Best local LLMs for the Apple iPhone SE (2nd 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. 30Basic quality (D) · 30 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. MiniCPM5 1B Q3_K_M · 51.5 tok/s · Runs well (tight fit)
  2. 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)
  3. 28Basic quality (D) · 28 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. MiniCPM-V 4.7 1B Q2_K · 45.6 tok/s · Runs well (tight fit)
  4. 26Basic quality (D) · 26 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. LFM2.5 1.2B Instruct Q3_K_M · 47.5 tok/s · Runs well (tight fit)
  5. 25Basic quality (D) · 25 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.5 0.8B Q5_K_M · 40.9 tok/s · Runs well (tight fit)

Coding at 32K context

  1. 7Basic quality (D) · 7 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. Qwen2.5 Coder 0.5B Instruct Q4_K_M · 87.8 tok/s · Runs well (tight fit)
  2. 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. Gemma 3 1B Q3_K_M · 55.6 tok/s · Runs well (tight fit)
  3. 12Basic quality (D) · 12 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. Granite 4.0 H 350M Q8_0 · 64.4 tok/s · Runs great
  4. 14Basic quality (D) · 14 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. Qwen2.5-Math 1.5B Instruct Q2_K · 45.9 tok/s · Runs well (tight fit)
  5. 13Basic quality (D) · 13 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. Falcon-H1 0.5B Instruct Q6_K · 57.4 tok/s · Runs well (tight fit)

Reasoning at 32K context

  1. 14Basic quality (D) · 14 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. Qwen2.5-Math 1.5B Instruct Q2_K · 45.9 tok/s · Runs well (tight fit)
  2. 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. Gemma 3 1B Q3_K_M · 55.6 tok/s · Runs well (tight fit)
  3. 12Basic quality (D) · 12 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. Granite 4.0 H 350M Q8_0 · 64.4 tok/s · Runs great
  4. 13Basic quality (D) · 13 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. Falcon-H1 0.5B Instruct Q6_K · 57.4 tok/s · Runs well (tight fit)
  5. 13Basic quality (D) · 13 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. LFM2.5 350M Q6_K · 85.3 tok/s · Runs well (tight fit)

Documents (RAG) at 32K context

  1. 16Basic quality (D) · 16 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. Gemma 3 1B Q3_K_M · 55.6 tok/s · Runs well (tight fit)
  2. 12Basic quality (D) · 12 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. surya ocr 2.5 Q3_K_M · 80.6 tok/s · Runs well (tight fit)
  3. 6Basic quality (D) · 6 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. Gemma 3 270M Q8_0 · 81.1 tok/s · Runs great
  4. 7Basic quality (D) · 7 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. GLiDE 0.8B Q2_K · 94.2 tok/s · Runs well (tight fit)
  5. 3Basic quality (D) · 3 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. Falcon-H1 Tiny 90M Instruct Q8_0 · 243 tok/s · Runs great

Agents & tools at 64K context

  1. 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. Gemma 3 1B Q3_K_M · 55.6 tok/s · Runs well (tight fit)
  2. 12Basic quality (D) · 12 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. Granite 4.0 H 350M Q8_0 · 64.4 tok/s · Runs great
  3. 14Basic quality (D) · 14 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. Qwen2.5-Math 1.5B Instruct Q2_K · 45.9 tok/s · Runs well (tight fit)
  4. 13Basic quality (D) · 13 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. Falcon-H1 0.5B Instruct Q6_K · 57.4 tok/s · Runs well (tight fit)
  5. 11Basic quality (D) · 11 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. LFM2-VL 450M Q5_K_M · 79.0 tok/s · Runs well (tight fit)

Reverse engineering at 32K context

  1. 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. Gemma 3 1B Q3_K_M · 55.6 tok/s · Runs well (tight fit)
  2. 12Basic quality (D) · 12 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. Granite 4.0 H 350M Q8_0 · 64.4 tok/s · Runs great
  3. 14Basic quality (D) · 14 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. Qwen2.5-Math 1.5B Instruct Q2_K · 45.9 tok/s · Runs well (tight fit)
  4. 13Basic quality (D) · 13 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. Falcon-H1 0.5B Instruct Q6_K · 57.4 tok/s · Runs well (tight fit)
  5. 13Basic quality (D) · 13 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. LFM2.5 350M Q6_K · 85.3 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?