text model · Yi · Windows
Yi Can I run Yi 1.5 34B on 32GB RAM Laptop (CPU/iGPU only)?
Yes. Yi 1.5 34B runs on 32GB RAM Laptop (CPU/iGPU only) at Q4_K_M (~21.4 GB of ~28 GB usable).
Runs at Q4_K_M using ~21.4 GB of ~28 GB usable.
- Q4_K_M needed
- ~21.4 GB
- Usable on device
- ~28 GB
- Device memory
- 32 GB
- Best quant
- Q4_K_M
Run it
Pick your tool. All three load the same Q4_K_M weights.
llama-cli -hf bartowski/Yi-1.5-34B-Chat-GGUF:Q4_K_M lms get bartowski/Yi-1.5-34B-Chat-GGUF AMD GPUs run via Vulkan/ROCm at roughly half CUDA throughput. NVIDIA is the smooth path on Windows.
How to run it
On Windows use LM Studio (Best GUI on Windows, auto-detects CUDA/Vulkan backends.). AMD GPUs run via Vulkan/ROCm at roughly half CUDA throughput. NVIDIA is the smooth path on Windows.
- Parameters
- 34B
- Q4_K_M size
- 19.24 GB
- Q8_0 size
- 34.03 GB
- Context
- 32k
- Memory
- 32 GB ram
- Usable for weights
- ~28 GB
- Best runtime
- Ollama (llama.cpp backend)
You could also run
Run Yi 1.5 34B on other hardware
FAQ
Can 32GB RAM Laptop (CPU/iGPU only) run Yi 1.5 34B?
Yes. Yi 1.5 34B runs on 32GB RAM Laptop (CPU/iGPU only) at Q4_K_M (~21.4 GB of ~28 GB usable).
How much memory does Yi 1.5 34B need?
32GB RAM Laptop (CPU/iGPU only) has room to spare. At Q4_K_M the weights are ~19.24 GB; with KV cache and runtime overhead, budget ~21.4 GB at a 4k context.
What is the best tool to run Yi 1.5 34B 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.
Sources
Memory figures are estimates. See methodology.