Can the Intel Arc A380 run Llama Guard 4 12B?

Barely: it runs very slowly (heavy RAM offload)

Very slow (heavy RAM offload). At Q8_0 it needs about 14.0 GB of 6.0 GB usable and makes one decision in about 3.8 s.

Best quant: Q8_0
Time per decision: 3.8 s
Decisions per second: 0.3/s
Input assumed: 512 tokens
Returns: Fixed labels

Best app to run it on the Intel Arc A380

On Windows

Command line + local API · runs on llama.cpp, vLLM

Splits the model between GPU memory and system RAM, which this setup needs.
Handy if you already work in Docker.

docker model run hf.co/meta-llama/Llama-Guard-4-12B

Sentence Transformers Can only use the CPU on this hardware, so it will be slow.

On Linux

Docker Model Runner

Command line + local API · runs on llama.cpp, vLLM

Splits the model between GPU memory and system RAM, which this setup needs.
Handy if you already work in Docker.

docker model run hf.co/meta-llama/Llama-Guard-4-12B

Sentence Transformers Can only use the CPU on this hardware, so it will be slow.

How we choose: the files published for this model, your operating system and GPU, whether it fits fully in memory, and published speed tests (MLX vs llama.cpp on Apple silicon, vLLM vs llama.cpp vs Ollama on NVIDIA). Details.

Download Llama Guard 4 12B

Original weights · Hugging Face

Full-precision files from Meta, for fine-tuning, vLLM, Transformers.

huggingface.co/meta-llama/Llama-Guard-4-12B (opens in a new tab)

Free Hugging Face account needed: request access on the model page, and Meta approves it (usually within minutes to a few hours).

Links checked 6 days ago against Hugging Face, Ollama and GitHub.

How it’s rated

Quality 66Good quality (B) · 66 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 48/100 (quality, fit, speed and memory use) sets the ranking.: How capable the model itself is at Q8_0, from its editorial quality tier scaled by the quantization or precision. It’s the same on any hardware that runs this variant. Scale: A+ 85+ · A 70+ · B 55+ · C 40+ · D under 40.
Runs Very slowheavy RAM offload: How well it runs on the Intel Arc A380: speed, capped by how well it fits in memory. Runs great: 30+ tokens/s (or near the image, video or decision speed target) · Runs well: 10+ tokens/s · Slow: 3+ tokens/s · Very slow: under 3 · Won’t run: doesn’t fit even with offload. A tight fit or RAM offload caps it at Runs well; heavy offload caps it at Slow.

Match score

To order lists, each result also gets a match score out of 100 from four parts. It favors the most capable model that still runs well.

PrecisionEditorial precision tier from the model’s published benchmarks, scaled by the quantization or precision used.	29.7 / 45
Memory fitFull marks when everything sits in GPU memory; fewer when part spills to system RAM.	4.0 / 25
SpeedTime for one decision against a 100 ms target: reading the input plus any tokens the model writes.	2.4 / 15
ClarityHow easy the answer is to use in code: a probability or score earns the most, written feedback before a score the least.	12.0 / 15
Match score	48.1 / 100

The match score orders results; it is not shown as a grade. Quality and Runs are the two ratings in the tables.

Every quantization on the Intel Arc A380

Quant	Memory needed	Available	Speed	Runs	Quality	Download
`Q4_K_M`	8.6 GB	6.0 GB	2.4 s	Very slowheavy RAM offload	62Good quality (B) · 62 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 47/100 (quality, fit, speed and memory use) sets the ranking.	All files (opens in a new tab)
`Q5_K_M`	9.8 GB	6.0 GB	2.7 s	Very slowheavy RAM offload	64Good quality (B) · 64 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 47/100 (quality, fit, speed and memory use) sets the ranking.	All files (opens in a new tab)
`Q6_K`	11.1 GB	6.0 GB	3.1 s	Very slowheavy RAM offload	65Good quality (B) · 65 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 48/100 (quality, fit, speed and memory use) sets the ranking.	All files (opens in a new tab)
`Q8_0`	14.0 GB	6.0 GB	3.8 s	Very slowheavy RAM offload	66Good quality (B) · 66 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 48/100 (quality, fit, speed and memory use) sets the ranking.	All files (opens in a new tab)
`F16`	25.3 GB	6.0 GB	—	Won't run	66Good quality (B) · 66 of 100: how capable the model is at F16, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking.	Original weights (opens in a new tab)

Times are for one request with a 512-token input and about 6 tokens written. Batching servers process many requests at once.

Other hardware that runs it

65Good quality (B) · 65 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA RTX PRO 6000 Blackwell Q6_K · 119 ms · Runs great
65Good quality (B) · 65 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5090 Q6_K · 133 ms · Runs great
65Good quality (B) · 65 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. AMD Radeon RX 7900 XTX Q6_K · 187 ms · Runs well
65Good quality (B) · 65 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4090 Q6_K · 191 ms · Runs well
65Good quality (B) · 65 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5080 Q6_K · 244 ms · Runs well
65Good quality (B) · 65 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. AMD Radeon RX 9070 XT Q6_K · 259 ms · Runs well

Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.