Best local LLMs for the Apple iPhone 15 / 15 Plus

Each list assumes the context that task needs, so a model that fits for chat may rank lower for long documents.

General chat at 8K context

  1. 57Good quality (B) · 57 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. MiniCPM5 2B Q4_K_M · 25.6 tok/s · Runs well
  2. 53Fair quality (C) · 53 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. LFM3 1.7B Q4_K_M · 37.3 tok/s · Runs great
  3. 55Good quality (B) · 55 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. Spark-X2.6 4B Q3_K_M · 20.3 tok/s · Runs well (tight fit)
  4. 47Fair quality (C) · 47 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. LFM3-VL 2B Q4_K_M · 33.6 tok/s · Runs great
  5. 43Fair quality (C) · 43 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. Gemma 4 E2B Q2_K · 46.1 tok/s · Runs well (tight fit)

Coding at 32K context

  1. 53Fair quality (C) · 53 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. LFM3 1.7B Q4_K_M · 37.3 tok/s · Runs great
  2. 35Basic quality (D) · 35 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. MiniCPM5 1B Q6_K · 41.5 tok/s · Runs great
  3. 47Fair quality (C) · 47 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. LFM3-VL 2B Q4_K_M · 33.6 tok/s · Runs great
  4. 41Fair quality (C) · 41 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. PaddleOCR-VL 1.6 0.9B Q6_K · 46.7 tok/s · Runs great
  5. 43Fair quality (C) · 43 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. Gemma 4 E2B Q2_K · 46.1 tok/s · Runs well (tight fit)

Reasoning at 32K context

  1. 53Fair quality (C) · 53 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. LFM3 1.7B Q4_K_M · 37.3 tok/s · Runs great
  2. 35Basic quality (D) · 35 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. MiniCPM5 1B Q6_K · 41.5 tok/s · Runs great
  3. 47Fair quality (C) · 47 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. LFM3-VL 2B Q4_K_M · 33.6 tok/s · Runs great
  4. 36Basic quality (D) · 36 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. Jamba Reasoning 3B Q3_K_M · 26.1 tok/s · Runs well
  5. 41Fair quality (C) · 41 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. PaddleOCR-VL 1.6 0.9B Q6_K · 46.7 tok/s · Runs great

Documents (RAG) at 32K context

  1. 53Fair quality (C) · 53 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. LFM3 1.7B Q4_K_M · 37.3 tok/s · Runs great
  2. 47Fair quality (C) · 47 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. LFM3-VL 2B Q4_K_M · 33.6 tok/s · Runs great
  3. 41Fair quality (C) · 41 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. PaddleOCR-VL 1.6 0.9B Q6_K · 46.7 tok/s · Runs great
  4. 43Fair quality (C) · 43 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. Gemma 4 E2B Q2_K · 46.1 tok/s · Runs well (tight fit)
  5. 40Fair quality (C) · 40 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. MiniCPM-OCR 1.0 1.3B Q5_K_M · 41.0 tok/s · Runs great

Agents & tools at 64K context

  1. 53Fair quality (C) · 53 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. LFM3 1.7B Q4_K_M · 37.3 tok/s · Runs great
  2. 33Basic quality (D) · 33 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. TMax 2B Q3_K_M · 44.4 tok/s · Runs great
  3. 34Basic quality (D) · 34 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. MiniCPM5 1B Q5_K_M · 49.4 tok/s · Runs well (tight fit)
  4. 47Fair quality (C) · 47 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. LFM3-VL 2B Q4_K_M · 33.6 tok/s · Runs well (tight fit)
  5. 40Fair quality (C) · 40 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. MiniCPM-OCR 1.0 1.3B Q5_K_M · 41.0 tok/s · Runs great

Reverse engineering at 32K context

  1. 53Fair quality (C) · 53 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. LFM3 1.7B Q4_K_M · 37.3 tok/s · Runs great
  2. 47Fair quality (C) · 47 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. LFM3-VL 2B Q4_K_M · 33.6 tok/s · Runs great
  3. 41Fair quality (C) · 41 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. PaddleOCR-VL 1.6 0.9B Q6_K · 46.7 tok/s · Runs great
  4. 43Fair quality (C) · 43 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. Gemma 4 E2B Q2_K · 46.1 tok/s · Runs well (tight fit)
  5. 40Fair quality (C) · 40 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. MiniCPM-OCR 1.0 1.3B Q5_K_M · 41.0 tok/s · Runs great

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?