Best local LLMs for the AMD Ryzen 9000 series (desktop) NAS (192 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. 93Excellent quality (A+) · 93 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.8 Flash Next (125B-A6B) Q5_K_M · 12.5 tok/s · Runs well
  2. 86Excellent quality (A+) · 86 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. Kolibri 1 (78B-A3.5B) Q4_K_M · 25.1 tok/s · Runs well
  3. 84Great quality (A) · 84 of 100: how capable the model is at MXFP4, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. gpt-oss 120B MXFP4 · 18.6 tok/s · Runs well
  4. 78Great quality (A) · 78 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. MiniMax M2.7 (230B-A10B) Q3_K_M · 11.8 tok/s · Runs well
  5. 78Great quality (A) · 78 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. Step 3.7 Flash (198B-A11B) Q3_K_M · 10.7 tok/s · Runs well

Coding at 32K context

  1. 93Excellent quality (A+) · 93 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.8 Flash Next (125B-A6B) Q5_K_M · 12.5 tok/s · Runs well
  2. 86Excellent quality (A+) · 86 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. Kolibri 1 (78B-A3.5B) Q4_K_M · 25.1 tok/s · Runs well
  3. 78Great quality (A) · 78 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. MiniMax M2.7 (230B-A10B) Q3_K_M · 11.8 tok/s · Runs well
  4. 78Great quality (A) · 78 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. Step 3.7 Flash (198B-A11B) Q3_K_M · 10.7 tok/s · Runs well
  5. 77Great quality (A) · 77 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. MiniMax M2.5 (230B-A10B) Q3_K_M · 11.8 tok/s · Runs well

Reasoning at 32K context

  1. 93Excellent quality (A+) · 93 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.8 Flash Next (125B-A6B) Q5_K_M · 12.5 tok/s · Runs well
  2. 86Excellent quality (A+) · 86 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. Kolibri 1 (78B-A3.5B) Q4_K_M · 25.1 tok/s · Runs well
  3. 78Great quality (A) · 78 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. MiniMax M2.7 (230B-A10B) Q3_K_M · 11.8 tok/s · Runs well
  4. 78Great quality (A) · 78 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. Step 3.7 Flash (198B-A11B) Q3_K_M · 10.7 tok/s · Runs well
  5. 77Great quality (A) · 77 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. MiniMax M2.5 (230B-A10B) Q3_K_M · 11.8 tok/s · Runs well

Documents (RAG) at 32K context

  1. 93Excellent quality (A+) · 93 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.8 Flash Next (125B-A6B) Q5_K_M · 12.5 tok/s · Runs well
  2. 86Excellent quality (A+) · 86 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. Kolibri 1 (78B-A3.5B) Q4_K_M · 25.1 tok/s · Runs well
  3. 84Great quality (A) · 84 of 100: how capable the model is at MXFP4, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. gpt-oss 120B MXFP4 · 18.6 tok/s · Runs well
  4. 78Great quality (A) · 78 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. MiniMax M2.7 (230B-A10B) Q3_K_M · 11.8 tok/s · Runs well
  5. 77Great quality (A) · 77 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. MiniMax M2.5 (230B-A10B) Q3_K_M · 11.8 tok/s · Runs well

Agents & tools at 64K context

  1. 93Excellent quality (A+) · 93 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.8 Flash Next (125B-A6B) Q5_K_M · 12.5 tok/s · Runs well
  2. 86Excellent quality (A+) · 86 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. Kolibri 1 (78B-A3.5B) Q4_K_M · 25.1 tok/s · Runs well
  3. 78Great quality (A) · 78 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. MiniMax M2.7 (230B-A10B) Q3_K_M · 11.8 tok/s · Runs well
  4. 78Great quality (A) · 78 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. Step 3.7 Flash (198B-A11B) Q3_K_M · 10.7 tok/s · Runs well
  5. 77Great quality (A) · 77 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. MiniMax M2.5 (230B-A10B) Q3_K_M · 11.8 tok/s · Runs well

Reverse engineering at 32K context

  1. 93Excellent quality (A+) · 93 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.8 Flash Next (125B-A6B) Q5_K_M · 12.5 tok/s · Runs well
  2. 84Great quality (A) · 84 of 100: how capable the model is at MXFP4, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. gpt-oss 120B MXFP4 · 18.6 tok/s · Runs well
  3. 88Excellent quality (A+) · 88 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.5 35B-A3B Q4_K_M · 28.5 tok/s · Runs well
  4. 85Excellent quality (A+) · 85 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. Devstral 2 (123B) Q6_K · 0.5 tok/s · Very slow
  5. 83Great quality (A) · 83 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. GLM-4.7 Flash (30B-A3B) Q4_K_M · 28.5 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?