Hardware · Intel

What AI models can the Intel Arc Pro B65 run?

VRAM
32.0 GB
Usable for models
32.0 GB
Memory bandwidth
608 GB/s
FP16 compute
24.6 TFLOPS
Released
2026
514 / 622 LLMs run Best: Gemma 4 26B-A4B 60 / 61 Image models run Best: FLUX.2 [klein] 9B 40 / 43 Video models run Best: Bernini-R A14B (video generation + editing) 68 / 70 Decision models run Best: Jina Reranker v3.5

More about this hardware

MakerIntel
TypeWorkstation / datacenter graphics card
InterfacePCIe 5.0

Apps that run models well on the Intel Arc Pro B65

Windows

  1. llama.cppSupports Intel Arc through SYCL and Vulkan.
  2. LM StudioPoint-and-click: search, download and chat in one window.
  3. OllamaIntel GPU support here is experimental (Vulkan).
  4. JanPoint-and-click: search, download and chat in one window.

Linux

  1. llama.cppSupports Intel Arc through SYCL and Vulkan.
  2. LM StudioPoint-and-click: search, download and chat in one window.
  3. OllamaIntel GPU support here is experimental (Vulkan).
  4. JanPoint-and-click: search, download and chat in one window.

For a typical model that fits in memory. Each model page picks the best app for that model on this hardware. All apps

Best LLMs for the Intel Arc Pro B65

Quality Model Quant Memory Speed Runs
91Excellent quality (A+) · 91 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 96/100 (quality, fit, speed and memory use) sets the ranking. Gemma 4 26B-A4BGoogle Q6_K 23.8 GB 75.7 tok/s Runs great
92Excellent quality (A+) · 92 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.6 35B-A3BAlibaba Q6_K 31.8 GB 89.3 tok/s Runs welltight fit
92Excellent quality (A+) · 92 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking. MiniCPM-V 4.7 35B-A3BOpenBMB Q6_K 31.2 GB 89.3 tok/s Runs welltight fit
92Excellent quality (A+) · 92 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.5 35B-A3BAlibaba Q6_K 31.8 GB 89.3 tok/s Runs welltight fit
91Excellent quality (A+) · 91 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking. Nex N2 Mini (35B-A3B)Nex-AGI Q6_K 31.2 GB 89.3 tok/s Runs welltight fit
88Excellent quality (A+) · 88 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking. KAT-Coder V2.5 Dev (35B-A3B)Kuaishou Q5_K_M 27.0 GB 101 tok/s Runs great
90Excellent quality (A+) · 90 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking. Sage-A1.5 35B-A3BInternScience Q6_K 31.8 GB 89.3 tok/s Runs welltight fit
87Excellent quality (A+) · 87 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking. Raon-1 mini Preview (30B-A4B)KRAFTON Q6_K 25.9 GB 69.1 tok/s Runs great
89Excellent quality (A+) · 89 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking. Ornith 1.5 35B-A3BDeepReinforce Q6_K 31.8 GB 89.3 tok/s Runs welltight fit
88Excellent quality (A+) · 88 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. Apodex 1.1 Mini (35B-A3B)Apodex Q6_K 31.8 GB 89.3 tok/s Runs welltight fit
88Excellent quality (A+) · 88 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. Ornith 1.0 35B-A3BDeepReinforce Q6_K 31.8 GB 89.3 tok/s Runs welltight fit
85Excellent quality (A+) · 85 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. Flint (40B-A2.5B)Recursive Q4_K_M 26.7 GB 129 tok/s Runs great

Best Image models for the Intel Arc Pro B65

Quality Model Quant Memory Speed Runs
83Great quality (A) · 83 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking. FLUX.2 [klein] 9BBlack Forest Labs Q8 GGUF 20.5 GB 9.2 s Runs great
90Excellent quality (A+) · 90 of 100: how capable the model is at FP8, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. Krea 2 TurboKrea FP8 20.2 GB 17 s Runs well
85Excellent quality (A+) · 85 of 100: how capable the model is at FP16, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking. ERNIE-Image TurboBaidu FP16 26.4 GB 14 s Runs well
91Excellent quality (A+) · 91 of 100: how capable the model is at FP16, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking. FLUX 3 Image KleinBlack Forest Labs FP16 22.4 GB 25 s Runs well
78Great quality (A) · 78 of 100: how capable the model is at FP16, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. FLUX.2 [klein] 4BBlack Forest Labs FP16 18.1 GB 4.5 s Runs great
82Great quality (A) · 82 of 100: how capable the model is at FP8, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. Z-Image TurboAlibaba (Tongyi) FP8 12.6 GB 10 s Runs great

Best Video models for the Intel Arc Pro B65

Quality Model Quant Memory Speed Runs
83Great quality (A) · 83 of 100: how capable the model is at FP8, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. Bernini-R A14B (video generation + editing)ByteDance FP8 26.0 GB 48.2 min Very slow
66Good quality (B) · 66 of 100: how capable the model is at FP8, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. LTX-Video 13B 0.9.8 (distilled)Lightricks FP8 30.1 GB 4.0 min Runs welltight fit
81Great quality (A) · 81 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. LTX-2.5 (22B, video + audio)Lightricks Q4 GGUF 26.8 GB 8.5 min Runs wellencoder in RAM
74Great quality (A) · 74 of 100: how capable the model is at FP8, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. HY-OmniWeaving (8.3B, unified video)Tencent FP8 24.6 GB 35.5 min Slow
78Great quality (A) · 78 of 100: how capable the model is at FP8, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. SCAIL-2 14B (character animation)Zhipu AI FP8 29.8 GB 80.4 min Very slowtight fit

Best Decision models for the Intel Arc Pro B65

Quality Model Quant Memory Speed Runs
86Excellent quality (A+) · 86 of 100: how capable the model is at F16, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. Jina Reranker v3.5Jina AI F16 3.6 GB 31 ms Runs great
84Great quality (A) · 84 of 100: how capable the model is at F16, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking. Jina Reranker v3Jina AI F16 3.6 GB 31 ms Runs great
84Great quality (A) · 84 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking. Intern-Decision 4BShanghai AI Lab Q8_0 7.1 GB 106 ms Runs great
90Excellent quality (A+) · 90 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking. Qwen3 Reranker 4BAlibaba Q8_0 6.8 GB 170 ms Runs well
82Great quality (A) · 82 of 100: how capable the model is at F16, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. d1 3BLiquid AI F16 8.5 GB 86 ms Runs great
82Great quality (A) · 82 of 100: how capable the model is at F16, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. mxbai-rerank-large v2Mixedbread F16 5.3 GB 74 ms Runs great
88Excellent quality (A+) · 88 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. zerank-2ZeroEntropy Q8_0 6.8 GB 170 ms Runs well
80Great quality (A) · 80 of 100: how capable the model is at F16, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. FRIDA-DecisionsSber AI F16 2.4 GB 23 ms Runs great

Best LLMs by task on this hardware Open in Model Finder

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?