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

Hardware · Apple Silicon

What AI models can the Apple M4 (16 GB) run?

Unified memory
16.0 GB
Usable for models
10.7 GB
Memory bandwidth
120 GB/s
FP16 compute
4.3 TFLOPS
Released
2024
379 / 621 LLMs run Best: Mellum2.1 Thinking (12B-A2.5B) 53 / 61 Image models run Best: FLUX.2 [klein] 4B 12 / 43 Video models run Best: LTX-Video 2B 64 / 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 16.0 GB.

More about this hardware

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

Apps that run models well on the Apple M4 (16 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 (16 GB)

Best LLMs for the Apple M4 (16 GB)

Quality Model Quant Memory Speed Runs
66Good quality (B) · 66 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. Mellum2.1 Thinking (12B-A2.5B)JetBrains Q4_K_M 9.0 GB 43.3 tok/s Runs great
76Great quality (A) · 76 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. K2 Horizon 7BInstitute of Foundation Models Q4_K_M 8.2 GB 14.1 tok/s Runs well
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 9.4 GB 10.6 tok/s Runs welltight fit
74Great quality (A) · 74 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. MiMo V2.6 Distill Qwen 9BXiaomi Q4_K_M 7.5 GB 13.5 tok/s Runs well
74Great quality (A) · 74 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. SenseNova Loop 9B PreviewSenseTime Q4_K_M 7.8 GB 13.1 tok/s Runs well
59Good quality (B) · 59 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. Ling 3.0 Tiny (8B-A1.3B)Ant Group (inclusionAI) Q6_K 8.2 GB 54.4 tok/s Runs great
73Great quality (A) · 73 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. Ornith 1.5 9BDeepReinforce Q4_K_M 7.6 GB 13.1 tok/s Runs well
66Good quality (B) · 66 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. Nemotron 3.5 Bolt E4BNVIDIA Q4_K_M 6.5 GB 28.2 tok/s Runs well
72Great quality (A) · 72 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.5 9BAlibaba Q4_K_M 7.6 GB 13.1 tok/s Runs well
71Great quality (A) · 71 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. Ornith 1.0 9BDeepReinforce Q4_K_M 7.6 GB 13.1 tok/s Runs well
64Good quality (B) · 64 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. Gemma 4 E4BGoogle Q4_K_M 6.5 GB 28.2 tok/s Runs well
70Great quality (A) · 70 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. TMax 9BAi2 Q4_K_M 7.2 GB 14.2 tok/s Runs well

Best Image models for the Apple M4 (16 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 84/100 (quality, fit, speed and memory use) sets the ranking. FLUX.2 [klein] 4BBlack Forest Labs FP8 10.2 GB 16 s Runs welltight fit
84Great quality (A) · 84 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. FLUX 3 Image KleinBlack Forest Labs Q4 GGUF 10.2 GB 2.0 min Slowtight fit
78Great quality (A) · 78 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. Z-Image TurboAlibaba (Tongyi) Q4 GGUF 10.1 GB 52 s Slowtight fit
78Great quality (A) · 78 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. FLUX.2 [klein] 9BBlack Forest Labs Q4 GGUF 8.0 GB 40 s Runs wellencoder unloaded after use
79Great quality (A) · 79 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. ERNIE-Image TurboBaidu Q4 GGUF 7.4 GB 70 s Slowencoder unloaded after use
52Fair quality (C) · 52 of 100: how capable the model is at FP8, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. SDXL-Lightning (4-step)ByteDance FP8 5.6 GB 11 s Runs great

Best Video models for the Apple M4 (16 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 65/100 (quality, fit, speed and memory use) sets the ranking. LTX-Video 2BLightricks FP8 6.1 GB 6.9 min Runs wellencoder unloaded after use
55Good quality (B) · 55 of 100: how capable the model is at FP16, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. Wan 2.1 T2V 1.3BAlibaba FP16 8.4 GB 73.2 min Very slowencoder unloaded after use
74Great quality (A) · 74 of 100: how capable the model is at FP8, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. HY-OmniWeaving (8.3B, unified video)Tencent FP8 7.8 GB 3.0 h Very slowCPU offload
53Fair quality (C) · 53 of 100: how capable the model is at FP8, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. Wan 2.1 VACE 1.3BAlibaba FP8 8.0 GB 71.4 min Very slowencoder unloaded after use
35Basic quality (D) · 35 of 100: how capable the model is at FP16, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. AnimateDiff v3 (SD 1.5)Shanghai AI Lab FP16 4.7 GB 5.8 min Runs well

Best Decision models for the Apple M4 (16 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 2.3 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 2.3 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 2.3 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 2.0 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?