Best local LLMs for the AMD Ryzen Embedded V1500B NAS (64 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. 95Excellent quality (A+) · 95 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. Nanbeige4.3 33B Q8_0 · 0.3 tok/s · Very slow
  2. 95Excellent quality (A+) · 95 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.8 27B Q8_0 · 0.4 tok/s · Very slow
  3. 94Excellent quality (A+) · 94 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.6 27B Q8_0 · 0.4 tok/s · Very slow
  4. 86Excellent quality (A+) · 86 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. Kolibri 1 (78B-A3.5B) Q4_K_M · 5.6 tok/s · Slow (tight fit)
  5. 93Excellent quality (A+) · 93 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.5 27B Q8_0 · 0.4 tok/s · Very slow

Coding at 32K context

  1. 94Excellent quality (A+) · 94 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. Nanbeige4.3 33B Q6_K · 0.4 tok/s · Very slow
  2. 94Excellent quality (A+) · 94 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.6 27B Q8_0 · 0.4 tok/s · Very slow
  3. 86Excellent quality (A+) · 86 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. Kolibri 1 (78B-A3.5B) Q4_K_M · 5.6 tok/s · Slow (tight fit)
  4. 92Excellent quality (A+) · 92 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. Muse Glimmer 30B Q8_0 · 0.3 tok/s · Very slow
  5. 91Excellent quality (A+) · 91 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. Gemma 4 26B-A4B Q6_K · 3.5 tok/s · Slow

Reasoning at 32K context

  1. 94Excellent quality (A+) · 94 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. Nanbeige4.3 33B Q6_K · 0.4 tok/s · Very slow
  2. 94Excellent quality (A+) · 94 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.6 27B Q8_0 · 0.4 tok/s · Very slow
  3. 86Excellent quality (A+) · 86 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. Kolibri 1 (78B-A3.5B) Q4_K_M · 5.6 tok/s · Slow (tight fit)
  4. 92Excellent quality (A+) · 92 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. Muse Glimmer 30B Q8_0 · 0.3 tok/s · Very slow
  5. 88Excellent quality (A+) · 88 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. Fara 1.5 27B Q8_0 · 0.4 tok/s · Very slow

Documents (RAG) at 32K context

  1. 95Excellent quality (A+) · 95 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.8 27B Q8_0 · 0.4 tok/s · Very slow
  2. 94Excellent quality (A+) · 94 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.6 27B Q8_0 · 0.4 tok/s · Very slow
  3. 86Excellent quality (A+) · 86 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. Kolibri 1 (78B-A3.5B) Q4_K_M · 5.6 tok/s · Slow (tight fit)
  4. 93Excellent quality (A+) · 93 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.5 27B Q8_0 · 0.4 tok/s · Very slow
  5. 92Excellent quality (A+) · 92 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. Muse Glimmer 30B Q8_0 · 0.3 tok/s · Very slow

Agents & tools at 64K context

  1. 94Excellent quality (A+) · 94 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. Nanbeige4.3 33B Q6_K · 0.4 tok/s · Very slow
  2. 94Excellent quality (A+) · 94 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.6 27B Q8_0 · 0.4 tok/s · Very slow
  3. 86Excellent quality (A+) · 86 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. Kolibri 1 (78B-A3.5B) Q4_K_M · 5.6 tok/s · Slow (tight fit)
  4. 91Excellent quality (A+) · 91 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. Gemma 4 26B-A4B Q6_K · 3.5 tok/s · Slow
  5. 92Excellent quality (A+) · 92 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. Muse Glimmer 30B Q8_0 · 0.3 tok/s · Very slow

Reverse engineering at 32K context

  1. 93Excellent quality (A+) · 93 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.5 27B Q8_0 · 0.4 tok/s · Very slow
  2. 95Excellent quality (A+) · 95 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.8 27B Q8_0 · 0.4 tok/s · Very slow
  3. 94Excellent quality (A+) · 94 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. Nanbeige4.3 33B Q6_K · 0.4 tok/s · Very slow
  4. 94Excellent quality (A+) · 94 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.6 27B Q8_0 · 0.4 tok/s · Very slow
  5. 77Great quality (A) · 77 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. Qwen3 Coder 30B-A3B Q6_K · 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?