on

Can the NVIDIA GB300 Grace Blackwell Ultra Desktop Superchip run Llama 3.1 70B Instruct?

70Great quality (A) · 70 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking.

Yes, it runs great

Runs great. At Q8_0 it needs about 90.7 GB of 252 GB usable, with an estimated speed of 62.8 tok/s.

Best quant
Q8_0
Generation speed
62.8 tok/s
Prompt processing
816 tok/s
First token (1K prompt)
1.3 s
Largest safe context
128K

Best app to run it on the NVIDIA GB300 Grace Blackwell Ultra Desktop Superchip

On Windows

Ollama

Command line + local API · runs on llama.cpp (ggml), MLX (Apple silicon, preview)

  • One command with Ollama’s own build of this model.
  • Serves an OpenAI-compatible API that other apps and coding tools can use.
ollama run llama3.1:70b-instruct-q8_0
  • LM Studio Point-and-click: search, download and chat in one window.
  • llama.cpp Usually the first to support new model architectures.

On Linux

Ollama

Command line + local API · runs on llama.cpp (ggml), MLX (Apple silicon, preview)

  • One command with Ollama’s own build of this model.
  • Serves an OpenAI-compatible API that other apps and coding tools can use.
ollama run llama3.1:70b-instruct-q8_0
  • 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.
  • LM Studio Point-and-click: search, download and chat in one window.

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 70B Instruct

Recommended for the NVIDIA GB300 Grace Blackwell Ultra Desktop Superchip: Q8_0. Every other quantization has its own download link in the table below.

Quickest · Ollama

One command downloads a ready-to-run version and starts a chat.

Get Ollama at ollama.com/download (opens in a new tab) · model page (opens in a new tab)

ollama run llama3.1:70b-instruct-q8_0

Quantized files · GGUF

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

Download the Q8_0 files (opens in a new tab)

huggingface.co/bartowski/Meta-Llama-3.1-70B-Instruct-GGUF (opens in a new tab)

ollama run hf.co/bartowski/Meta-Llama-3.1-70B-Instruct-GGUF

Original weights · Hugging Face

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

huggingface.co/meta-llama/Llama-3.1-70B-Instruct (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).

Official repo · GitHub

Reference code, inference scripts and docs from Meta. The weights themselves download from Hugging Face.

github.com/meta-llama/llama-models (opens in a new tab)

Meta’s official Llama repo: model cards, prompt formats and download tools.

git clone https://github.com/meta-llama/llama-models

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

How it’s rated

Quality 70Great quality (A) · 70 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 79/100 (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 Runs great
How well it runs on the NVIDIA GB300 Grace Blackwell Ultra Desktop Superchip: 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.

Model qualityEditorial quality tier of the model, scaled by the quantization or precision used.31.5 / 45
Memory fitFull marks when everything sits in GPU memory; fewer when part spills to system RAM.25.0 / 25
SpeedGeneration speed against a 40 tokens/s target for LLMs, or render time against a target for image and video.15.0 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.8.3 / 15
Match score79.8 / 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 GB300 Grace Blackwell Ultra Desktop Superchip

Quant Memory needed Available Speed Runs Quality Download
Q2_K 44.1 GB 252 GB 203 tok/s Runs great 49Fair quality (C) · 49 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. GGUF (opens in a new tab)
Q3_K_M 50.5 GB 252 GB 160 tok/s Runs great 58Good quality (B) · 58 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. GGUF (opens in a new tab)
Q4_K_M 59.0 GB 252 GB 123 tok/s Runs great 66Good quality (B) · 66 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. GGUF (opens in a new tab)
Q5_K_M 66.0 GB 252 GB 102 tok/s Runs great 67Good quality (B) · 67 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. GGUF · folder (opens in a new tab)
Q6_K 73.8 GB 252 GB 85.7 tok/s Runs great 69Good quality (B) · 69 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. GGUF · folder (opens in a new tab)
Q8_0 90.7 GB 252 GB 62.8 tok/s Runs great 70Great quality (A) · 70 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. GGUF · folder (opens in a new tab)
F16 157 GB 252 GB 29.0 tok/s Runs well 70Great quality (A) · 70 of 100: how capable the model is at F16, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. Original weights (opens in a new tab)

Memory figures assume 8K of context. Longer conversations or documents grow the KV cache.

Other hardware that runs it

Quick answers

How much memory does Llama 3.1 70B Instruct need on the NVIDIA GB300 Grace Blackwell Ultra Desktop Superchip 252GB?

At Q8_0 it needs about 90.7 GB. The NVIDIA GB300 Grace Blackwell Ultra Desktop Superchip 252GB has 252 GB usable.

How fast is Llama 3.1 70B Instruct on the NVIDIA GB300 Grace Blackwell Ultra Desktop Superchip 252GB?

About 62.8 tok/s at Q8_0, an estimate from the hardware’s memory bandwidth and the size of the model.

Which quantization of Llama 3.1 70B Instruct should I use on the NVIDIA GB300 Grace Blackwell Ultra Desktop Superchip 252GB?

Q8_0. Of the versions that fit, it is the one that runs best; when two run equally well, the check prefers the higher-rated one.

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?