Best local LLMs for the Apple iPhone 17e

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. 64Good quality (B) · 64 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. Nemotron Labs Dory 1.0 4B Q4_K_M · 21.7 tok/s · Runs well
  2. 58Good quality (B) · 58 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. Gemma 4 E2B Q4_K_M · 37.5 tok/s · Runs well (tight fit)
  3. 62Good quality (B) · 62 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. Spark-X2.6 4B Q4_K_M · 21.0 tok/s · Runs well
  4. 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 · 34.2 tok/s · Runs great
  5. 57Good quality (B) · 57 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. Nanbeige4.2 3B Q3_K_M · 26.7 tok/s · Runs well (tight fit)

Coding at 32K context

  1. 57Good quality (B) · 57 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. MiniCPM5 2B Q4_K_M · 34.2 tok/s · Runs great
  2. 62Good quality (B) · 62 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. Spark-X2.6 4B Q4_K_M · 21.0 tok/s · Runs well (tight fit)
  3. 58Good quality (B) · 58 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 E2B Q4_K_M · 37.5 tok/s · Runs well (tight fit)
  4. 47Fair quality (C) · 47 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. Nemotron Labs Dory 1.0 4B Q2_K · 35.6 tok/s · Runs well (tight fit)
  5. 54Fair quality (C) · 54 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. LFM3 1.7B Q5_K_M · 41.1 tok/s · Runs great

Reasoning at 32K context

  1. 57Good quality (B) · 57 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. MiniCPM5 2B Q4_K_M · 34.2 tok/s · Runs great
  2. 62Good quality (B) · 62 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. Spark-X2.6 4B Q4_K_M · 21.0 tok/s · Runs well (tight fit)
  3. 58Good quality (B) · 58 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 E2B Q4_K_M · 37.5 tok/s · Runs well (tight fit)
  4. 47Fair quality (C) · 47 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. Nemotron Labs Dory 1.0 4B Q2_K · 35.6 tok/s · Runs well (tight fit)
  5. 52Fair quality (C) · 52 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. Qwen3.5 4B Q3_K_M · 23.9 tok/s · Runs well (tight fit)

Documents (RAG) at 32K context

  1. 58Good quality (B) · 58 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. Gemma 4 E2B Q4_K_M · 37.5 tok/s · Runs well (tight fit)
  2. 54Fair quality (C) · 54 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. LFM3 1.7B Q5_K_M · 41.1 tok/s · Runs great
  3. 57Good quality (B) · 57 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 4B Q4_K_M · 20.5 tok/s · Runs well (tight fit)
  4. 57Good quality (B) · 57 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. MiniCPM5 2B Q4_K_M · 34.2 tok/s · Runs great
  5. 49Fair quality (C) · 49 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. Nemotron 3.5 Bolt E4B Q2_K · 31.4 tok/s · Runs well (tight fit)

Agents & tools at 64K context

  1. 54Fair quality (C) · 54 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. LFM3 1.7B Q5_K_M · 41.1 tok/s · Runs great
  2. 58Good quality (B) · 58 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 E2B Q4_K_M · 37.5 tok/s · Runs well (tight fit)
  3. 36Basic quality (D) · 36 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. MiniCPM5 1B Q8_0 · 40.6 tok/s · Runs great
  4. 38Basic quality (D) · 38 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. TMax 2B Q4_K_M · 45.8 tok/s · Runs great
  5. 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 · 44.9 tok/s · Runs great

Reverse engineering at 32K context

  1. 58Good quality (B) · 58 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 E2B Q4_K_M · 37.5 tok/s · Runs well (tight fit)
  2. 57Good quality (B) · 57 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. MiniCPM5 2B Q4_K_M · 34.2 tok/s · Runs great
  3. 62Good quality (B) · 62 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. Spark-X2.6 4B Q4_K_M · 21.0 tok/s · Runs well (tight fit)
  4. 54Fair quality (C) · 54 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. LFM3 1.7B Q5_K_M · 41.1 tok/s · Runs great
  5. 57Good quality (B) · 57 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. TMax 4B Q4_K_M · 20.5 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?