Best local LLMs for the Intel Xeon Silver (4100 to 4300 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 91/100 (quality, fit, speed and memory use) sets the ranking. gpt-oss 120B MXFP4 · 13.7 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 90/100 (quality, fit, speed and memory use) sets the ranking. Kolibri 1 (78B-A3.5B) Q4_K_M · 18.6 tok/s · Runs well
  3. 89Excellent quality (A+) · 89 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking. Nemotron 3.5 Super VL 120B-A12B Q4_K_M · 5.6 tok/s · Slow
  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 · 21.2 tok/s · Runs well
  5. 81Great quality (A) · 81 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.8 Flash Next (125B-A6B) Q3_K_M · 14.1 tok/s · Runs well (tight fit)

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 90/100 (quality, fit, speed and memory use) sets the ranking. Kolibri 1 (78B-A3.5B) Q4_K_M · 18.6 tok/s · Runs well
  2. 89Excellent quality (A+) · 89 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking. Nemotron 3.5 Super VL 120B-A12B Q4_K_M · 5.6 tok/s · Slow
  3. 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 · 21.2 tok/s · Runs well
  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 Coder Next (80B-A3B) Q4_K_M · 21.2 tok/s · Runs well
  5. 81Great quality (A) · 81 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.8 Flash Next (125B-A6B) Q3_K_M · 14.1 tok/s · Runs well (tight fit)

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 90/100 (quality, fit, speed and memory use) sets the ranking. Kolibri 1 (78B-A3.5B) Q4_K_M · 18.6 tok/s · Runs well
  2. 89Excellent quality (A+) · 89 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking. Nemotron 3.5 Super VL 120B-A12B Q4_K_M · 5.6 tok/s · Slow
  3. 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 · 21.2 tok/s · Runs well
  4. 81Great quality (A) · 81 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.8 Flash Next (125B-A6B) Q3_K_M · 14.1 tok/s · Runs well (tight fit)
  5. 77Great quality (A) · 77 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. Ling 3.0 Flash (127B-A5B) Q4_K_M · 12.9 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 91/100 (quality, fit, speed and memory use) sets the ranking. gpt-oss 120B MXFP4 · 13.7 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 90/100 (quality, fit, speed and memory use) sets the ranking. Kolibri 1 (78B-A3.5B) Q4_K_M · 18.6 tok/s · Runs well
  3. 89Excellent quality (A+) · 89 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking. Nemotron 3.5 Super VL 120B-A12B Q4_K_M · 5.6 tok/s · Slow
  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 · 21.2 tok/s · Runs well
  5. 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 Coder Next (80B-A3B) Q4_K_M · 21.2 tok/s · Runs well

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 91/100 (quality, fit, speed and memory use) sets the ranking. Kolibri 1 (78B-A3.5B) Q4_K_M · 18.6 tok/s · Runs well
  2. 89Excellent quality (A+) · 89 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking. Nemotron 3.5 Super VL 120B-A12B Q4_K_M · 5.6 tok/s · Slow
  3. 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 Coder Next (80B-A3B) Q4_K_M · 21.2 tok/s · Runs well
  4. 81Great quality (A) · 81 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.8 Flash Next (125B-A6B) Q3_K_M · 14.1 tok/s · Runs well (tight fit)
  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 · 21.2 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 91/100 (quality, fit, speed and memory use) sets the ranking. gpt-oss 120B MXFP4 · 13.7 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 87/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.5 35B-A3B Q4_K_M · 21.2 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 85/100 (quality, fit, speed and memory use) sets the ranking. Kolibri 1 (78B-A3.5B) Q4_K_M · 18.6 tok/s · Runs well
  4. 89Excellent quality (A+) · 89 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 Super VL 120B-A12B Q4_K_M · 5.6 tok/s · Slow
  5. 81Great quality (A) · 81 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. Qwen3-Next 80B-A3B Thinking Q4_K_M · 21.2 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?