Llama Guard 3 1B — Hardware Requirements & GPU Compatibility
Chat
Llama Guard 3 1B is a 1.5B-parameter open language model from Meta in the Llama family. At BF16 it needs about 3.30 GB of VRAM — see which GPUs and Macs can run it below.
44.9K downloads
109 likesSpecifications
- Publisher
- Meta
- Family
- Llama
- Parameters
- 1.5B
- Release Date
- 2024-09-26
- License
- llama3.2
Get Started
HuggingFace
How Much VRAM Does Llama Guard 3 1B Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| BF16 | 16.00 | 3.3 GB | — | 3.00 GB | Brain floating point 16 — preferred for training |
Which GPUs Can Run Llama Guard 3 1B?
BF16 · 3.3 GBLlama Guard 3 1B (BF16) requires 3.3 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 5+ 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 Llama Guard 3 1B?
BF16 · 3.3 GB33 devices with unified memory can run Llama Guard 3 1B, including NVIDIA DGX H100, NVIDIA DGX A100 640GB.
Runs great
— Plenty of headroomRelated Models
Frequently Asked Questions
- How much VRAM does Llama Guard 3 1B need?
Llama Guard 3 1B requires 3.3 GB of VRAM at BF16.
VRAM = Weights + KV Cache + Overhead
Weights = 1.5B × 16 bits ÷ 8 = 3 GB
KV Cache + Overhead ≈ 0.3 GB (at 2K context + ~0.3 GB framework)
VRAM usage by quantization
BF163.3 GB- Can I run Llama Guard 3 1B on a Mac?
Llama Guard 3 1B requires at least 3.3 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 Llama Guard 3 1B locally?
Yes — Llama Guard 3 1B can run locally on consumer hardware. At BF16 quantization it needs 3.3 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is Llama Guard 3 1B?
At BF16, Llama Guard 3 1B can reach ~883 tok/s on AMD Instinct MI300X. On NVIDIA GeForce RTX 4090: ~199 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 ÷ 3.3 × 0.55 = ~883 tok/s
Estimated speed at BF16 (3.3 GB)
~883 tok/s~199 tok/s~660 tok/s~546 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of Llama Guard 3 1B?
At BF16, the download is about 3.00 GB.
- Which GPUs can run Llama Guard 3 1B?
35 consumer GPUs can run Llama Guard 3 1B at BF16 (3.3 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 Llama Guard 3 1B?
33 devices with unified memory can run Llama Guard 3 1B at BF16 (3.3 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.