SmolLM 360M Instruct — Hardware Requirements & GPU Compatibility
Chat
SmolLM 360M Instruct is a 362M-parameter open language model from Hugging Face. It supports a context window of up to 2,048 tokens. At BF16 it needs about 1.11 GB of VRAM — see which GPUs and Macs can run it below.
7.8K downloads
84 likesSpecifications
- Publisher
- Hugging Face
- Parameters
- 362M
- Architecture
- LlamaForCausalLM
- Context Length
- 2,048 tokens
- Vocabulary Size
- 49,152
- Release Date
- 2024-08-18
- License
- Apache 2.0
Get Started
HuggingFace
How Much VRAM Does SmolLM 360M Instruct Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| BF16 | 16.00 | 1.1 GB | — | 0.72 GB | Brain floating point 16 — preferred for training |
Which GPUs Can Run SmolLM 360M Instruct?
BF16 · 1.1 GBSmolLM 360M Instruct (BF16) requires 1.1 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 2+ GB is recommended. 35 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti.
Runs great
— Plenty of headroomWhich Devices Can Run SmolLM 360M Instruct?
BF16 · 1.1 GB33 devices with unified memory can run SmolLM 360M Instruct, including NVIDIA DGX H100, NVIDIA DGX A100 640GB.
Runs great
— Plenty of headroomRelated Models
Frequently Asked Questions
- How much VRAM does SmolLM 360M Instruct need?
SmolLM 360M Instruct requires 1.1 GB of VRAM at BF16.
VRAM = Weights + KV Cache + Overhead
Weights = 362M × 16 bits ÷ 8 = 0.7 GB
KV Cache + Overhead ≈ 0.4 GB (at 2K context + ~0.3 GB framework)
VRAM usage by quantization
BF161.1 GB- Can I run SmolLM 360M Instruct on a Mac?
SmolLM 360M Instruct requires at least 1.1 GB at BF16, which exceeds the unified memory of most consumer Macs. You would need a Mac Studio or Mac Pro with a high-memory configuration.
- Can I run SmolLM 360M Instruct locally?
Yes — SmolLM 360M Instruct can run locally on consumer hardware. At BF16 quantization it needs 1.1 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is SmolLM 360M Instruct?
At BF16, SmolLM 360M Instruct can reach ~2626 tok/s on AMD Instinct MI300X. On NVIDIA GeForce RTX 4090: ~590 tok/s. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = (bandwidth GB/s ÷ model GB) × efficiency
Example: AMD Instinct MI300X → 5300 ÷ 1.1 × 0.55 = ~2626 tok/s
Estimated speed at BF16 (1.1 GB)
~2626 tok/s~590 tok/s~1963 tok/s~1624 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of SmolLM 360M Instruct?
At BF16, the download is about 0.72 GB.
- Which GPUs can run SmolLM 360M Instruct?
35 consumer GPUs can run SmolLM 360M Instruct at BF16 (1.1 GB). Top options include AMD Radeon RX 6700 XT, AMD Radeon RX 6800, AMD Radeon RX 6800 XT. 35 GPUs have plenty of headroom for comfortable inference.
- Which devices can run SmolLM 360M Instruct?
33 devices with unified memory can run SmolLM 360M Instruct at BF16 (1.1 GB), including Mac Mini M4 (16 GB), Mac Mini M4 (32 GB), Mac Mini M4 Pro (24 GB), Mac Mini M4 Pro (48 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.