text model · SmolLM2 · Windows
Can I run SmolLM2 360M on Nvidia GeForce RTX 3090 (24GB)?
Yes. SmolLM2 360M runs on Nvidia GeForce RTX 3090 (24GB) at Q4_K_M (~1.2 GB of ~23 GB usable).
Runs at Q4_K_M using ~1.2 GB of ~23 GB usable. You have room for FP16 for higher quality.
- Q4_K_M needed
- ~1.2 GB
- Usable on device
- ~23 GB
- Device memory
- 24 GB
- Best quant
- Q4_K_M
Run it
Pick your tool. All three load the same Q4_K_M weights.
ollama run smollm2:360m llama-cli -hf bartowski/SmolLM2-360M-Instruct-GGUF:Q4_K_M lms get bartowski/SmolLM2-360M-Instruct-GGUF AMD GPUs run via Vulkan/ROCm at roughly half CUDA throughput. NVIDIA is the smooth path on Windows.
- Parameters
- 0.362B
- Q4_K_M size
- 0.271 GB
- Q8_0 size
- 0.386 GB
- Context
- 2k
- Ollama tag
- smollm2:360m
- Memory
- 24 GB vram
- Usable for weights
- ~23 GB
- Best runtime
- vLLM (Linux) / Ollama (CUDA)
You could also run
Run SmolLM2 360M on other hardware
FAQ
Can Nvidia GeForce RTX 3090 (24GB) run SmolLM2 360M?
Yes. SmolLM2 360M runs on Nvidia GeForce RTX 3090 (24GB) at Q4_K_M (~1.2 GB of ~23 GB usable).
How much memory does SmolLM2 360M need?
Nvidia GeForce RTX 3090 (24GB) has room to spare. At Q4_K_M the weights are ~0.271 GB; with KV cache and runtime overhead, budget ~1.2 GB at a 4k context.
What is the best tool to run SmolLM2 360M 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.