Best local LLMs for the Annapurna Labs Alpine AL324 NAS (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. 65Good quality (B) · 65 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. Nemotron Labs Dory 1.0 4B Q5_K_M · 0.9 tok/s · Very slow
  2. 64Good quality (B) · 64 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. Spark-X2.6 4B Q5_K_M · 0.9 tok/s · Very slow
  3. 64Good quality (B) · 64 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. Nanbeige4.2 3B Q4_K_M · 1.0 tok/s · Very slow (tight fit)
  4. 59Good quality (B) · 59 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. MiniCPM5 2B Q6_K · 1.2 tok/s · Very slow
  5. 59Good quality (B) · 59 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. TMax 4B Q5_K_M · 0.9 tok/s · Very slow

Coding at 32K context

  1. 64Good quality (B) · 64 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. Spark-X2.6 4B Q5_K_M · 0.9 tok/s · Very slow (tight fit)
  2. 58Good quality (B) · 58 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. MiniCPM5 2B Q5_K_M · 1.4 tok/s · Very slow
  3. 57Good quality (B) · 57 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. Nemotron Labs Dory 1.0 4B Q3_K_M · 1.4 tok/s · Very slow (tight fit)
  4. 59Good quality (B) · 59 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. TMax 4B Q5_K_M · 0.9 tok/s · Very slow (tight fit)
  5. 58Good quality (B) · 58 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. Qwen3.5 4B Q4_K_M · 0.9 tok/s · Very slow (tight fit)

Reasoning at 32K context

  1. 64Good quality (B) · 64 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. Spark-X2.6 4B Q5_K_M · 0.9 tok/s · Very slow (tight fit)
  2. 58Good quality (B) · 58 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. MiniCPM5 2B Q5_K_M · 1.4 tok/s · Very slow
  3. 58Good quality (B) · 58 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.5 4B Q4_K_M · 0.9 tok/s · Very 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 72/100 (quality, fit, speed and memory use) sets the ranking. Nemotron Labs Dory 1.0 4B Q3_K_M · 1.4 tok/s · Very slow (tight fit)
  5. 48Fair quality (C) · 48 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. Nemotron 3 Nano 4B Q5_K_M · 0.9 tok/s · Very slow

Documents (RAG) at 32K context

  1. 59Good quality (B) · 59 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. TMax 4B Q5_K_M · 0.9 tok/s · Very slow (tight fit)
  2. 58Good quality (B) · 58 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.5 4B Q4_K_M · 0.9 tok/s · Very slow (tight fit)
  3. 57Good quality (B) · 57 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. Agents-A1 4B Q4_K_M · 1.0 tok/s · Very slow (tight fit)
  4. 55Good quality (B) · 55 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. Fara 1.5 4B Q4_K_M · 1.0 tok/s · Very slow (tight fit)
  5. 64Good quality (B) · 64 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. Spark-X2.6 4B Q5_K_M · 0.9 tok/s · Very slow (tight fit)

Agents & tools at 64K context

  1. 50Fair quality (C) · 50 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. MiniCPM5 2B Q3_K_M · 2.2 tok/s · Very slow (tight fit)
  2. 46Fair quality (C) · 46 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. Spark-X2.6 4B Q2_K · 1.7 tok/s · Very slow (tight fit)
  3. 47Fair quality (C) · 47 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. LFM3 1.7B Q3_K_M · 3.3 tok/s · Slow
  4. 42Fair quality (C) · 42 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. TMax 4B Q2_K · 1.7 tok/s · Very slow (tight fit)
  5. 36Basic quality (D) · 36 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. Granite 4.0 H Tiny (7B-A1B) Q3_K_M · 5.5 tok/s · Slow (tight fit)

Reverse engineering at 32K context

  1. 64Good quality (B) · 64 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. Spark-X2.6 4B Q5_K_M · 0.9 tok/s · Very slow (tight fit)
  2. 58Good quality (B) · 58 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. MiniCPM5 2B Q5_K_M · 1.4 tok/s · Very slow
  3. 59Good quality (B) · 59 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. TMax 4B Q5_K_M · 0.9 tok/s · Very slow (tight fit)
  4. 58Good quality (B) · 58 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. Qwen3.5 4B Q4_K_M · 0.9 tok/s · Very slow (tight fit)
  5. 57Good quality (B) · 57 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. Nemotron Labs Dory 1.0 4B Q3_K_M · 1.4 tok/s · Very 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?