Apple MacBook Air (13-inch, M4, 2025)

Hardware · Apple Silicon

What AI models can the Apple M4 (24 GB) run?

Unified memory
24.0 GB
Usable for models
16.1 GB
Memory bandwidth
120 GB/s
FP16 compute
4.3 TFLOPS
Released
2024
455 / 621 LLMs run Best: Gemma 4 26B-A4B 55 / 61 Image models run Best: FLUX.2 [klein] 4B 17 / 43 Video models run Best: LTX-Video 2B 66 / 70 Decision models run Best: Jina Reranker v3.5

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 24.0 GB.

More about this hardware

MakerApple Silicon
TypeApple silicon (system on a chip)
ChipApple M4

Apps that run models well on the Apple M4 (24 GB)

macOS

  1. LM StudioRuns the MLX build, typically 20–35% faster than GGUF for a model with 8B active parameters on Apple silicon.
  2. OllamaOne command with Ollama’s own build of this model.
  3. MLX LMRuns the MLX build, typically 20–35% faster than GGUF for a model with 8B active parameters on Apple silicon.
  4. JanRuns the MLX build, typically 20–35% faster than GGUF for a model with 8B active parameters on Apple silicon.

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

5 products with the Apple M4 (24 GB)

Best LLMs for the Apple M4 (24 GB)

Quality Model Quant Memory Speed Runs
77Great quality (A) · 77 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. Gemma 4 26B-A4BGoogle Q3_K_M 14.9 GB 37.9 tok/s Runs welltight fit
73Great quality (A) · 73 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. Raon-1 mini Preview (30B-A4B)KRAFTON Q3_K_M 16.1 GB 33.9 tok/s Runs welltight fit
70Great quality (A) · 70 of 100: how capable the model is at MXFP4, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. gpt-oss 20BOpenAI MXFP4 14.0 GB 33.5 tok/s Runs welltight fit
66Good quality (B) · 66 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. Maple Preview (20B-A1B)DeepGrove Q4_K_M 14.3 GB 66.2 tok/s Runs welltight fit
66Good quality (B) · 66 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. Mellum2.1 Thinking (12B-A2.5B)JetBrains Q4_K_M 9.4 GB 43.3 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 83/100 (quality, fit, speed and memory use) sets the ranking. ERNIE 4.5 21B-A3B ThinkingBaidu Q4_K_M 15.7 GB 37.0 tok/s Runs welltight fit
65Good quality (B) · 65 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. DiffusionGemma 26B-A4B ITGoogle Q3_K_M 14.9 GB 36.2 tok/s Runs welltight fit
63Good quality (B) · 63 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. KAT-Coder V2.5 Dev (35B-A3B)Kuaishou Q2_K 15.9 GB 57.1 tok/s Runs welltight fit
78Great quality (A) · 78 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. Gemma 4 12BGoogle Q4_K_M 9.9 GB 10.6 tok/s Runs well
60Good quality (B) · 60 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. Ling 3.0 Tiny (8B-A1.3B)Ant Group (inclusionAI) Q8_0 10.5 GB 41.8 tok/s Runs great
62Good quality (B) · 62 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. LFM2.5 24B-A2BLiquid AI Q3_K_M 13.8 GB 55.0 tok/s Runs welltight fit
61Good quality (B) · 61 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. GLM-4.7 Flash (30B-A3B)Zhipu AI Q2_K 14.8 GB 57.1 tok/s Runs welltight fit

Best Image models for the Apple M4 (24 GB)

Quality Model Quant Memory Speed Runs
76Great quality (A) · 76 of 100: how capable the model is at FP8, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. FLUX.2 [klein] 4BBlack Forest Labs FP8 10.2 GB 16 s Runs well
89Excellent quality (A+) · 89 of 100: how capable the model is at FP8, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. FLUX 3 Image KleinBlack Forest Labs FP8 12.4 GB 89 s Slow
82Great quality (A) · 82 of 100: how capable the model is at FP8, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. Z-Image TurboAlibaba (Tongyi) FP8 12.6 GB 39 s Runs well
83Great quality (A) · 83 of 100: how capable the model is at FP8, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. ERNIE-Image TurboBaidu FP8 14.5 GB 50 s Slowtight fit
82Great quality (A) · 82 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. FLUX.2 [klein] 9BBlack Forest Labs FP8 11.7 GB 30 s Runs wellencoder unloaded after use
81Great quality (A) · 81 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. Z-ImageAlibaba (Tongyi) Q8 GGUF 13.0 GB 5.7 min Very slow

Best Video models for the Apple M4 (24 GB)

Quality Model Quant Memory Speed Runs
49Fair quality (C) · 49 of 100: how capable the model is at FP8, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. LTX-Video 2BLightricks FP8 10.8 GB 6.5 min Runs well
53Fair quality (C) · 53 of 100: how capable the model is at FP8, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. Wan 2.1 T2V 1.3BAlibaba FP8 12.8 GB 62.8 min Very slow
44Fair quality (C) · 44 of 100: how capable the model is at FP8, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. CogVideoX 2BZhipu AI FP8 11.0 GB 15.7 min Slow
68Good quality (B) · 68 of 100: how capable the model is at FP16, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. Kandinsky 6.0 Video Lite (3B, video + audio)Sber AI FP16 14.7 GB 1.6 h Very slowtight fit · encoder unloaded after use
83Great quality (A) · 83 of 100: how capable the model is at FP8, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. Bernini-R A14B (video generation + editing)ByteDance FP8 10.7 GB 4.1 h Very slowCPU offload

Best Decision models for the Apple M4 (24 GB)

Quality Model Quant Memory Speed Runs
86Excellent quality (A+) · 86 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. Jina Reranker v3.5Jina AI Q8_0 2.8 GB 129 ms Runs great
84Great quality (A) · 84 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. Jina Reranker v3Jina AI Q8_0 2.8 GB 129 ms Runs great
80Great quality (A) · 80 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. FRIDA-DecisionsSber AI Q8_0 1.7 GB 90 ms Runs great
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. GLiNER2.5 DecideFastino F16 1.7 GB 63 ms Runs great
80Great quality (A) · 80 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. Qwen3 Reranker 0.6BAlibaba Q8_0 2.8 GB 129 ms Runs great
76Great quality (A) · 76 of 100: how capable the model is at F16, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. Llama Prompt Guard 2 86MMeta F16 1.2 GB 71 ms Runs great
76Great quality (A) · 76 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. mxbai-rerank-base v2Mixedbread Q8_0 2.4 GB 106 ms Runs great
74Great quality (A) · 74 of 100: how capable the model is at F16, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. GLiClass ModernBERT Large v3Knowledgator F16 1.5 GB 52 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?