text model · GLM · Windows
Can I run GLM-4.5-Air on AMD Ryzen AI Halo (128GB)?
Yes. GLM-4.5-Air runs on AMD Ryzen AI Halo (128GB) at Q4_K_M (~71.8 GB of ~96 GB usable).
Runs at Q4_K_M using ~71.8 GB of ~96 GB usable.
That figure is at a 4k context and moves about ±15% as context length changes. AMD Ryzen AI Halo (128GB) leaves ~24.2 GB of headroom.
- Q4_K_M needed
- ~71.8 GB
- Usable on device
- ~96 GB
- Device memory
- 128 GB
- Best quant
- Q4_K_M
Which quant fits
Run it
Pick your tool. All 2 load the same Q4_K_M weights.
llama-cli -hf bartowski/zai-org_GLM-4.5-Air-GGUF:Q4_K_M lms get bartowski/zai-org_GLM-4.5-Air-GGUF How to run it
On Windows use LM Studio (Best GUI on Windows, auto-detects CUDA/Vulkan backends.).
- Parameters
- 106B (MoE, 12B active)
- Q4_K_M size
- 68.45 GB
- Q8_0 size
- 109.39 GB
- Context
- 128k
- Memory
- 128 GB unified
- Usable for weights
- ~96 GB
- Power draw
- ~120 W
- Best runtime
- llama.cpp (Vulkan/ROCm) / LM Studio
You could also run
Run GLM-4.5-Air on other hardware
FAQ
Can AMD Ryzen AI Halo (128GB) run GLM-4.5-Air?
Yes. GLM-4.5-Air runs on AMD Ryzen AI Halo (128GB) at Q4_K_M (~71.8 GB of ~96 GB usable).
How much memory does GLM-4.5-Air need?
AMD Ryzen AI Halo (128GB) has room to spare. At Q4_K_M the weights are ~68.45 GB; with KV cache and runtime overhead, budget ~71.8 GB at a 4k context. It is a Mixture-of-Experts model (106B total / 12B active), so all experts must stay in memory; memory tracks total params, not active params.
What is the best tool to run GLM-4.5-Air on Windows?
LM Studio for a simple setup; Ollama (CUDA) for the most speed. AMD GPUs run via Vulkan/ROCm at roughly half CUDA throughput. NVIDIA is the smooth path on Windows.
Embed this
A live badge for your model card or README, updated as the data is. [](https://localmodel.run/can-i-run/glm-4.5-air/amd-ryzen-ai-halo-128gb) Sources
Weights are measured from GGUF files; KV cache and overhead are computed, so totals can vary ~15% with context and runtime. Any tok/s is a bandwidth estimate. See methodology.