Check my GPU

Hardware · Intel

What AI models can the Intel Core Ultra 200H (Arc 140T) (96 GB) run?

Unified memory
96.0 GB
Usable for models
54.7 GB
Memory bandwidth
102 GB/s
FP16 compute
9.2 TFLOPS
Released
2025

macOS lets the GPU use roughly two-thirds to three-quarters of unified memory by default, so we plan around that figure rather than the full 96.0 GB.

Specifications

MakerIntel
TypeUnified-memory system on a chip
GPU share of memory57% (what the GPU can typically be given for a model)
ChipApple Intel Core Ultra 200H (Arc 140T)
Unified memory96.0 GB
Usable for AI models54.7 GB
Memory bandwidth102 GB/s
FP16 compute9.2 TFLOPS
InterfaceUNIFIED
Released2025

Best LLMs for the Intel Core Ultra 200H (Arc 140T) (96 GB)

Grade · points Model Quant Memory Speed Fit
89 ptsExcellent (S) · 89 of 100 points: Model quality 41.7/45, Memory fit 25.0/25, Speed 7.9/15, Memory use 14.6/15 Qwen3.6 35B-A3BAlibaba Q6_K 34.6 GB 11.1 tok/s Runs well
88 ptsExcellent (S) · 88 of 100 points: Model quality 41.4/45, Memory fit 25.0/25, Speed 7.9/15, Memory use 14.6/15 Qwen3.5 35B-A3BAlibaba Q6_K 34.6 GB 11.1 tok/s Runs well
87 ptsExcellent (S) · 87 of 100 points: Model quality 40.1/45, Memory fit 25.0/25, Speed 7.9/15, Memory use 14.6/15 Ornith 1.5 35B-A3BDeepReinforce Q6_K 34.6 GB 11.1 tok/s Runs well
87 ptsExcellent (S) · 87 of 100 points: Model quality 39.6/45, Memory fit 25.0/25, Speed 7.9/15, Memory use 14.6/15 Apodex 1.1 Mini (35B-A3B)Apodex Q6_K 34.6 GB 11.1 tok/s Runs well
87 ptsExcellent (S) · 87 of 100 points: Model quality 39.6/45, Memory fit 25.0/25, Speed 7.9/15, Memory use 14.6/15 Ornith 1.0 35B-A3BDeepReinforce Q6_K 34.6 GB 11.1 tok/s Runs well
85 ptsExcellent (S) · 85 of 100 points: Model quality 36.8/45, Memory fit 24.0/25, Speed 9.5/15, Memory use 15.0/15 Qwen3 Coder Next (80B-A3B)Alibaba Q4_K_M 53.8 GB 16.0 tok/s Tight fit
84 ptsGreat (A) · 84 of 100 points: Model quality 41.2/45, Memory fit 25.0/25, Speed 7.0/15, Memory use 11.2/15 Gemma 4 26B-A4BGoogle Q6_K 26.5 GB 8.8 tok/s Runs well
83 ptsGreat (A) · 83 of 100 points: Model quality 32.5/45, Memory fit 25.0/25, Speed 10.8/15, Memory use 15.0/15 Qwen3-Next 80B-A3B ThinkingAlibaba Q3_K_M 45.0 GB 20.7 tok/s Runs well
83 ptsGreat (A) · 83 of 100 points: Model quality 42.6/45, Memory fit 25.0/25, Speed 3.7/15, Memory use 11.9/15 Qwen3.8 27BAlibaba Q6_K 28.3 GB 2.4 tok/s Runs well
82 ptsGreat (A) · 82 of 100 points: Model quality 37.2/45, Memory fit 25.0/25, Speed 9.5/15, Memory use 11.2/15 Agents-A1 35B-A3BInternScience Q4_K_M 26.6 GB 16.0 tok/s Runs well
82 ptsGreat (A) · 82 of 100 points: Model quality 37.2/45, Memory fit 25.0/25, Speed 9.5/15, Memory use 11.1/15 Qwen AgentWorld 35B-A3BAlibaba Q4_K_M 26.3 GB 16.0 tok/s Runs well
82 ptsGreat (A) · 82 of 100 points: Model quality 40.5/45, Memory fit 25.0/25, Speed 3.5/15, Memory use 13.6/15 Gemma 4 31BGoogle Q6_K 32.2 GB 2.1 tok/s Runs well

Best Image models for the Intel Core Ultra 200H (Arc 140T) (96 GB)

Grade · points Model Precision Memory Time per output Fit
89 ptsExcellent (S) · 89 of 100 points: Model quality 37.8/45, Memory fit 25.0/25, Speed 11.6/15, Memory use 15.0/15 FLUX.2 [klein] 9BBlack Forest Labs FP16 37.1 GB 17 s Runs well
82 ptsGreat (A) · 82 of 100 points: Model quality 35.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 7.6/15 FLUX.2 [klein] 4BBlack Forest Labs FP16 18.1 GB 9.3 s Runs well
82 ptsGreat (A) · 82 of 100 points: Model quality 31.5/45, Memory fit 25.0/25, Speed 11.0/15, Memory use 15.0/15 FLUX.1 [schnell]Black Forest Labs FP16 36.4 GB 19 s Runs well
82 ptsGreat (A) · 82 of 100 points: Model quality 37.8/45, Memory fit 25.0/25, Speed 9.8/15, Memory use 9.6/15 Z-Image TurboAlibaba (Tongyi) FP16 22.7 GB 23 s Runs well
81 ptsGreat (A) · 81 of 100 points: Model quality 40.1/45, Memory fit 25.0/25, Speed 1.5/15, Memory use 15.0/15 Qwen-Image 2512Alibaba Q8 GGUF 36.5 GB 16.1 min Runs well
81 ptsGreat (A) · 81 of 100 points: Model quality 36.9/45, Memory fit 25.0/25, Speed 4.5/15, Memory use 15.0/15 FLUX.1 Krea [dev]Black Forest Labs FP16 36.4 GB 1.9 min Runs well

Best Video models for the Intel Core Ultra 200H (Arc 140T) (96 GB)

Grade · points Model Precision Memory Time per output Fit
81 ptsGreat (A) · 81 of 100 points: Model quality 37.9/45, Memory fit 25.0/25, Speed 3.5/15, Memory use 15.0/15 LTX-2.3Lightricks FP8 44.3 GB 56.0 min Runs well
79 ptsGreat (A) · 79 of 100 points: Model quality 38.3/45, Memory fit 25.0/25, Speed 1.5/15, Memory use 15.0/15 Wan 2.2 I2V A14BAlibaba Q8 GGUF 39.3 GB 4.8 h Runs well
79 ptsGreat (A) · 79 of 100 points: Model quality 38.3/45, Memory fit 25.0/25, Speed 1.5/15, Memory use 15.0/15 Wan 2.2 T2V A14BAlibaba Q8 GGUF 39.3 GB 4.8 h Runs well
79 ptsGreat (A) · 79 of 100 points: Model quality 36.2/45, Memory fit 25.0/25, Speed 3.5/15, Memory use 15.0/15 LTX-2 (19B, video + audio)Lightricks FP8 44.3 GB 56.0 min Runs well
78 ptsGreat (A) · 78 of 100 points: Model quality 37.0/45, Memory fit 25.0/25, Speed 1.6/15, Memory use 15.0/15 HunyuanVideo 1.5 (8.3B)Tencent FP8 38.4 GB 4.2 h Runs well

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.