Best local LLMs for the Intel Core 3 304 / Core 5 320 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. 92Excellent quality (A+) · 92 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.6 35B-A3B Q6_K · 10.7 tok/s · Runs well
  2. 92Excellent quality (A+) · 92 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.5 35B-A3B Q6_K · 10.7 tok/s · Runs well
  3. 92Excellent quality (A+) · 92 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. MiniCPM-V 4.7 35B-A3B Q6_K · 10.7 tok/s · Runs well
  4. 89Excellent quality (A+) · 89 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. Flint (40B-A2.5B) Q6_K · 12.7 tok/s · Runs well
  5. 91Excellent quality (A+) · 91 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. Nex N2 Mini (35B-A3B) Q6_K · 10.7 tok/s · Runs well

Coding at 32K context

  1. 92Excellent quality (A+) · 92 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. MiniCPM-V 4.7 35B-A3B Q6_K · 10.7 tok/s · Runs well
  2. 89Excellent quality (A+) · 89 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. Flint (40B-A2.5B) Q6_K · 12.7 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 93/100 (quality, fit, speed and memory use) sets the ranking. Nex N2 Mini (35B-A3B) Q6_K · 10.7 tok/s · Runs well
  4. 90Excellent quality (A+) · 90 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. Sage-A1.5 35B-A3B Q6_K · 10.7 tok/s · Runs well
  5. 90Excellent quality (A+) · 90 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking. KAT-Coder V2.5 Dev (35B-A3B) Q6_K · 10.7 tok/s · Runs well

Reasoning at 32K context

  1. 92Excellent quality (A+) · 92 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. MiniCPM-V 4.7 35B-A3B Q6_K · 10.7 tok/s · Runs well
  2. 89Excellent quality (A+) · 89 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. Flint (40B-A2.5B) Q6_K · 12.7 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 93/100 (quality, fit, speed and memory use) sets the ranking. Nex N2 Mini (35B-A3B) Q6_K · 10.7 tok/s · Runs well
  4. 90Excellent quality (A+) · 90 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. Sage-A1.5 35B-A3B Q6_K · 10.7 tok/s · Runs well
  5. 90Excellent quality (A+) · 90 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking. KAT-Coder V2.5 Dev (35B-A3B) Q6_K · 10.7 tok/s · Runs well

Documents (RAG) at 32K context

  1. 92Excellent quality (A+) · 92 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.6 35B-A3B Q6_K · 10.7 tok/s · Runs well
  2. 92Excellent quality (A+) · 92 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.5 35B-A3B Q6_K · 10.7 tok/s · Runs well
  3. 92Excellent quality (A+) · 92 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. MiniCPM-V 4.7 35B-A3B Q6_K · 10.7 tok/s · Runs well
  4. 89Excellent quality (A+) · 89 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking. Ornith 1.5 35B-A3B Q6_K · 10.7 tok/s · Runs well
  5. 88Excellent quality (A+) · 88 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking. Apodex 1.1 Mini (35B-A3B) Q6_K · 10.7 tok/s · Runs well

Agents & tools at 64K context

  1. 92Excellent quality (A+) · 92 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking. MiniCPM-V 4.7 35B-A3B Q6_K · 10.7 tok/s · Runs well
  2. 91Excellent quality (A+) · 91 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. Nex N2 Mini (35B-A3B) Q6_K · 10.7 tok/s · Runs well
  3. 89Excellent quality (A+) · 89 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. Flint (40B-A2.5B) Q6_K · 12.7 tok/s · Runs well
  4. 90Excellent quality (A+) · 90 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. Sage-A1.5 35B-A3B Q6_K · 10.7 tok/s · Runs well
  5. 90Excellent quality (A+) · 90 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. KAT-Coder V2.5 Dev (35B-A3B) Q6_K · 10.7 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 94/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.5 35B-A3B Q6_K · 10.7 tok/s · Runs well
  2. 87Excellent quality (A+) · 87 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. GLM-4.7 Flash (30B-A3B) Q6_K · 10.7 tok/s · Runs well
  3. 92Excellent quality (A+) · 92 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. Qwen3.6 35B-A3B Q6_K · 10.7 tok/s · Runs well
  4. 93Excellent quality (A+) · 93 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. Qwen3.5 27B Q8_0 · 0.9 tok/s · Very slow
  5. 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. MiniCPM-V 4.7 35B-A3B Q6_K · 10.7 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?