Best local LLMs for the Other Android device (12 GB RAM)

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. 57Good quality (B) · 57 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. Ling 3.0 Tiny (8B-A1.3B) Q4_K_M · 22.0 tok/s · Runs well
  2. 74Great quality (A) · 74 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. SenseNova Loop 9B Preview Q4_K_M · 3.2 tok/s · Slow (tight fit)
  3. 73Great quality (A) · 73 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. Ornith 1.5 9B Q4_K_M · 3.2 tok/s · Slow (tight fit)
  4. 72Great quality (A) · 72 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.5 9B Q4_K_M · 3.2 tok/s · Slow (tight fit)
  5. 71Great quality (A) · 71 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. Ornith 1.0 9B Q4_K_M · 3.2 tok/s · Slow (tight fit)

Coding at 32K context

  1. 58Good quality (B) · 58 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. Mellum2.1 Thinking (12B-A2.5B) Q3_K_M · 15.2 tok/s · Runs well (tight fit)
  2. 65Good quality (B) · 65 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. MiMo V2.6 Distill Qwen 9B Q3_K_M · 4.2 tok/s · Slow (tight fit)
  3. 57Good quality (B) · 57 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. Nemotron Labs Dory 1.0 4B Q3_K_M · 10.0 tok/s · Runs well
  4. 57Good quality (B) · 57 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. Ling 3.0 Tiny (8B-A1.3B) Q4_K_M · 22.0 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 75/100 (quality, fit, speed and memory use) sets the ranking. MiniCPM5 2B Q4_K_M · 12.2 tok/s · Runs well

Reasoning at 32K context

  1. 58Good quality (B) · 58 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. Mellum2.1 Thinking (12B-A2.5B) Q3_K_M · 15.2 tok/s · Runs well (tight fit)
  2. 65Good quality (B) · 65 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. MiMo V2.6 Distill Qwen 9B Q3_K_M · 4.2 tok/s · Slow (tight fit)
  3. 63Good quality (B) · 63 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.5 9B Q3_K_M · 4.1 tok/s · Slow (tight fit)
  4. 57Good quality (B) · 57 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. Nemotron Labs Dory 1.0 4B Q3_K_M · 10.0 tok/s · Runs well
  5. 57Good quality (B) · 57 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. Ling 3.0 Tiny (8B-A1.3B) Q4_K_M · 22.0 tok/s · Runs well (tight fit)

Documents (RAG) at 32K context

  1. 70Great quality (A) · 70 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. TMax 9B Q4_K_M · 3.4 tok/s · Slow (tight fit)
  2. 41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. Unlimited OCR 2 (3B-A0.6B) Q4_K_M · 43.8 tok/s · Runs great
  3. 58Good quality (B) · 58 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. Gemma 4 E2B Q4_K_M · 13.4 tok/s · Runs well
  4. 64Good quality (B) · 64 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. Ornith 1.5 9B Q3_K_M · 4.1 tok/s · Slow (tight fit)
  5. 63Good quality (B) · 63 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.5 9B Q3_K_M · 4.1 tok/s · Slow (tight fit)

Agents & tools at 64K context

  1. 57Good quality (B) · 57 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. MiniCPM5 2B Q4_K_M · 12.2 tok/s · Runs well
  2. 49Fair quality (C) · 49 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. LFM2.5 8B-A1B Q4_K_M · 19.2 tok/s · Runs well (tight fit)
  3. 49Fair quality (C) · 49 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. Mellum2.1 Thinking (12B-A2.5B) Q2_K · 19.0 tok/s · Runs well (tight fit)
  4. 41Fair quality (C) · 41 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. Granite 4.0 H Tiny (7B-A1B) Q4_K_M · 27.9 tok/s · Runs well
  5. 49Fair quality (C) · 49 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. Nemotron 3.5 Bolt E4B Q2_K · 11.2 tok/s · Runs well

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 75/100 (quality, fit, speed and memory use) sets the ranking. Ling 3.0 Tiny (8B-A1.3B) Q4_K_M · 22.0 tok/s · Runs well (tight fit)
  2. 70Great quality (A) · 70 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. TMax 9B Q4_K_M · 3.4 tok/s · Slow (tight fit)
  3. 58Good quality (B) · 58 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. Mellum2.1 Thinking (12B-A2.5B) Q3_K_M · 15.2 tok/s · Runs well (tight fit)
  4. 41Fair quality (C) · 41 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. Unlimited OCR 2 (3B-A0.6B) Q4_K_M · 43.8 tok/s · Runs great
  5. 65Good quality (B) · 65 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. MiMo V2.6 Distill Qwen 9B Q3_K_M · 4.2 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?