Best local LLMs for the Intel Atom C3538 / C3558 NAS (4 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. 53Fair quality (C) · 53 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. LFM3 1.7B Q4_K_M · 5.7 tok/s · Slow (tight fit)
  2. 42Fair quality (C) · 42 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. LFM3-VL 2B Q3_K_M · 6.6 tok/s · Slow (tight fit)
  3. 30Basic quality (D) · 30 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. MiniCPM5 1B Q3_K_M · 11.8 tok/s · Runs well
  4. 39Basic quality (D) · 39 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. PaddleOCR-VL 1.6 0.9B Q4_K_M · 10.2 tok/s · Runs well
  5. 33Basic quality (D) · 33 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. TMax 2B Q3_K_M · 6.8 tok/s · Slow (tight fit)

Coding at 32K context

  1. 39Basic quality (D) · 39 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. PaddleOCR-VL 1.6 0.9B Q4_K_M · 10.2 tok/s · Runs well (tight fit)
  2. 25Basic quality (D) · 25 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. MiniCPM5 1B Q2_K · 14.9 tok/s · Runs well (tight fit)
  3. 39Basic quality (D) · 39 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. LFM3 1.7B Q2_K · 9.3 tok/s · Slow (tight fit)
  4. 35Basic quality (D) · 35 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. LFM3-VL 2B Q2_K · 8.4 tok/s · Slow (tight fit)
  5. 29Basic quality (D) · 29 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. MiniCPM-OCR 1.0 1.3B Q2_K · 12.4 tok/s · Runs well

Reasoning at 32K context

  1. 39Basic quality (D) · 39 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. PaddleOCR-VL 1.6 0.9B Q4_K_M · 10.2 tok/s · Runs well (tight fit)
  2. 25Basic quality (D) · 25 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. MiniCPM5 1B Q2_K · 14.9 tok/s · Runs well (tight fit)
  3. 39Basic quality (D) · 39 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. LFM3 1.7B Q2_K · 9.3 tok/s · Slow (tight fit)
  4. 35Basic quality (D) · 35 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. LFM3-VL 2B Q2_K · 8.4 tok/s · Slow (tight fit)
  5. 29Basic quality (D) · 29 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. MiniCPM-OCR 1.0 1.3B Q2_K · 12.4 tok/s · Runs well

Documents (RAG) at 32K context

  1. 39Basic quality (D) · 39 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. PaddleOCR-VL 1.6 0.9B Q4_K_M · 10.2 tok/s · Runs well (tight fit)
  2. 39Basic quality (D) · 39 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. LFM3 1.7B Q2_K · 9.3 tok/s · Slow (tight fit)
  3. 35Basic quality (D) · 35 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. LFM3-VL 2B Q2_K · 8.4 tok/s · Slow (tight fit)
  4. 29Basic quality (D) · 29 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. MiniCPM-OCR 1.0 1.3B Q2_K · 12.4 tok/s · Runs well
  5. 28Basic quality (D) · 28 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. MiniCPM-V 4.7 1B Q2_K · 10.4 tok/s · Runs well (tight fit)

Agents & tools at 64K context

  1. 9Basic quality (D) · 9 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. LFM2.5 230M Q4_K_M · 42.7 tok/s · Runs great
  2. 11Basic quality (D) · 11 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. LFM2.5 350M Q3_K_M · 36.3 tok/s · Runs well (tight fit)
  3. 8Basic quality (D) · 8 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. LFM2-VL 450M Q2_K · 35.8 tok/s · Runs great
  4. 21Basic quality (D) · 21 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.5 0.8B Q3_K_M · 14.6 tok/s · Runs well (tight fit)
  5. 10Basic quality (D) · 10 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. LFM2 350M Q3_K_M · 36.3 tok/s · Runs well (tight fit)

Reverse engineering at 32K context

  1. 39Basic quality (D) · 39 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. PaddleOCR-VL 1.6 0.9B Q4_K_M · 10.2 tok/s · Runs well (tight fit)
  2. 39Basic quality (D) · 39 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. LFM3 1.7B Q2_K · 9.3 tok/s · Slow (tight fit)
  3. 35Basic quality (D) · 35 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. LFM3-VL 2B Q2_K · 8.4 tok/s · Slow (tight fit)
  4. 29Basic quality (D) · 29 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. MiniCPM-OCR 1.0 1.3B Q2_K · 12.4 tok/s · Runs well
  5. 11Basic quality (D) · 11 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. LFM2.5 350M Q3_K_M · 36.3 tok/s · Runs great

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?