Best local LLMs for the LattePanda 3 Delta (8 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. 59Good quality (B) · 59 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. MiniCPM5 2B Q6_K · 3.0 tok/s · Slow
  2. 57Good quality (B) · 57 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. Nemotron Labs Dory 1.0 4B Q3_K_M · 3.6 tok/s · Slow
  3. 55Good quality (B) · 55 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. Spark-X2.6 4B Q3_K_M · 3.5 tok/s · Slow
  4. 52Fair quality (C) · 52 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. Gemma 4 E2B Q3_K_M · 6.2 tok/s · Slow (tight fit)
  5. 51Fair quality (C) · 51 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. TMax 4B Q3_K_M · 3.4 tok/s · Slow

Coding at 32K context

  1. 57Good quality (B) · 57 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. MiniCPM5 2B Q4_K_M · 4.4 tok/s · Slow (tight fit)
  2. 46Fair quality (C) · 46 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. Spark-X2.6 4B Q2_K · 4.4 tok/s · Slow (tight fit)
  3. 52Fair quality (C) · 52 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. Gemma 4 E2B Q3_K_M · 6.2 tok/s · Slow (tight fit)
  4. 34Basic quality (D) · 34 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. MiniCPM5 1B Q4_K_M · 10.2 tok/s · Runs well
  5. 47Fair quality (C) · 47 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. LFM3-VL 2B Q4_K_M · 5.7 tok/s · Slow

Reasoning at 32K context

  1. 57Good quality (B) · 57 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. MiniCPM5 2B Q4_K_M · 4.4 tok/s · Slow (tight fit)
  2. 46Fair quality (C) · 46 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. Spark-X2.6 4B Q2_K · 4.4 tok/s · Slow (tight fit)
  3. 52Fair quality (C) · 52 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. Gemma 4 E2B Q3_K_M · 6.2 tok/s · Slow (tight fit)
  4. 41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. Jamba Reasoning 3B Q4_K_M · 3.4 tok/s · Slow
  5. 43Fair quality (C) · 43 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. Qwen3.5 4B Q2_K · 3.9 tok/s · Slow (tight fit)

Documents (RAG) at 32K context

  1. 52Fair quality (C) · 52 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. Gemma 4 E2B Q3_K_M · 6.2 tok/s · Slow (tight fit)
  2. 47Fair quality (C) · 47 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. LFM3-VL 2B Q4_K_M · 5.7 tok/s · Slow
  3. 57Good quality (B) · 57 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. MiniCPM5 2B Q4_K_M · 4.4 tok/s · Slow (tight fit)
  4. 41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. LFM2.5-VL 3B Q4_K_M · 3.5 tok/s · Slow
  5. 43Fair quality (C) · 43 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. Qwen3.5 4B Q2_K · 3.9 tok/s · Slow (tight fit)

Agents & tools at 64K context

  1. 39Basic quality (D) · 39 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. LFM3 1.7B Q2_K · 10.4 tok/s · Runs well
  2. 52Fair quality (C) · 52 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. Gemma 4 E2B Q3_K_M · 6.2 tok/s · 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 67/100 (quality, fit, speed and memory use) sets the ranking. MiniCPM5 1B Q4_K_M · 10.2 tok/s · Runs well
  4. 38Basic quality (D) · 38 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. TMax 2B Q4_K_M · 5.8 tok/s · Slow
  5. 47Fair quality (C) · 47 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. LFM3-VL 2B Q4_K_M · 5.7 tok/s · Slow

Reverse engineering at 32K context

  1. 57Good quality (B) · 57 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. MiniCPM5 2B Q4_K_M · 4.4 tok/s · Slow (tight fit)
  2. 52Fair quality (C) · 52 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. Gemma 4 E2B Q3_K_M · 6.2 tok/s · Slow (tight fit)
  3. 47Fair quality (C) · 47 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. LFM3-VL 2B Q4_K_M · 5.7 tok/s · Slow
  4. 46Fair quality (C) · 46 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. Spark-X2.6 4B Q2_K · 4.4 tok/s · Slow (tight fit)
  5. 41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. LFM2.5 2.6B Q4_K_M · 4.1 tok/s · 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?