Best local LLMs for the Intel Core i3-N305 / Core 3 N355 NAS (48 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. 85Excellent quality (A+) · 85 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. Flint (40B-A2.5B) Q4_K_M · 11.3 tok/s · Runs well
  2. 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. Qwen3.8 27B Q8_0 · 0.5 tok/s · Very slow
  3. 94Excellent quality (A+) · 94 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. Nanbeige4.3 33B Q6_K · 0.6 tok/s · Very slow
  4. 94Excellent quality (A+) · 94 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. Qwen3.6 27B Q8_0 · 0.5 tok/s · Very slow
  5. 93Excellent quality (A+) · 93 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. Qwen3.5 27B Q8_0 · 0.5 tok/s · Very slow

Coding at 32K context

  1. 85Excellent quality (A+) · 85 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. Flint (40B-A2.5B) Q4_K_M · 11.3 tok/s · Runs well
  2. 93Excellent quality (A+) · 93 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.6 27B Q6_K · 0.7 tok/s · Very slow
  3. 94Excellent quality (A+) · 94 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. Nanbeige4.3 33B Q6_K · 0.6 tok/s · Very slow (tight fit)
  4. 91Excellent quality (A+) · 91 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. Muse Glimmer 30B Q6_K · 0.7 tok/s · Very slow
  5. 88Excellent quality (A+) · 88 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. Gemma 4 31B Q5_K_M · 0.8 tok/s · Very slow

Reasoning at 32K context

  1. 85Excellent quality (A+) · 85 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. Flint (40B-A2.5B) Q4_K_M · 11.3 tok/s · Runs well
  2. 93Excellent quality (A+) · 93 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.6 27B Q6_K · 0.7 tok/s · Very slow
  3. 94Excellent quality (A+) · 94 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. Nanbeige4.3 33B Q6_K · 0.6 tok/s · Very slow (tight fit)
  4. 91Excellent quality (A+) · 91 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. Muse Glimmer 30B Q6_K · 0.7 tok/s · Very slow
  5. 87Excellent quality (A+) · 87 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. Fara 1.5 27B Q6_K · 0.7 tok/s · Very slow

Documents (RAG) at 32K context

  1. 94Excellent quality (A+) · 94 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. Qwen3.8 27B Q6_K · 0.7 tok/s · Very slow
  2. 93Excellent quality (A+) · 93 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.6 27B Q6_K · 0.7 tok/s · Very slow
  3. 92Excellent quality (A+) · 92 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.5 27B Q6_K · 0.7 tok/s · Very slow
  4. 91Excellent quality (A+) · 91 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. Muse Glimmer 30B Q6_K · 0.7 tok/s · Very slow
  5. 89Excellent quality (A+) · 89 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. TMax 27B Q6_K · 0.7 tok/s · Very slow

Agents & tools at 64K context

  1. 85Excellent quality (A+) · 85 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. Flint (40B-A2.5B) Q4_K_M · 11.3 tok/s · Runs well
  2. 93Excellent quality (A+) · 93 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.6 27B Q6_K · 0.7 tok/s · Very slow
  3. 91Excellent quality (A+) · 91 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. Muse Glimmer 30B Q6_K · 0.7 tok/s · Very slow
  4. 90Excellent quality (A+) · 90 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. Nanbeige4.3 33B Q4_K_M · 0.9 tok/s · Very slow (tight fit)
  5. 78Great quality (A) · 78 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. MiniCPM-V 4.7 35B-A3B Q3_K_M · 12.2 tok/s · Runs well

Reverse engineering at 32K context

  1. 92Excellent quality (A+) · 92 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.5 27B Q6_K · 0.7 tok/s · Very slow
  2. 85Excellent quality (A+) · 85 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. Flint (40B-A2.5B) Q4_K_M · 11.3 tok/s · Runs well
  3. 78Great quality (A) · 78 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. Qwen3.5 35B-A3B Q3_K_M · 12.2 tok/s · Runs well
  4. 94Excellent quality (A+) · 94 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.8 27B Q6_K · 0.7 tok/s · Very slow
  5. 93Excellent quality (A+) · 93 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.6 27B Q6_K · 0.7 tok/s · Very 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?