on

Can the NVIDIA L40 run Llama 3.1 Nemotron Safety Guard 8B v3?

83Great quality (A) · 83 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking.

Yes, it runs great

Runs great. At Q6_K it needs about 9.9 GB of 48.0 GB usable and makes one decision in about 133 ms.

Best quant
Q6_K
Time per decision
133 ms
Decisions per second
7.5/s
Input assumed
512 tokens
Returns
Fixed labels

Best app to run it on the NVIDIA L40

On Linux

vLLM

Inference server · runs on vLLM

  • The full model fits in GPU memory at 8-bit, so it can batch many requests: best for serving a team or an app.
vllm serve nvidia/Llama-3.1-Nemotron-Safety-Guard-8B-v3
  • LM Studio Point-and-click: search, download and chat in one window.
  • SGLang The full model fits in GPU memory at 8-bit, so it can batch many requests: best for serving a team or an app.

On Windows

LM Studio

Desktop app · runs on llama.cpp, MLX

  • Point-and-click: search, download and chat in one window.

Open Llama 3.1 Nemotron Safety Guard 8B v3 in LM Studio

  • llama.cpp Usually the first to support new model architectures.
  • Ollama Runs the Hugging Face GGUF with ollama run hf.co/…

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 3.1 Nemotron Safety Guard 8B v3

Recommended for the NVIDIA L40: Q6_K. Every other quantization has its own download link in the table below.

Quantized files · GGUF

Works in LM Studio, llama.cpp, Jan and Ollama. No sign-in needed.

Download the Q6_K file (opens in a new tab)

huggingface.co/mradermacher/Llama-3.1-Nemotron-Safety-Guard-8B-v3-GGUF (opens in a new tab)

ollama run hf.co/mradermacher/Llama-3.1-Nemotron-Safety-Guard-8B-v3-GGUF:Q6_K

Original weights · Hugging Face

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

huggingface.co/nvidia/Llama-3.1-Nemotron-Safety-Guard-8B-v3 (opens in a new tab)

No sign-in needed.

Links checked 3 days ago against Hugging Face, Ollama and GitHub.

How it’s rated

Quality 83Great quality (A) · 83 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking.
How capable the model itself is at Q6_K, 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 Runs great
How well it runs on the NVIDIA L40: 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.37.4 / 45
Memory fitFull marks when everything sits in GPU memory; fewer when part spills to system RAM.25.0 / 25
SpeedTime for one decision against a 100 ms target: reading the input plus any tokens the model writes.13.0 / 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 score87.4 / 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 NVIDIA L40

Quant Memory needed Available Speed Runs Quality Download
Q4_K_M 8.2 GB 48.0 GB 113 ms Runs great 79Great quality (A) · 79 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. GGUF (opens in a new tab)
Q5_K_M 9.0 GB 48.0 GB 122 ms Runs great 81Great quality (A) · 81 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. GGUF (opens in a new tab)
Q6_K 9.9 GB 48.0 GB 133 ms Runs great 83Great quality (A) · 83 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. GGUF (opens in a new tab)
Q8_0 11.8 GB 48.0 GB 156 ms Runs well 84Great quality (A) · 84 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. GGUF (opens in a new tab)
F16 19.3 GB 48.0 GB 261 ms Runs well 84Great quality (A) · 84 of 100: how capable the model is at F16, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. GGUF (opens in a new tab) 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

Quick answers

How much memory does Llama 3.1 Nemotron Safety Guard 8B v3 need on the NVIDIA L40 48GB?

At Q6_K it needs about 9.9 GB. The NVIDIA L40 48GB has 48.0 GB usable.

How fast is Llama 3.1 Nemotron Safety Guard 8B v3 on the NVIDIA L40 48GB?

It makes one decision in about 133 ms at Q6_K, an estimate from the hardware and the size of the model.

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.

Was this page helpful?