Best local LLMs for the AMD EPYC 7002 / 7003 series NAS (64 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. 87Excellent quality (A+) · 87 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 98/100 (quality, fit, speed and memory use) sets the ranking. Flint (40B-A2.5B) Q5_K_M · 39.7 tok/s · Runs great
  2. 86Excellent quality (A+) · 86 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 97/100 (quality, fit, speed and memory use) sets the ranking. Kolibri 1 (78B-A3.5B) Q4_K_M · 35.5 tok/s · Runs well (tight fit)
  3. 88Excellent quality (A+) · 88 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 96/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.6 35B-A3B Q4_K_M · 40.2 tok/s · Runs great
  4. 88Excellent quality (A+) · 88 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 96/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.5 35B-A3B 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 96/100 (quality, fit, speed and memory use) sets the ranking. MiniCPM-V 4.7 35B-A3B Q4_K_M · 40.2 tok/s · Runs great

Coding at 32K context

  1. 87Excellent quality (A+) · 87 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 98/100 (quality, fit, speed and memory use) sets the ranking. Flint (40B-A2.5B) Q5_K_M · 39.7 tok/s · Runs great
  2. 86Excellent quality (A+) · 86 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 97/100 (quality, fit, speed and memory use) sets the ranking. Kolibri 1 (78B-A3.5B) Q4_K_M · 35.5 tok/s · Runs well (tight fit)
  3. 88Excellent quality (A+) · 88 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 96/100 (quality, fit, speed and memory use) sets the ranking. MiniCPM-V 4.7 35B-A3B Q4_K_M · 40.2 tok/s · Runs great
  4. 87Excellent quality (A+) · 87 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. Nex N2 Mini (35B-A3B) 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 95/100 (quality, fit, speed and memory use) sets the ranking. Qwen3 Coder Next (80B-A3B) Q4_K_M · 40.2 tok/s · Runs well (tight fit)

Reasoning at 32K context

  1. 87Excellent quality (A+) · 87 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 98/100 (quality, fit, speed and memory use) sets the ranking. Flint (40B-A2.5B) Q5_K_M · 39.7 tok/s · Runs great
  2. 86Excellent quality (A+) · 86 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 97/100 (quality, fit, speed and memory use) sets the ranking. Kolibri 1 (78B-A3.5B) Q4_K_M · 35.5 tok/s · Runs well (tight fit)
  3. 88Excellent quality (A+) · 88 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 96/100 (quality, fit, speed and memory use) sets the ranking. MiniCPM-V 4.7 35B-A3B Q4_K_M · 40.2 tok/s · Runs great
  4. 87Excellent quality (A+) · 87 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. Nex N2 Mini (35B-A3B) Q4_K_M · 40.2 tok/s · Runs great
  5. 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. Sage-A1.5 35B-A3B Q4_K_M · 40.2 tok/s · Runs great

Documents (RAG) 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 97/100 (quality, fit, speed and memory use) sets the ranking. Kolibri 1 (78B-A3.5B) Q4_K_M · 35.5 tok/s · Runs well (tight fit)
  2. 88Excellent quality (A+) · 88 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 96/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.6 35B-A3B Q4_K_M · 40.2 tok/s · Runs great
  3. 88Excellent quality (A+) · 88 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 96/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.5 35B-A3B Q4_K_M · 40.2 tok/s · Runs great
  4. 88Excellent quality (A+) · 88 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 96/100 (quality, fit, speed and memory use) sets the ranking. MiniCPM-V 4.7 35B-A3B 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 95/100 (quality, fit, speed and memory use) sets the ranking. Qwen3 Coder Next (80B-A3B) Q4_K_M · 40.2 tok/s · Runs well (tight fit)

Agents & tools at 64K context

  1. 87Excellent quality (A+) · 87 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 99/100 (quality, fit, speed and memory use) sets the ranking. Flint (40B-A2.5B) Q5_K_M · 39.7 tok/s · Runs great
  2. 86Excellent quality (A+) · 86 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 97/100 (quality, fit, speed and memory use) sets the ranking. Kolibri 1 (78B-A3.5B) Q4_K_M · 35.5 tok/s · Runs well (tight fit)
  3. 88Excellent quality (A+) · 88 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 96/100 (quality, fit, speed and memory use) sets the ranking. MiniCPM-V 4.7 35B-A3B Q4_K_M · 40.2 tok/s · Runs great
  4. 87Excellent quality (A+) · 87 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 96/100 (quality, fit, speed and memory use) sets the ranking. Nex N2 Mini (35B-A3B) Q4_K_M · 40.2 tok/s · Runs great
  5. 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. Sage-A1.5 35B-A3B Q4_K_M · 40.2 tok/s · Runs great

Reverse engineering at 32K context

  1. 88Excellent quality (A+) · 88 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 96/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.5 35B-A3B Q4_K_M · 40.2 tok/s · Runs great
  2. 87Excellent quality (A+) · 87 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. Flint (40B-A2.5B) Q5_K_M · 39.7 tok/s · Runs great
  3. 83Great quality (A) · 83 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. GLM-4.7 Flash (30B-A3B) Q4_K_M · 40.2 tok/s · Runs great
  4. 86Excellent quality (A+) · 86 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking. Kolibri 1 (78B-A3.5B) Q4_K_M · 35.5 tok/s · Runs well (tight fit)
  5. 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. Qwen3.6 35B-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?