Best local LLMs for the Raspberry Pi 5 (16 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. 80Great quality (A) · 80 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. Gemma 4 12B Q5_K_M · 1.2 tok/s · Very slow
  2. 77Great quality (A) · 77 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. SenseNova Loop 9B Preview Q6_K · 1.3 tok/s · Very slow
  3. 76Great quality (A) · 76 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. Ornith 1.5 9B Q6_K · 1.3 tok/s · Very slow
  4. 75Great quality (A) · 75 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.5 9B Q6_K · 1.3 tok/s · Very slow
  5. 74Great quality (A) · 74 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. Ornith 1.0 9B Q6_K · 1.3 tok/s · Very slow

Coding at 32K context

  1. 77Great quality (A) · 77 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. SenseNova Loop 9B Preview Q6_K · 1.3 tok/s · Very slow
  2. 58Good quality (B) · 58 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. Maple Preview (20B-A1B) Q3_K_M · 14.5 tok/s · Runs well (tight fit)
  3. 65Good quality (B) · 65 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. Nanbeige4.2 3B Q5_K_M · 3.5 tok/s · Slow
  4. 80Great quality (A) · 80 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. Gemma 4 12B Q5_K_M · 1.2 tok/s · Very slow (tight fit)
  5. 61Good quality (B) · 61 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. Raon-1 mini Preview (30B-A4B) Q2_K · 6.5 tok/s · Slow (tight fit)

Reasoning at 32K context

  1. 77Great quality (A) · 77 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. SenseNova Loop 9B Preview Q6_K · 1.3 tok/s · Very slow
  2. 75Great quality (A) · 75 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.5 9B Q6_K · 1.3 tok/s · Very slow
  3. 58Good quality (B) · 58 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. Maple Preview (20B-A1B) Q3_K_M · 14.5 tok/s · Runs well (tight fit)
  4. 65Good quality (B) · 65 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. Nanbeige4.2 3B Q5_K_M · 3.5 tok/s · Slow
  5. 80Great quality (A) · 80 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. Gemma 4 12B Q5_K_M · 1.2 tok/s · Very slow (tight fit)

Documents (RAG) at 32K context

  1. 80Great quality (A) · 80 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. Gemma 4 12B Q5_K_M · 1.2 tok/s · Very slow (tight fit)
  2. 77Great quality (A) · 77 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. SenseNova Loop 9B Preview Q6_K · 1.3 tok/s · Very slow
  3. 76Great quality (A) · 76 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. Ornith 1.5 9B Q6_K · 1.3 tok/s · Very slow
  4. 75Great quality (A) · 75 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.5 9B Q6_K · 1.3 tok/s · Very slow
  5. 74Great quality (A) · 74 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. Ornith 1.0 9B Q6_K · 1.3 tok/s · Very slow

Agents & tools at 64K context

  1. 74Great quality (A) · 74 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. SenseNova Loop 9B Preview Q4_K_M · 1.8 tok/s · Very slow
  2. 67Good quality (B) · 67 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. Nemotron 3.5 Bolt E4B Q5_K_M · 3.2 tok/s · Slow
  3. 69Good quality (B) · 69 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. Gemma 4 12B Q3_K_M · 1.9 tok/s · Very slow (tight fit)
  4. 74Great quality (A) · 74 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. Ornith 1.5 9B Q5_K_M · 1.5 tok/s · Very slow
  5. 73Great quality (A) · 73 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. Qwen3.5 9B Q5_K_M · 1.5 tok/s · Very slow

Reverse engineering at 32K context

  1. 80Great quality (A) · 80 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. Gemma 4 12B Q5_K_M · 1.2 tok/s · Very slow (tight fit)
  2. 77Great quality (A) · 77 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. SenseNova Loop 9B Preview Q6_K · 1.3 tok/s · Very slow
  3. 76Great quality (A) · 76 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. Ornith 1.5 9B Q6_K · 1.3 tok/s · Very slow
  4. 75Great quality (A) · 75 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. Qwen3.5 9B Q6_K · 1.3 tok/s · Very slow
  5. 74Great quality (A) · 74 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. Ornith 1.0 9B Q6_K · 1.3 tok/s · Very slow

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?