Best local LLMs for the AMD Instinct MI300X

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. 92Excellent quality (A+) · 92 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 100/100 (quality, fit, speed and memory use) sets the ranking. Nemotron 3.5 Super VL 120B-A12B Q6_K · 149 tok/s · Runs great
  2. 91Excellent quality (A+) · 91 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 100/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.8 Flash Next (125B-A6B) Q4_K_M · 225 tok/s · Runs great
  3. 89Excellent quality (A+) · 89 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 100/100 (quality, fit, speed and memory use) sets the ranking. Step 3.5 Flash (196B-A11B) Q5_K_M · 170 tok/s · Runs great
  4. 92Excellent quality (A+) · 92 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 100/100 (quality, fit, speed and memory use) sets the ranking. Step 3.7 Flash (198B-A11B) Q6_K · 155 tok/s · Runs well (tight fit)
  5. 88Excellent quality (A+) · 88 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 99/100 (quality, fit, speed and memory use) sets the ranking. MiniMax M2.7 (230B-A10B) Q4_K_M · 194 tok/s · Runs great

Coding at 32K context

  1. 92Excellent quality (A+) · 92 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 100/100 (quality, fit, speed and memory use) sets the ranking. Nemotron 3.5 Super VL 120B-A12B Q6_K · 149 tok/s · Runs great
  2. 91Excellent quality (A+) · 91 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 100/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.8 Flash Next (125B-A6B) Q4_K_M · 225 tok/s · Runs great
  3. 89Excellent quality (A+) · 89 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 100/100 (quality, fit, speed and memory use) sets the ranking. Step 3.5 Flash (196B-A11B) Q5_K_M · 170 tok/s · Runs great
  4. 92Excellent quality (A+) · 92 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 100/100 (quality, fit, speed and memory use) sets the ranking. Step 3.7 Flash (198B-A11B) Q6_K · 155 tok/s · Runs well (tight fit)
  5. 91Excellent quality (A+) · 91 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 99/100 (quality, fit, speed and memory use) sets the ranking. Ornith 1.5 122B-A10B Q6_K · 162 tok/s · Runs great

Reasoning at 32K context

  1. 92Excellent quality (A+) · 92 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 100/100 (quality, fit, speed and memory use) sets the ranking. Nemotron 3.5 Super VL 120B-A12B Q6_K · 149 tok/s · Runs great
  2. 91Excellent quality (A+) · 91 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 100/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.8 Flash Next (125B-A6B) Q4_K_M · 225 tok/s · Runs great
  3. 89Excellent quality (A+) · 89 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 100/100 (quality, fit, speed and memory use) sets the ranking. Step 3.5 Flash (196B-A11B) Q5_K_M · 170 tok/s · Runs great
  4. 92Excellent quality (A+) · 92 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 100/100 (quality, fit, speed and memory use) sets the ranking. Step 3.7 Flash (198B-A11B) Q6_K · 155 tok/s · Runs well (tight fit)
  5. 91Excellent quality (A+) · 91 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 99/100 (quality, fit, speed and memory use) sets the ranking. Ornith 1.5 122B-A10B Q6_K · 162 tok/s · Runs great

Documents (RAG) at 32K context

  1. 92Excellent quality (A+) · 92 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 100/100 (quality, fit, speed and memory use) sets the ranking. Nemotron 3.5 Super VL 120B-A12B Q6_K · 149 tok/s · Runs great
  2. 91Excellent quality (A+) · 91 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 100/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.8 Flash Next (125B-A6B) Q4_K_M · 225 tok/s · Runs great
  3. 89Excellent quality (A+) · 89 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 100/100 (quality, fit, speed and memory use) sets the ranking. Step 3.5 Flash (196B-A11B) Q5_K_M · 170 tok/s · Runs great
  4. 88Excellent quality (A+) · 88 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 99/100 (quality, fit, speed and memory use) sets the ranking. MiniMax M2.7 (230B-A10B) Q4_K_M · 194 tok/s · Runs great
  5. 91Excellent quality (A+) · 91 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 99/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.5 122B-A10B Q6_K · 162 tok/s · Runs great

Agents & tools at 64K context

  1. 92Excellent quality (A+) · 92 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 100/100 (quality, fit, speed and memory use) sets the ranking. Nemotron 3.5 Super VL 120B-A12B Q6_K · 149 tok/s · Runs great
  2. 91Excellent quality (A+) · 91 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 100/100 (quality, fit, speed and memory use) sets the ranking. Ornith 1.5 122B-A10B Q6_K · 162 tok/s · Runs great
  3. 91Excellent quality (A+) · 91 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 100/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.8 Flash Next (125B-A6B) Q4_K_M · 225 tok/s · Runs great
  4. 89Excellent quality (A+) · 89 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 100/100 (quality, fit, speed and memory use) sets the ranking. Step 3.5 Flash (196B-A11B) Q5_K_M · 170 tok/s · Runs great
  5. 92Excellent quality (A+) · 92 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 100/100 (quality, fit, speed and memory use) sets the ranking. Step 3.7 Flash (198B-A11B) Q6_K · 155 tok/s · Runs well (tight fit)

Reverse engineering at 32K context

  1. 95Excellent quality (A+) · 95 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 97/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.8 Flash Next (125B-A6B) Q6_K · 194 tok/s · Runs great
  2. 93Excellent quality (A+) · 93 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 97/100 (quality, fit, speed and memory use) sets the ranking. Nemotron 3.5 Super VL 120B-A12B Q8_0 · 125 tok/s · Runs great
  3. 93Excellent quality (A+) · 93 of 100: how capable the model is at F16, whatever it runs on. Match score 96/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.5 35B-A3B F16 · 150 tok/s · Runs great
  4. 92Excellent quality (A+) · 92 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 96/100 (quality, fit, speed and memory use) sets the ranking. Ornith 1.5 122B-A10B Q8_0 · 137 tok/s · Runs great
  5. 92Excellent quality (A+) · 92 of 100: how capable the model is at F16, whatever it runs on. Match score 96/100 (quality, fit, speed and memory use) sets the ranking. Nemotron 3.5 Bolt 74B-A9B F16 · 89.1 tok/s · Runs great

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?