GLM-4.5-Air
GLM 4.5 Air on similar machines
- Radeon AI PRO R9700Too big
- RTX 5090Too big
- 2× RTX 3090Runs
- 2× RTX 4090Runs
- RTX 6000 AdaRuns
- L40SRuns
- 2× RTX 5090Runs
- 4× RTX 3090Runs
All machines: GLM 4.5 Air VRAM requirements. Everything that runs here: what can the RTX PRO 5000 Blackwell 48 GB run?
Other models that run on RTX PRO 5000 Blackwell 48 GB
Questions
Can GLM 4.5 Air run on RTX PRO 5000 Blackwell 48 GB?
GLM 4.5 Air at 2-bit runs on the RTX PRO 5000 Blackwell 48 GB with 32K of context at about 115 tokens a second.
Report VR-0Q19ENB, calculated Nov 22, 2026 from published specs, not benchmarked.