Best local LLMs for the Intel Celeron J1800 / N3710 / 3865U 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. 39Basic quality (D) · 39 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 1.7B Q2_K · 3.1 tok/s · Slow
  2. 42Fair quality (C) · 42 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. LFM3-VL 2B Q3_K_M · 2.2 tok/s · Very slow (tight fit)
  3. 34Basic quality (D) · 34 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. MiniCPM5 1B Q4_K_M · 3.0 tok/s · Slow
  4. 33Basic quality (D) · 33 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. TMax 2B Q3_K_M · 2.3 tok/s · Very slow (tight fit)
  5. 33Basic quality (D) · 33 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.5 2B Q3_K_M · 1.9 tok/s · Very 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 61/100 (quality, fit, speed and memory use) sets the ranking. PaddleOCR-VL 1.6 0.9B Q4_K_M · 3.4 tok/s · Slow (tight fit)
  2. 39Basic quality (D) · 39 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. LFM3 1.7B Q2_K · 3.1 tok/s · Slow (tight fit)
  3. 25Basic quality (D) · 25 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. MiniCPM5 1B Q2_K · 5.0 tok/s · Slow (tight fit)
  4. 35Basic quality (D) · 35 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. MiniCPM-OCR 1.0 1.3B Q3_K_M · 3.3 tok/s · Slow (tight fit)
  5. 35Basic quality (D) · 35 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. LFM3-VL 2B Q2_K · 2.8 tok/s · Very slow (tight fit)

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 61/100 (quality, fit, speed and memory use) sets the ranking. PaddleOCR-VL 1.6 0.9B Q4_K_M · 3.4 tok/s · Slow (tight fit)
  2. 39Basic quality (D) · 39 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. LFM3 1.7B Q2_K · 3.1 tok/s · Slow (tight fit)
  3. 25Basic quality (D) · 25 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. MiniCPM5 1B Q2_K · 5.0 tok/s · Slow (tight fit)
  4. 35Basic quality (D) · 35 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. MiniCPM-OCR 1.0 1.3B Q3_K_M · 3.3 tok/s · Slow (tight fit)
  5. 35Basic quality (D) · 35 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. LFM3-VL 2B Q2_K · 2.8 tok/s · Very slow (tight fit)

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 66/100 (quality, fit, speed and memory use) sets the ranking. PaddleOCR-VL 1.6 0.9B Q4_K_M · 3.4 tok/s · Slow (tight fit)
  2. 39Basic quality (D) · 39 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. LFM3 1.7B Q2_K · 3.1 tok/s · Slow (tight fit)
  3. 35Basic quality (D) · 35 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. MiniCPM-OCR 1.0 1.3B Q3_K_M · 3.3 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 63/100 (quality, fit, speed and memory use) sets the ranking. LFM3-VL 2B Q2_K · 2.8 tok/s · Very slow (tight fit)
  5. 28Basic quality (D) · 28 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-V 4.7 1B Q2_K · 3.5 tok/s · Slow (tight fit)

Agents & tools at 64K context

  1. 2Basic quality (D) · 2 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. Falcon-H1 Tiny 90M Instruct Q3_K_M · 47.0 tok/s · Runs great
  2. 7Basic quality (D) · 7 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. LFM2.5 230M Q2_K · 23.4 tok/s · Runs well
  3. 21Basic quality (D) · 21 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.5 0.8B Q3_K_M · 4.9 tok/s · Slow (tight fit)
  4. 19Basic quality (D) · 19 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking. Gemma 3 1B Q4_K_M · 3.3 tok/s · Slow
  5. 2Basic quality (D) · 2 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking. SmolLM2 135M Instruct Q2_K · 41.4 tok/s · Runs great

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 61/100 (quality, fit, speed and memory use) sets the ranking. PaddleOCR-VL 1.6 0.9B Q4_K_M · 3.4 tok/s · Slow (tight fit)
  2. 39Basic quality (D) · 39 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. LFM3 1.7B Q2_K · 3.1 tok/s · Slow (tight fit)
  3. 35Basic quality (D) · 35 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. MiniCPM-OCR 1.0 1.3B Q3_K_M · 3.3 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 58/100 (quality, fit, speed and memory use) sets the ranking. LFM3-VL 2B Q2_K · 2.8 tok/s · Very slow (tight fit)
  5. 28Basic quality (D) · 28 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. MiniCPM-V 4.7 1B Q2_K · 3.5 tok/s · 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?