Best local LLMs for the AMD Ryzen 5 PRO 8640U NAS (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. 78Great quality (A) · 78 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. Gemma 4 12B Q4_K_M · 5.5 tok/s · Slow
  2. 57Good quality (B) · 57 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. Ling 3.0 Tiny (8B-A1.3B) Q4_K_M · 43.1 tok/s · Runs great
  3. 51Fair quality (C) · 51 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. LFM2.5 24B-A2B Q2_K · 38.6 tok/s · Runs well (tight fit)
  4. 66Good quality (B) · 66 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. Nemotron 3.5 Bolt E4B Q4_K_M · 14.5 tok/s · Runs well
  5. 66Good quality (B) · 66 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. Mellum2.1 Thinking (12B-A2.5B) Q4_K_M · 24.1 tok/s · Runs well

Coding at 32K context

  1. 66Good quality (B) · 66 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. Mellum2.1 Thinking (12B-A2.5B) Q4_K_M · 24.1 tok/s · Runs well
  2. 58Good quality (B) · 58 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. Maple Preview (20B-A1B) Q3_K_M · 48.0 tok/s · Runs well (tight fit)
  3. 64Good quality (B) · 64 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. Nanbeige4.2 3B Q4_K_M · 15.7 tok/s · Runs well
  4. 51Fair quality (C) · 51 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. LFM2.5 24B-A2B Q2_K · 38.6 tok/s · Runs well (tight fit)
  5. 78Great quality (A) · 78 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 12B Q4_K_M · 5.5 tok/s · Slow (tight fit)

Reasoning at 32K context

  1. 66Good quality (B) · 66 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. Mellum2.1 Thinking (12B-A2.5B) Q4_K_M · 24.1 tok/s · Runs well
  2. 58Good quality (B) · 58 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. Maple Preview (20B-A1B) Q3_K_M · 48.0 tok/s · Runs well (tight fit)
  3. 64Good quality (B) · 64 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. Nanbeige4.2 3B Q4_K_M · 15.7 tok/s · Runs well
  4. 51Fair quality (C) · 51 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. LFM2.5 24B-A2B Q2_K · 38.6 tok/s · Runs well (tight fit)
  5. 78Great quality (A) · 78 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 12B Q4_K_M · 5.5 tok/s · Slow (tight fit)

Documents (RAG) at 32K context

  1. 78Great quality (A) · 78 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 12B Q4_K_M · 5.5 tok/s · Slow (tight fit)
  2. 66Good quality (B) · 66 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. Nemotron 3.5 Bolt E4B Q4_K_M · 14.5 tok/s · Runs well
  3. 66Good quality (B) · 66 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. Mellum2.1 Thinking (12B-A2.5B) Q4_K_M · 24.1 tok/s · Runs well
  4. 64Good quality (B) · 64 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. Gemma 4 E4B Q4_K_M · 14.5 tok/s · Runs well
  5. 58Good quality (B) · 58 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. Maple Preview (20B-A1B) Q3_K_M · 48.0 tok/s · Runs well (tight fit)

Agents & tools at 64K context

  1. 66Good quality (B) · 66 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. Mellum2.1 Thinking (12B-A2.5B) Q4_K_M · 24.1 tok/s · Runs well
  2. 66Good quality (B) · 66 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. Nemotron 3.5 Bolt E4B Q4_K_M · 14.5 tok/s · Runs well
  3. 49Fair quality (C) · 49 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. LFM2.5 8B-A1B Q4_K_M · 38.1 tok/s · Runs great
  4. 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. Ling 3.0 Tiny (8B-A1.3B) Q4_K_M · 43.1 tok/s · Runs great
  5. 62Good quality (B) · 62 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. Spark-X2.6 4B Q4_K_M · 15.9 tok/s · Runs well

Reverse engineering at 32K context

  1. 66Good quality (B) · 66 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. Mellum2.1 Thinking (12B-A2.5B) Q4_K_M · 24.1 tok/s · Runs well
  2. 58Good quality (B) · 58 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. Maple Preview (20B-A1B) Q3_K_M · 48.0 tok/s · Runs well (tight fit)
  3. 78Great quality (A) · 78 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 12B Q4_K_M · 5.5 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 79/100 (quality, fit, speed and memory use) sets the ranking. Ling 3.0 Tiny (8B-A1.3B) Q4_K_M · 43.1 tok/s · Runs great
  5. 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 · 15.7 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?