Best local LLMs for the Raspberry Pi 5 (8 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. 67Good quality (B) · 67 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. Nemotron Labs Dory 1.0 4B Q6_K · 3.0 tok/s · Slow
  2. 64Good quality (B) · 64 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. Nanbeige4.2 3B Q4_K_M · 4.2 tok/s · Slow
  3. 66Good quality (B) · 66 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. Nemotron 3.5 Bolt E4B Q4_K_M · 3.9 tok/s · Slow (tight fit)
  4. 64Good quality (B) · 64 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. Spark-X2.6 4B Q5_K_M · 3.5 tok/s · Slow
  5. 57Good quality (B) · 57 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. Ling 3.0 Tiny (8B-A1.3B) Q4_K_M · 12.9 tok/s · Runs well (tight fit)

Coding at 32K context

  1. 64Good quality (B) · 64 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. Nemotron Labs Dory 1.0 4B Q4_K_M · 4.4 tok/s · Slow
  2. 64Good quality (B) · 64 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. Spark-X2.6 4B Q5_K_M · 3.5 tok/s · Slow
  3. 54Fair quality (C) · 54 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. MiMo V2.6 Distill Qwen 9B Q2_K · 3.1 tok/s · Slow (tight fit)
  4. 50Fair quality (C) · 50 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. Ling 3.0 Tiny (8B-A1.3B) Q3_K_M · 16.5 tok/s · Runs well (tight fit)
  5. 58Good quality (B) · 58 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. Qwen3.5 4B Q4_K_M · 3.8 tok/s · Slow

Reasoning at 32K context

  1. 64Good quality (B) · 64 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. Nemotron Labs Dory 1.0 4B Q4_K_M · 4.4 tok/s · Slow
  2. 64Good quality (B) · 64 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. Spark-X2.6 4B Q5_K_M · 3.5 tok/s · Slow
  3. 58Good quality (B) · 58 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. Qwen3.5 4B Q4_K_M · 3.8 tok/s · Slow
  4. 54Fair quality (C) · 54 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. MiMo V2.6 Distill Qwen 9B Q2_K · 3.1 tok/s · Slow (tight fit)
  5. 53Fair quality (C) · 53 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.5 9B Q2_K · 3.0 tok/s · Very slow (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 76/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.5 4B Q4_K_M · 3.8 tok/s · Slow
  2. 41Fair quality (C) · 41 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. Unlimited OCR 2 (3B-A0.6B) Q4_K_M · 26.5 tok/s · Runs well
  3. 59Good quality (B) · 59 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. TMax 4B Q5_K_M · 3.4 tok/s · Slow
  4. 58Good quality (B) · 58 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. Nemotron 3.5 Bolt E4B Q3_K_M · 5.0 tok/s · Slow (tight fit)
  5. 58Good quality (B) · 58 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. Agents-A1 4B Q5_K_M · 3.2 tok/s · Slow

Agents & tools at 64K context

  1. 62Good quality (B) · 62 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. Spark-X2.6 4B Q4_K_M · 4.3 tok/s · Slow (tight fit)
  2. 58Good quality (B) · 58 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. Nemotron 3.5 Bolt E4B Q3_K_M · 5.0 tok/s · Slow (tight fit)
  3. 59Good quality (B) · 59 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. TMax 4B Q5_K_M · 3.4 tok/s · Slow (tight fit)
  4. 57Good quality (B) · 57 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. Agents-A1 4B Q4_K_M · 3.9 tok/s · Slow (tight fit)
  5. 55Good quality (B) · 55 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. Fara 1.5 4B Q4_K_M · 3.9 tok/s · Slow (tight fit)

Reverse engineering at 32K context

  1. 64Good quality (B) · 64 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. Nemotron Labs Dory 1.0 4B Q4_K_M · 4.4 tok/s · Slow
  2. 64Good quality (B) · 64 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. Spark-X2.6 4B Q5_K_M · 3.5 tok/s · Slow
  3. 50Fair quality (C) · 50 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. Ling 3.0 Tiny (8B-A1.3B) Q3_K_M · 16.5 tok/s · Runs well (tight fit)
  4. 58Good quality (B) · 58 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. Qwen3.5 4B Q4_K_M · 3.8 tok/s · Slow
  5. 41Fair quality (C) · 41 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. Unlimited OCR 2 (3B-A0.6B) Q4_K_M · 26.5 tok/s · Runs well

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?