Best local LLMs for the Raspberry Pi 4 (2 GB)

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. 8Basic quality (D) · 8 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. LFM2.5 230M Q3_K_M · 36.8 tok/s · Runs great
  2. 9Basic quality (D) · 9 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. LFM2.5 350M Q2_K · 30.7 tok/s · Runs great
  3. 8Basic quality (D) · 8 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 350M Q2_K · 31.6 tok/s · Runs great
  4. 8Basic quality (D) · 8 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. LFM2 350M Q2_K · 30.7 tok/s · Runs great
  5. 4Basic quality (D) · 4 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. SmolVLM 256M Instruct Q2_K · 41.4 tok/s · Runs great

Coding at 32K context

  1. 8Basic quality (D) · 8 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. LFM2.5 230M Q3_K_M · 36.8 tok/s · Runs well (tight fit)
  2. 8Basic quality (D) · 8 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. Granite 4.0 H 350M Q2_K · 31.6 tok/s · Runs great
  3. 4Basic quality (D) · 4 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. SmolVLM 256M Instruct Q2_K · 41.4 tok/s · Runs great
  4. 4Basic quality (D) · 4 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. Gemma 3 270M Q2_K · 39.8 tok/s · Runs great
  5. 3Basic quality (D) · 3 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. SmolLM2 135M Instruct Q5_K_M · 41.6 tok/s · Runs great

Reasoning at 32K context

  1. 8Basic quality (D) · 8 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. LFM2.5 230M Q3_K_M · 36.8 tok/s · Runs well (tight fit)
  2. 8Basic quality (D) · 8 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. Granite 4.0 H 350M Q2_K · 31.6 tok/s · Runs great
  3. 4Basic quality (D) · 4 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. SmolVLM 256M Instruct Q2_K · 41.4 tok/s · Runs great
  4. 4Basic quality (D) · 4 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. Gemma 3 270M Q2_K · 39.8 tok/s · Runs great
  5. 3Basic quality (D) · 3 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. SmolLM2 135M Instruct Q5_K_M · 41.6 tok/s · Runs great

Documents (RAG) at 32K context

  1. 4Basic quality (D) · 4 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. Gemma 3 270M Q2_K · 39.8 tok/s · Runs great
  2. 2Basic quality (D) · 2 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 Tiny 90M Instruct Q6_K · 50.5 tok/s · Runs well (tight fit)
  3. 8Basic quality (D) · 8 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. LFM2.5 230M Q3_K_M · 36.8 tok/s · Runs well (tight fit)
  4. 8Basic quality (D) · 8 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. Granite 4.0 H 350M Q2_K · 31.6 tok/s · Runs great
  5. 4Basic quality (D) · 4 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. SmolVLM 256M Instruct Q2_K · 41.4 tok/s · Runs great

Agents & tools at 64K context

  1. 8Basic quality (D) · 8 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. Granite 4.0 H 350M Q2_K · 31.6 tok/s · Runs great
  2. 4Basic quality (D) · 4 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. SmolVLM 256M Instruct Q2_K · 41.4 tok/s · Runs great
  3. 4Basic quality (D) · 4 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. Gemma 3 270M Q2_K · 39.8 tok/s · Runs great
  4. 3Basic quality (D) · 3 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. SmolLM2 135M Instruct Q5_K_M · 41.6 tok/s · Runs great
  5. 1Basic quality (D) · 1 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. SmolLM 135M Instruct Q5_K_M · 41.6 tok/s · Runs great

Reverse engineering at 32K context

  1. 8Basic quality (D) · 8 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. LFM2.5 230M Q3_K_M · 36.8 tok/s · Runs well (tight fit)
  2. 8Basic quality (D) · 8 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. Granite 4.0 H 350M Q2_K · 31.6 tok/s · Runs great
  3. 4Basic quality (D) · 4 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. SmolVLM 256M Instruct Q2_K · 41.4 tok/s · Runs great
  4. 4Basic quality (D) · 4 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. Gemma 3 270M Q2_K · 39.8 tok/s · Runs great
  5. 3Basic quality (D) · 3 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. SmolLM2 135M Instruct Q5_K_M · 41.6 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?