Best local LLMs for the Apple iPhone SE (3rd generation)

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. 53Fair quality (C) · 53 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 1.7B Q4_K_M · 24.9 tok/s · Runs well (tight fit)
  2. 42Fair quality (C) · 42 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. LFM3-VL 2B Q3_K_M · 29.0 tok/s · Runs well (tight fit)
  3. 34Basic quality (D) · 34 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. MiniCPM5 1B Q4_K_M · 39.8 tok/s · Runs great
  4. 33Basic quality (D) · 33 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. MiniCPM-V 4.7 1B Q3_K_M · 35.9 tok/s · Runs great
  5. 30Basic quality (D) · 30 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. LFM2.5 1.2B Instruct Q4_K_M · 36.8 tok/s · Runs great

Coding at 32K context

  1. 39Basic quality (D) · 39 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. PaddleOCR-VL 1.6 0.9B Q4_K_M · 44.8 tok/s · Runs well (tight fit)
  2. 39Basic quality (D) · 39 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. LFM3 1.7B Q2_K · 40.8 tok/s · Runs well (tight fit)
  3. 39Basic quality (D) · 39 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. MiniCPM-OCR 1.0 1.3B Q4_K_M · 33.1 tok/s · Runs well (tight fit)
  4. 35Basic quality (D) · 35 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. LFM3-VL 2B Q2_K · 36.8 tok/s · Runs well (tight fit)
  5. 33Basic quality (D) · 33 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. MiniCPM-V 4.7 1B Q3_K_M · 35.9 tok/s · Runs well (tight fit)

Reasoning at 32K context

  1. 39Basic quality (D) · 39 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. PaddleOCR-VL 1.6 0.9B Q4_K_M · 44.8 tok/s · Runs well (tight fit)
  2. 39Basic quality (D) · 39 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. LFM3 1.7B Q2_K · 40.8 tok/s · Runs well (tight fit)
  3. 39Basic quality (D) · 39 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. MiniCPM-OCR 1.0 1.3B Q4_K_M · 33.1 tok/s · Runs well (tight fit)
  4. 35Basic quality (D) · 35 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. LFM3-VL 2B Q2_K · 36.8 tok/s · Runs well (tight fit)
  5. 33Basic quality (D) · 33 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. MiniCPM-V 4.7 1B Q3_K_M · 35.9 tok/s · Runs well (tight fit)

Documents (RAG) at 32K context

  1. 39Basic quality (D) · 39 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. PaddleOCR-VL 1.6 0.9B Q4_K_M · 44.8 tok/s · Runs well (tight fit)
  2. 39Basic quality (D) · 39 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. LFM3 1.7B Q2_K · 40.8 tok/s · Runs well (tight fit)
  3. 39Basic quality (D) · 39 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. MiniCPM-OCR 1.0 1.3B Q4_K_M · 33.1 tok/s · Runs well (tight fit)
  4. 35Basic quality (D) · 35 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. LFM3-VL 2B Q2_K · 36.8 tok/s · Runs well (tight fit)
  5. 33Basic quality (D) · 33 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. MiniCPM-V 4.7 1B Q3_K_M · 35.9 tok/s · Runs well (tight fit)

Agents & tools at 64K context

  1. 19Basic quality (D) · 19 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. Gemma 3 1B Q4_K_M · 43.0 tok/s · Runs great
  2. 19Basic quality (D) · 19 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. Granite 4.0 H 1B Q2_K · 48.4 tok/s · Runs well (tight fit)
  3. 18Basic quality (D) · 18 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.5 0.8B Q2_K · 81.2 tok/s · Runs well (tight fit)
  4. 20Basic quality (D) · 20 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. LFM2-VL 1.6B Q3_K_M · 35.2 tok/s · Runs well (tight fit)
  5. 16Basic quality (D) · 16 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. Qwen2.5-Math 1.5B Instruct Q3_K_M · 36.1 tok/s · Runs great

Reverse engineering at 32K context

  1. 39Basic quality (D) · 39 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. PaddleOCR-VL 1.6 0.9B Q4_K_M · 44.8 tok/s · Runs well (tight fit)
  2. 39Basic quality (D) · 39 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. LFM3 1.7B Q2_K · 40.8 tok/s · Runs well (tight fit)
  3. 39Basic quality (D) · 39 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. MiniCPM-OCR 1.0 1.3B Q4_K_M · 33.1 tok/s · Runs well (tight fit)
  4. 35Basic quality (D) · 35 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. LFM3-VL 2B Q2_K · 36.8 tok/s · Runs well (tight fit)
  5. 33Basic quality (D) · 33 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. MiniCPM-V 4.7 1B Q3_K_M · 35.9 tok/s · Runs well (tight fit)

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?