Best local LLMs for the Intel Xeon D-1600 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 88/100 (quality, fit, speed and memory use) sets the ranking. gpt-oss 120B MXFP4 · 6.1 tok/s · Slow
  2. 81Great quality (A) · 81 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.8 Flash Next (125B-A6B) Q3_K_M · 6.2 tok/s · Slow (tight fit)
  3. 77Great quality (A) · 77 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. Ling 3.0 Flash (127B-A5B) Q4_K_M · 5.7 tok/s · Slow
  4. 87Excellent quality (A+) · 87 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. Nemotron 3.5 Bolt 74B-A9B Q4_K_M · 3.2 tok/s · Slow
  5. 78Great quality (A) · 78 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. Mistral Small 4 (119B-A6B) Q5_K_M · 4.0 tok/s · Slow

Coding at 32K context

  1. 81Great quality (A) · 81 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.8 Flash Next (125B-A6B) Q3_K_M · 6.2 tok/s · Slow (tight fit)
  2. 81Great quality (A) · 81 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. Laguna S 2.1 (118B-A8B) Q4_K_M · 3.6 tok/s · Slow
  3. 95Excellent quality (A+) · 95 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. Nanbeige4.3 33B Q8_0 · 0.5 tok/s · Very slow
  4. 87Excellent quality (A+) · 87 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. Nemotron 3.5 Bolt 74B-A9B Q4_K_M · 3.2 tok/s · Slow
  5. 78Great quality (A) · 78 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. Mistral Small 4 (119B-A6B) Q5_K_M · 4.0 tok/s · Slow

Reasoning at 32K context

  1. 81Great quality (A) · 81 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.8 Flash Next (125B-A6B) Q3_K_M · 6.2 tok/s · Slow (tight fit)
  2. 77Great quality (A) · 77 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. Ling 3.0 Flash (127B-A5B) Q4_K_M · 5.7 tok/s · Slow
  3. 95Excellent quality (A+) · 95 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. Nanbeige4.3 33B Q8_0 · 0.5 tok/s · Very slow
  4. 87Excellent quality (A+) · 87 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. Nemotron 3.5 Bolt 74B-A9B Q4_K_M · 3.2 tok/s · Slow
  5. 78Great quality (A) · 78 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. Mistral Small 4 (119B-A6B) Q5_K_M · 4.0 tok/s · Slow

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 88/100 (quality, fit, speed and memory use) sets the ranking. gpt-oss 120B MXFP4 · 6.1 tok/s · Slow
  2. 81Great quality (A) · 81 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.8 Flash Next (125B-A6B) Q3_K_M · 6.2 tok/s · Slow (tight fit)
  3. 77Great quality (A) · 77 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. Ling 3.0 Flash (127B-A5B) Q4_K_M · 5.7 tok/s · Slow
  4. 78Great quality (A) · 78 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. Mistral Small 4 (119B-A6B) Q5_K_M · 4.0 tok/s · Slow
  5. 78Great quality (A) · 78 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. Nemotron 3.5 Super VL 120B-A12B Q3_K_M · 3.1 tok/s · Slow

Agents & tools at 64K context

  1. 95Excellent quality (A+) · 95 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. Nanbeige4.3 33B Q8_0 · 0.5 tok/s · Very slow
  2. 81Great quality (A) · 81 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.8 Flash Next (125B-A6B) Q3_K_M · 6.2 tok/s · Slow (tight fit)
  3. 81Great quality (A) · 81 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. Laguna S 2.1 (118B-A8B) Q4_K_M · 3.6 tok/s · Slow
  4. 77Great quality (A) · 77 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. Ling 3.0 Flash (127B-A5B) Q4_K_M · 5.7 tok/s · Slow
  5. 87Excellent quality (A+) · 87 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. Nemotron 3.5 Bolt 74B-A9B Q4_K_M · 3.2 tok/s · Slow

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 · 6.1 tok/s · Slow
  2. 83Great quality (A) · 83 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. Devstral 2 (123B) Q5_K_M · 0.2 tok/s · Very slow (tight fit)
  3. 93Excellent quality (A+) · 93 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.5 27B Q8_0 · 0.5 tok/s · Very slow
  4. 81Great quality (A) · 81 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.8 Flash Next (125B-A6B) Q3_K_M · 6.2 tok/s · Slow (tight fit)
  5. 81Great quality (A) · 81 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. Laguna S 2.1 (118B-A8B) Q4_K_M · 3.6 tok/s · Slow

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?