Intel Arc Pro B65 — Local LLM Performance & Compatibility

Written by Jakub Rusinowski · Last updated September 19, 2026

The B65 keeps the B70's 32 GB and 608 GB/s but drops to 20 Xe cores of compute. For inference, which is bandwidth-bound far more than compute-bound, that matters less than the core count suggests.

Technical Specifications

VRAM32 GB
Memory Bandwidth608 GB/s
TDP200 W
ArchitectureXe2 Battlemage BMG-G31
Release Year2026
MSRP at Launch$0
Inference Speed (Llama 3.1 8B Q4_K_M)35–72 tok/s (estimated)
Inference Speed (Llama 3.3 70B Q4_K_M)Does not fit — needs ~44 GB of 32 GB usable
Buy This HardwareApple Mac mini M4 (16GB) — 32 GB VRAM · 22 W board powerDeploy in the Cloud NowNVIDIA A40 on RunPod — from $0.44/hr · rate checked 2026-08

or compare on Vast.ai

As an Amazon Associate we earn from qualifying purchases. Cloud GPU links are referral links — we may earn a commission at no extra cost to you.

LLMs Compatible with 32 GB VRAM

All models below run comfortably in 32 GB VRAM with Q4_K_M quantization.

Command R FamilyCommand R (35B) · 22 GB VRAM · Q4_K_M · ollama run command-r
Qwen 3.5Qwen 3.5 35B-A3B · 22 GB VRAM · Q4_K_M · ollama run qwen3.5:35b-a3b
Qwen 3.6Qwen 3.6 35B-A3B · 22 GB VRAM · Q4_K_M · ollama run qwen3.6:35b-a3b
Nex-N2Nex-N2 mini · 22 GB VRAM · Q4_K_M · nex-n2
Yi 1.5 FamilyYi 1.5 34B Chat · 22 GB VRAM · Q4_K_M · ollama run yi:34b
Qwen 3Qwen 3 32B · 21 GB VRAM · Q4_K_M · ollama run qwen3:32b
Aya ExpanseAya Expanse 32B · 20 GB VRAM · Q4_K_M · ollama run aya-expanse:32b
DeepSeek R1DeepSeek R1 Distill Qwen 32B · 20 GB VRAM · Q4_K_M · ollama run deepseek-r1:32b

56 more families also fit 32 GB — browse the full model library.

Best Use Cases

FAQ

Can the Intel Arc Pro B65 run local LLMs?

Yes — the Intel Arc Pro B65 has 32 GB VRAM and runs The B65 keeps the B70's 32 GB and 608 GB/s but drops to 20 Xe cores of compute. For inference, which is bandwidth-bound

How fast is the Intel Arc Pro B65 for AI inference?

The Intel Arc Pro B65 is estimated to run Llama 3.1 8B at 35–72 tok/s with Q4_K_M quantization. Llama 3.3 70B does not fit: it needs about 44 GB against 32 GB usable. These are modelled estimates, not measurements — see /en/methodology.

What LLMs can I run on 32 GB VRAM?

With 32 GB you can run: Command R Family, Qwen 3.5, Qwen 3.6, Nex-N2, Yi 1.5 Family. Use Ollama for the easiest setup: ollama run llama3.1:8b.

Compare Similar GPUs

VRAM Tier

Buying Guide

← All GPU Reviews | All Hardware | Check Your Hardware | Full Benchmarks | Can I Run It?