Llama 3.1 70B Instruct on Intel Arc Pro B50

Can the Intel Arc Pro B50 run Llama 3.1 70B Instruct?

44 pts

Barely: most of the model spills into system RAM

Heavy offload. At Q2_K it needs about 32.3 GB of 16.0 GB usable, with an estimated speed of 2.6 tok/s.

Best quant: Q2_K
Generation speed: 2.6 tok/s
Prompt processing: 64.5 tok/s
First token (1K prompt): 15.9 s
Largest safe context: —

Download Llama 3.1 70B Instruct

Recommended for the Intel Arc Pro B50: Q2_K. 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.

ollama run llama3.1:70b-instruct-q2_K

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

Quantized files · GGUF

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

Download the Q2_K file (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:Q2_K

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)

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

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

Links checked 1 week ago against Hugging Face, Ollama and GitHub.

How the C grade is scored

Every result gets up to 100 points from four parts. The points decide the letter grade.

Model qualityEditorial quality tier of the model, scaled by the quantization or precision used.	22.1 / 45
Memory fitFull marks when everything sits in GPU or unified memory; fewer when part spills to system RAM.	4.0 / 25
SpeedGeneration speed against a 40 tokens/s target for LLMs, or render time against a target for image and video.	3.8 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.	15.0 / 15
Total	44.8 / 100	44 ptsUsable (C) · 44 of 100 points: Model quality 22.1/45, Memory fit 4.0/25, Speed 3.8/15, Memory use 15.0/15

Grade scale: S 85+ · A 72+ · B 58+ · C 42+ · D 25+ · F under 25 points.

Every quantization on the Intel Arc Pro B50

Quant	Memory needed	Available	Speed	Fit	Grade · points	Download
`Q2_K`	32.3 GB	16.0 GB	2.6 tok/s	Heavy offload	44 ptsUsable (C) · 44 of 100 points: Model quality 22.1/45, Memory fit 4.0/25, Speed 3.8/15, Memory use 15.0/15	GGUF (opens in a new tab)
`Q3_K_M`	38.7 GB	16.0 GB	—	Won't run	7 ptsWon't run (F) · 7 of 100 points: Model quality 7.9/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	GGUF (opens in a new tab)
`Q4_K_M`	47.2 GB	16.0 GB	—	Won't run	8 ptsWon't run (F) · 8 of 100 points: Model quality 9.0/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	GGUF (opens in a new tab)
`Q5_K_M`	54.2 GB	16.0 GB	—	Won't run	9 ptsWon't run (F) · 9 of 100 points: Model quality 9.2/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	GGUF · folder (opens in a new tab)
`Q6_K`	62.0 GB	16.0 GB	—	Won't run	9 ptsWon't run (F) · 9 of 100 points: Model quality 9.4/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	GGUF · folder (opens in a new tab)
`Q8_0`	78.9 GB	16.0 GB	—	Won't run	9 ptsWon't run (F) · 9 of 100 points: Model quality 9.5/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	GGUF · folder (opens in a new tab)
`F16`	145 GB	16.0 GB	—	Won't run	9 ptsWon't run (F) · 9 of 100 points: Model quality 9.5/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	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

80 ptsGreat (A) · 80 of 100 points: Model quality 29.9/45, Memory fit 25.0/25, Speed 13.2/15, Memory use 12.3/15 NVIDIA RTX PRO 6000 Blackwell Q4_K_M · 31.2 tok/s
76 ptsGreat (A) · 76 of 100 points: Model quality 31.2/45, Memory fit 25.0/25, Speed 5.6/15, Memory use 15.0/15 Apple M4 Max (128 GB) Q6_K · 5.7 tok/s
75 ptsGreat (A) · 75 of 100 points: Model quality 31.2/45, Memory fit 25.0/25, Speed 3.9/15, Memory use 15.0/15 AMD Ryzen AI Max+ 395 (128 GB) Q6_K · 2.7 tok/s
74 ptsGreat (A) · 74 of 100 points: Model quality 31.2/45, Memory fit 25.0/25, Speed 4.3/15, Memory use 14.1/15 NVIDIA GB10 (128 GB) Q6_K · 3.3 tok/s
73 ptsGreat (A) · 73 of 100 points: Model quality 26.5/45, Memory fit 24.0/25, Speed 7.7/15, Memory use 15.0/15 Apple M4 Max (64 GB) Q3_K_M · 10.6 tok/s
72 ptsGreat (A) · 72 of 100 points: Model quality 29.9/45, Memory fit 25.0/25, Speed 8.2/15, Memory use 9.3/15 Apple M2 Ultra (192 GB) Q4_K_M · 12.0 tok/s

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.