Best local LLMs for the Intel Xeon D-1700 series NAS (96 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. 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 · 11.7 tok/s · Runs well
  2. 83Great quality (A) · 83 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-Next 80B-A3B Thinking Q5_K_M · 11.2 tok/s · Runs well
  3. 91Excellent quality (A+) · 91 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking. Nemotron 3.5 Bolt 74B-A9B Q6_K · 3.2 tok/s · Slow
  4. 79Great quality (A) · 79 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 Instruct Q4_K_M · 13.4 tok/s · Runs well
  5. 89Excellent quality (A+) · 89 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. Flint (40B-A2.5B) Q6_K · 11.2 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 92/100 (quality, fit, speed and memory use) sets the ranking. Kolibri 1 (78B-A3.5B) Q4_K_M · 11.7 tok/s · Runs well
  2. 83Great quality (A) · 83 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 Coder Next (80B-A3B) Q5_K_M · 11.2 tok/s · Runs well
  3. 83Great quality (A) · 83 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-Next 80B-A3B Thinking Q5_K_M · 11.2 tok/s · Runs well
  4. 91Excellent quality (A+) · 91 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking. Nemotron 3.5 Bolt 74B-A9B Q6_K · 3.2 tok/s · Slow
  5. 89Excellent quality (A+) · 89 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. Flint (40B-A2.5B) Q6_K · 11.2 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 92/100 (quality, fit, speed and memory use) sets the ranking. Kolibri 1 (78B-A3.5B) Q4_K_M · 11.7 tok/s · Runs well
  2. 83Great quality (A) · 83 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-Next 80B-A3B Thinking Q5_K_M · 11.2 tok/s · Runs well
  3. 91Excellent quality (A+) · 91 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking. Nemotron 3.5 Bolt 74B-A9B Q6_K · 3.2 tok/s · Slow
  4. 89Excellent quality (A+) · 89 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. Flint (40B-A2.5B) Q6_K · 11.2 tok/s · Runs well
  5. 95Excellent quality (A+) · 95 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. Nanbeige4.3 33B Q8_0 · 0.6 tok/s · Very slow

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 92/100 (quality, fit, speed and memory use) sets the ranking. Kolibri 1 (78B-A3.5B) Q4_K_M · 11.7 tok/s · Runs well
  2. 83Great quality (A) · 83 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 Coder Next (80B-A3B) Q5_K_M · 11.2 tok/s · Runs well
  3. 83Great quality (A) · 83 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-Next 80B-A3B Thinking Q5_K_M · 11.2 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 89/100 (quality, fit, speed and memory use) sets the ranking. Qwen3 Next 80B-A3B Instruct Q4_K_M · 13.4 tok/s · Runs well
  5. 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 · 8.6 tok/s · Slow (tight fit)

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 92/100 (quality, fit, speed and memory use) sets the ranking. Kolibri 1 (78B-A3.5B) Q4_K_M · 11.7 tok/s · Runs well
  2. 83Great quality (A) · 83 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 Coder Next (80B-A3B) Q5_K_M · 11.2 tok/s · Runs well
  3. 91Excellent quality (A+) · 91 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking. Nemotron 3.5 Bolt 74B-A9B Q6_K · 3.2 tok/s · Slow
  4. 95Excellent quality (A+) · 95 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. Nanbeige4.3 33B Q8_0 · 0.6 tok/s · Very slow
  5. 79Great quality (A) · 79 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 Instruct Q4_K_M · 13.4 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 88/100 (quality, fit, speed and memory use) sets the ranking. gpt-oss 120B MXFP4 · 8.6 tok/s · Slow (tight fit)
  2. 90Excellent quality (A+) · 90 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.5 35B-A3B Q5_K_M · 11.2 tok/s · Runs well
  3. 86Excellent quality (A+) · 86 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. Kolibri 1 (78B-A3.5B) Q4_K_M · 11.7 tok/s · Runs well
  4. 83Great quality (A) · 83 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. Qwen3 Coder Next (80B-A3B) Q5_K_M · 11.2 tok/s · Runs well
  5. 83Great quality (A) · 83 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. Qwen3-Next 80B-A3B Thinking Q5_K_M · 11.2 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?