Best local LLMs for the AMD EPYC 7002 / 7003 series NAS (128 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. 84Great quality (A) · 84 of 100: how capable the model is at MXFP4, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking. gpt-oss 120B MXFP4 · 26.7 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 94/100 (quality, fit, speed and memory use) sets the ranking. Kolibri 1 (78B-A3.5B) Q4_K_M · 35.5 tok/s · Runs great
  3. 81Great quality (A) · 81 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. Qwen3-Next 80B-A3B Thinking Q4_K_M · 40.2 tok/s · Runs great
  4. 91Excellent quality (A+) · 91 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. Nemotron 3.5 Bolt 74B-A9B Q6_K · 10.4 tok/s · Runs well
  5. 88Excellent quality (A+) · 88 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. Ornith 1.5 122B-A10B Q4_K_M · 13.3 tok/s · Runs well

Coding at 32K context

  1. 86Excellent quality (A+) · 86 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking. Kolibri 1 (78B-A3.5B) Q4_K_M · 35.5 tok/s · Runs great
  2. 81Great quality (A) · 81 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking. Qwen3-Next 80B-A3B Thinking Q4_K_M · 40.2 tok/s · Runs great
  3. 81Great quality (A) · 81 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. Qwen3 Coder Next (80B-A3B) Q4_K_M · 40.2 tok/s · Runs great
  4. 91Excellent quality (A+) · 91 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. Nemotron 3.5 Bolt 74B-A9B Q6_K · 10.4 tok/s · Runs well
  5. 88Excellent quality (A+) · 88 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. Ornith 1.5 122B-A10B Q4_K_M · 13.3 tok/s · Runs well

Reasoning at 32K context

  1. 86Excellent quality (A+) · 86 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking. Kolibri 1 (78B-A3.5B) Q4_K_M · 35.5 tok/s · Runs great
  2. 81Great quality (A) · 81 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking. Qwen3-Next 80B-A3B Thinking Q4_K_M · 40.2 tok/s · Runs great
  3. 91Excellent quality (A+) · 91 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. Nemotron 3.5 Bolt 74B-A9B Q6_K · 10.4 tok/s · Runs well
  4. 88Excellent quality (A+) · 88 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. Ornith 1.5 122B-A10B Q4_K_M · 13.3 tok/s · Runs well
  5. 89Excellent quality (A+) · 89 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. Nemotron 3.5 Super VL 120B-A12B Q4_K_M · 11.2 tok/s · Runs well

Documents (RAG) at 32K context

  1. 84Great quality (A) · 84 of 100: how capable the model is at MXFP4, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking. gpt-oss 120B MXFP4 · 26.7 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 94/100 (quality, fit, speed and memory use) sets the ranking. Kolibri 1 (78B-A3.5B) Q4_K_M · 35.5 tok/s · Runs great
  3. 81Great quality (A) · 81 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking. Qwen3-Next 80B-A3B Thinking Q4_K_M · 40.2 tok/s · Runs great
  4. 81Great quality (A) · 81 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. Qwen3 Coder Next (80B-A3B) Q4_K_M · 40.2 tok/s · Runs great
  5. 79Great quality (A) · 79 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. Qwen3 Next 80B-A3B Instruct Q4_K_M · 40.2 tok/s · Runs great

Agents & tools at 64K context

  1. 86Excellent quality (A+) · 86 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking. Kolibri 1 (78B-A3.5B) Q4_K_M · 35.5 tok/s · Runs great
  2. 81Great quality (A) · 81 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking. Qwen3 Coder Next (80B-A3B) Q4_K_M · 40.2 tok/s · Runs great
  3. 91Excellent quality (A+) · 91 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. Nemotron 3.5 Bolt 74B-A9B Q6_K · 10.4 tok/s · Runs well
  4. 79Great quality (A) · 79 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. Qwen3 Next 80B-A3B Instruct Q4_K_M · 40.2 tok/s · Runs great
  5. 88Excellent quality (A+) · 88 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. Ornith 1.5 122B-A10B Q4_K_M · 13.3 tok/s · Runs well

Reverse engineering at 32K context

  1. 84Great quality (A) · 84 of 100: how capable the model is at MXFP4, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking. gpt-oss 120B MXFP4 · 26.7 tok/s · Runs well
  2. 88Excellent quality (A+) · 88 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.5 35B-A3B Q4_K_M · 40.2 tok/s · Runs great
  3. 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 · 35.5 tok/s · Runs great
  4. 81Great quality (A) · 81 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. Qwen3-Next 80B-A3B Thinking Q4_K_M · 40.2 tok/s · Runs great
  5. 81Great quality (A) · 81 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. Qwen3 Coder Next (80B-A3B) Q4_K_M · 40.2 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?