Best local LLMs for the Intel Celeron J3455 / N3450 (Apollo Lake) NAS (16 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. 79Great quality (A) · 79 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. K2 Horizon 7B Q6_K · 0.4 tok/s · Very slow
  2. 78Great quality (A) · 78 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. Gemma 4 12B Q4_K_M · 0.4 tok/s · Very slow
  3. 77Great quality (A) · 77 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. SenseNova Loop 9B Preview Q6_K · 0.4 tok/s · Very slow
  4. 76Great quality (A) · 76 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. Ornith 1.5 9B Q6_K · 0.4 tok/s · Very slow
  5. 75Great quality (A) · 75 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.5 9B Q6_K · 0.4 tok/s · Very slow

Coding at 32K context

  1. 75Great quality (A) · 75 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. MiMo V2.6 Distill Qwen 9B Q5_K_M · 0.4 tok/s · Very slow
  2. 77Great quality (A) · 77 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. SenseNova Loop 9B Preview Q6_K · 0.4 tok/s · Very slow (tight fit)
  3. 76Great quality (A) · 76 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. K2 Horizon 7B Q4_K_M · 0.6 tok/s · Very slow (tight fit)
  4. 64Good quality (B) · 64 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. Nanbeige4.2 3B Q4_K_M · 1.2 tok/s · Very slow
  5. 78Great quality (A) · 78 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. Gemma 4 12B Q4_K_M · 0.4 tok/s · Very slow (tight fit)

Reasoning at 32K context

  1. 75Great quality (A) · 75 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. MiMo V2.6 Distill Qwen 9B Q5_K_M · 0.4 tok/s · Very slow
  2. 77Great quality (A) · 77 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. SenseNova Loop 9B Preview Q6_K · 0.4 tok/s · Very slow (tight fit)
  3. 76Great quality (A) · 76 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. K2 Horizon 7B Q4_K_M · 0.6 tok/s · Very slow (tight fit)
  4. 73Great quality (A) · 73 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.5 9B Q5_K_M · 0.4 tok/s · Very slow
  5. 64Good quality (B) · 64 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. Nanbeige4.2 3B Q4_K_M · 1.2 tok/s · Very slow

Documents (RAG) at 32K context

  1. 78Great quality (A) · 78 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. Gemma 4 12B Q4_K_M · 0.4 tok/s · Very slow (tight fit)
  2. 77Great quality (A) · 77 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. SenseNova Loop 9B Preview Q6_K · 0.4 tok/s · Very slow (tight fit)
  3. 74Great quality (A) · 74 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. Ornith 1.5 9B Q5_K_M · 0.4 tok/s · Very slow
  4. 73Great quality (A) · 73 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.5 9B Q5_K_M · 0.4 tok/s · Very slow
  5. 73Great quality (A) · 73 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. TMax 9B Q6_K · 0.4 tok/s · Very slow

Agents & tools at 64K context

  1. 77Great quality (A) · 77 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. MiMo V2.6 Distill Qwen 9B Q6_K · 0.4 tok/s · Very slow (tight fit)
  2. 74Great quality (A) · 74 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. SenseNova Loop 9B Preview Q4_K_M · 0.5 tok/s · Very slow (tight fit)
  3. 69Good quality (B) · 69 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. Nemotron 3.5 Bolt E4B Q6_K · 0.8 tok/s · Very slow
  4. 66Good quality (B) · 66 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. UI-Mate 9B Q4_K_M · 0.5 tok/s · Very slow
  5. 66Good quality (B) · 66 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. UI-Venus 2 9B Q4_K_M · 0.5 tok/s · Very slow

Reverse engineering at 32K context

  1. 78Great quality (A) · 78 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. Gemma 4 12B Q4_K_M · 0.4 tok/s · Very slow (tight fit)
  2. 75Great quality (A) · 75 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. MiMo V2.6 Distill Qwen 9B Q5_K_M · 0.4 tok/s · Very slow
  3. 77Great quality (A) · 77 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. SenseNova Loop 9B Preview Q6_K · 0.4 tok/s · Very slow (tight fit)
  4. 74Great quality (A) · 74 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. Ornith 1.5 9B Q5_K_M · 0.4 tok/s · Very slow
  5. 76Great quality (A) · 76 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. K2 Horizon 7B Q4_K_M · 0.6 tok/s · Very slow (tight fit)

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?