Best local LLMs for the LattePanda Sigma (32 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. 77Great quality (A) · 77 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. Gemma 4 26B-A4B Q3_K_M · 29.5 tok/s · Runs well (tight fit)
  2. 70Great quality (A) · 70 of 100: how capable the model is at MXFP4, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. gpt-oss 20B MXFP4 · 26.0 tok/s · Runs well (tight fit)
  3. 62Good quality (B) · 62 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. LFM2.5 24B-A2B Q3_K_M · 43.5 tok/s · Runs well (tight fit)
  4. 61Good quality (B) · 61 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. GLM-4.7 Flash (30B-A3B) Q2_K · 45.1 tok/s · Runs well (tight fit)
  5. 60Good quality (B) · 60 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. Qwen AgentWorld 35B-A3B Q2_K · 45.1 tok/s · Runs well (tight fit)

Coding at 32K context

  1. 66Good quality (B) · 66 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. Maple Preview (20B-A1B) Q4_K_M · 53.0 tok/s · Runs well (tight fit)
  2. 66Good quality (B) · 66 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. Mellum2.1 Thinking (12B-A2.5B) Q4_K_M · 34.0 tok/s · Runs great
  3. 64Good quality (B) · 64 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. Gemma 4 26B-A4B Q2_K · 36.7 tok/s · Runs well (tight fit)
  4. 62Good quality (B) · 62 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. LFM2.5 24B-A2B Q3_K_M · 43.5 tok/s · Runs well (tight fit)
  5. 76Great quality (A) · 76 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. K2 Horizon 7B Q4_K_M · 10.7 tok/s · Runs well

Reasoning at 32K context

  1. 66Good quality (B) · 66 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. Maple Preview (20B-A1B) Q4_K_M · 53.0 tok/s · Runs well (tight fit)
  2. 66Good quality (B) · 66 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. Mellum2.1 Thinking (12B-A2.5B) Q4_K_M · 34.0 tok/s · Runs great
  3. 70Great quality (A) · 70 of 100: how capable the model is at MXFP4, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. gpt-oss 20B MXFP4 · 26.0 tok/s · Runs well (tight fit)
  4. 62Good quality (B) · 62 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. LFM2.5 24B-A2B Q3_K_M · 43.5 tok/s · Runs well (tight fit)
  5. 76Great quality (A) · 76 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. K2 Horizon 7B Q4_K_M · 10.7 tok/s · Runs well

Documents (RAG) at 32K context

  1. 64Good quality (B) · 64 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. Gemma 4 26B-A4B Q2_K · 36.7 tok/s · Runs well (tight fit)
  2. 56Good quality (B) · 56 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. Nemotron Cascade 2 30B-A3B Q2_K · 39.5 tok/s · Runs well (tight fit)
  3. 69Good quality (B) · 69 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. Gemma 4 12B Q3_K_M · 10.4 tok/s · Runs well
  4. 66Good quality (B) · 66 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. Maple Preview (20B-A1B) Q4_K_M · 53.0 tok/s · Runs well (tight fit)
  5. 57Good quality (B) · 57 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. Kimi-VL A3B Thinking 2506 Q4_K_M · 28.9 tok/s · Runs well

Agents & tools at 64K context

  1. 66Good quality (B) · 66 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. Mellum2.1 Thinking (12B-A2.5B) Q4_K_M · 34.0 tok/s · Runs great
  2. 70Great quality (A) · 70 of 100: how capable the model is at MXFP4, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. gpt-oss 20B MXFP4 · 26.0 tok/s · Runs well (tight fit)
  3. 64Good quality (B) · 64 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. Gemma 4 26B-A4B Q2_K · 36.7 tok/s · Runs well (tight fit)
  4. 62Good quality (B) · 62 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. LFM2.5 24B-A2B Q3_K_M · 43.5 tok/s · Runs well (tight fit)
  5. 61Good quality (B) · 61 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. Raon-1 mini Preview (30B-A4B) Q2_K · 32.9 tok/s · Runs well (tight fit)

Reverse engineering at 32K context

  1. 70Great quality (A) · 70 of 100: how capable the model is at MXFP4, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. gpt-oss 20B MXFP4 · 26.0 tok/s · Runs well (tight fit)
  2. 66Good quality (B) · 66 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. Maple Preview (20B-A1B) Q4_K_M · 53.0 tok/s · Runs well (tight fit)
  3. 66Good quality (B) · 66 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. Mellum2.1 Thinking (12B-A2.5B) Q4_K_M · 34.0 tok/s · Runs great
  4. 64Good quality (B) · 64 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. Gemma 4 26B-A4B Q2_K · 36.7 tok/s · Runs well (tight fit)
  5. 62Good quality (B) · 62 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. LFM2.5 24B-A2B Q3_K_M · 43.5 tok/s · Runs well (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?