Llama Guard 3 1B — Hardware Requirements & GPU Compatibility
Chat
Llama Guard 3 1B is a 1.5B-parameter open language model from alpindale in the Llama family. It supports a context window of up to 131,072 tokens. At Q4_K_M it needs about 1.27 GB of VRAM — see which GPUs and Macs can run it below.
Runs great on a 24 GB GPU
Runs from 8 GB (Q4_K_M · 128K)Best on 24 GB (Q4_K_M · ~516 tok/s · 128K)Macs from 8 GB (Q4_K_M · ~56 tok/s)
llama3.2
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Llama Guard 3 1B
One recommended way. Every other method, OS and quant is in the step-by-step guide.Each way opens a step-by-step guide for your OS and quant.
Recommended
ollama run llama-guard3:1b-q4_K_MQ4_K_M fits fully on the RTX 4090 · 22.3 GB free · 16K context
Download: Llama-Guard-3-1B.i1-Q4_K_M.gguf0.96 GBmradermacher
Ways to runOther ways
each opens step-by-stepRun in cloud
Runs on RTX 3080 Ti (12 GB) (10 GB headroom) · Q4_K_M
- Generation speed
- ~467 tok/s
- generation speed
- Cost per 1M output tokens
- $0.073
- per 1M output tokens
How Much VRAM Does Llama Guard 3 1B Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 1 GB | 2 GB | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Fits: 128K context · ~655 tok/s | |
| 1.0 GB | 2 GB | 3-bit small — 3-bit small quantization | Fits: 128K context · ~642 tok/s | |
| 1.1 GB | 2.1 GB | 3-bit medium — 3-bit medium quantization | Fits: 128K context · ~596 tok/s | |
| 1.1 GB | 2.1 GB | 4-bit · legacy — 4-bit legacy quantization | Fits: 128K context · ~585 tok/s | |
| 1.3 GB | 2.3 GB | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Fits: 128K context · ~516 tok/s | |
| 1.4 GB | 2.4 GB | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Fits: 128K context · ~458 tok/s | |
| 1.6 GB | 2.6 GB | 6-bit, very good — 6-bit quantization, very good quality | Fits: 128K context · ~410 tok/s | |
| 1.9 GB | 2.9 GB | 8-bit, near-lossless — 8-bit quantization, near-lossless | Fits: 128K context · ~350 tok/s |
Selected Q4_K_M
4-bit medium quantization1.7GBat 16K context
- Weights
- 0.9 GB
- KV cache
- 0.5 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 22.3 GB free · ~516 tok/s
≥50 tok/s needs ≥98 GB/s · RTX 5090 ~917, RTX 3090 Ti ~516
Which Hardware Can Run Llama Guard 3 1B?
Q4_K_M · 1.3 GBLlama Guard 3 1B (Q4_K_M) requires 1.3 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 2+ GB is recommended. Using the full 131K context window can add up to 4.2 GB, bringing total usage to 5.5 GB. 52 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti. 163 devices with unified memory can run Llama Guard 3 1B, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB).
≤ 11 GB
≤ 11 GB tier →fits · 6.3 GB free · up to 128K ctx
16 GPUs · 1 Mac class · 2 device families
RTX 3080~389Simulate output on RTX 3080RTX 2080 Ti~315Simulate output on RTX 2080 TiRTX 3070 Ti~311Simulate output on RTX 3070 TiM3*8 GB~56Simulate output on iMac 24" M3 (8 GB)Orin Nano~52Simulate output on NVIDIA Jetson Orin Nano 8GB (Super)iPhone~38Simulate output on iPhone 1720 GB
fits · 18.3 GB free · up to 128K ctx
1 GPU
RX 7900 XT~378Simulate output on RX 7900 XT32–40 GB
fits · 30.3 GB free · up to 128K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~917Simulate output on RTX 5090M5 Max36 GB~254Simulate output on Mac Studio M5 Max (36 GB)M532 GB~85Simulate output on MacBook Air 13" M5 (32 GB)Orin~105Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~69Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at Q4_K_M
Alternatives to Llama Guard 3 1B
Llama family · 20 models →Similar models
6| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| MiniCPM V 4.7 1BOpenBMB | — | 1.6 GB | ~512 | same size |
| TeleOCRXingChen-AGI | — | 2.1 GB | ~516 | same size |
| LFM2 VL 1.6BLiquid AI | — | 1.5 GB | ~496 | same size |
| Inkling Small DSpark PreviewRadixArk | — | 1.5 GB | ~555 | same size |
| Ouro 1.4BByteDance | — | 6.4 GB | ~184 | same size |
| Qwen Base Invoicev1.01 1.5BLaaP-ai | — | 1.7 GB | ~512 | same size |
Specifications
- Publisher
- alpindale
- Family
- Llama
- Parameters
- 1.5B
- Architecture
- LlamaForCausalLM
- Context Length
- 131,072 tokens
- Vocabulary Size
- 128,256
- Release Date
- 2024-09-25
- License
- llama3.2
Frequently Asked Questions
How much VRAM does Llama Guard 3 1B need?
Llama Guard 3 1B requires 1.3 GB of VRAM at Q4_K_M, or 3.4 GB at BF16. Full 131K context adds up to 4.2 GB (5.5 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 1.5B × 4.8 bits ÷ 8 = 0.9 GB
KV Cache + Overhead ≈ 0.4 GB (at 2K context + ~0.3 GB framework)
Fit ratings and hardware model lists check this model with room for a 16K-token context, which needs a little more memory.
KV Cache + Overhead ≈ 4.6 GB (at full 131K context)
VRAM usage by quantization
What's the best quantization for Llama Guard 3 1B?
For Llama Guard 3 1B, Q4_K_M (1.3 GB) offers the best balance of quality and VRAM usage. Q5_K_S (1.4 GB) provides better quality if you have the VRAM. The smallest option is IQ2_XXS at 0.8 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run Llama Guard 3 1B on a Mac?
Yes — MacBook Air 13" M3 (8 GB) and 145 other Macs can run Llama Guard 3 1B. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 1.3 GB of usable unified memory (RAM minus macOS overhead).
Can I run Llama Guard 3 1B locally?
Yes — Llama Guard 3 1B can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Llama Guard 3 1B?
At Q4_K_M, Llama Guard 3 1B can reach ~3780 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~516 tok/s. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = (bandwidth GB/s ÷ model GB) × efficiency
Example: NVIDIA B200 → 8000 ÷ 1.2700 × 0.65 = ~4094 tok/s
Estimated speed at Q4_K_M (1.3 GB)
Real-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 Q4_K_M, the download is about 0.90 GB. The full-precision BF16 version is 3.00 GB. The smallest option (IQ2_XXS) is 0.41 GB.
Which GPUs can run Llama Guard 3 1B?
52 consumer GPUs can run Llama Guard 3 1B at Q4_K_M. Top options include AMD Radeon RX 6700 XT, AMD Radeon RX 6800, AMD Radeon RX 6800 XT. 52 GPUs have plenty of headroom for comfortable inference.
Which devices can run Llama Guard 3 1B?
163 devices with unified memory can run Llama Guard 3 1B at Q4_K_M (1.3 GB), including AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10, Beelink GTR9 Pro (Ryzen AI Max+ 395, 128 GB), Framework Desktop (Ryzen AI Max+ 395, 128 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.