Best local LLMs for the AMD Radeon RX 7600 XT

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 93/100 (quality, fit, speed and memory use) sets the ranking. Gemma 4 26B-A4B Q3_K_M · 77.5 tok/s · Runs well (tight fit)
  2. 73Great quality (A) · 73 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking. Raon-1 mini Preview (30B-A4B) Q3_K_M · 70.6 tok/s · Runs well (tight fit)
  3. 70Great quality (A) · 70 of 100: how capable the model is at MXFP4, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. gpt-oss 20B MXFP4 · 69.4 tok/s · Runs great
  4. 78Great quality (A) · 78 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking. Gemma 4 12B Q4_K_M · 25.5 tok/s · Runs well
  5. 76Great quality (A) · 76 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. K2 Horizon 7B Q4_K_M · 33.8 tok/s · Runs great

Coding at 32K context

  1. 77Great quality (A) · 77 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. Gemma 4 26B-A4B Q3_K_M · 77.5 tok/s · Runs well (tight fit)
  2. 76Great quality (A) · 76 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking. K2 Horizon 7B Q4_K_M · 33.8 tok/s · Runs great
  3. 73Great quality (A) · 73 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking. Raon-1 mini Preview (30B-A4B) Q3_K_M · 70.6 tok/s · Runs well (tight fit)
  4. 69Good quality (B) · 69 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. Mellum2.1 Thinking (12B-A2.5B) Q6_K · 64.7 tok/s · Runs great
  5. 67Good quality (B) · 67 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking. Nanbeige4.2 3B Q6_K · 50.7 tok/s · Runs great

Reasoning at 32K context

  1. 76Great quality (A) · 76 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking. K2 Horizon 7B Q4_K_M · 33.8 tok/s · Runs great
  2. 73Great quality (A) · 73 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking. Raon-1 mini Preview (30B-A4B) Q3_K_M · 70.6 tok/s · Runs well (tight fit)
  3. 69Good quality (B) · 69 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. Mellum2.1 Thinking (12B-A2.5B) Q6_K · 64.7 tok/s · Runs great
  4. 70Great quality (A) · 70 of 100: how capable the model is at MXFP4, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking. gpt-oss 20B MXFP4 · 69.4 tok/s · Runs well (tight fit)
  5. 67Good quality (B) · 67 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking. Nanbeige4.2 3B Q6_K · 50.7 tok/s · Runs great

Documents (RAG) at 32K context

  1. 77Great quality (A) · 77 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. Gemma 4 26B-A4B Q3_K_M · 77.5 tok/s · Runs well (tight fit)
  2. 78Great quality (A) · 78 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking. Gemma 4 12B Q4_K_M · 25.5 tok/s · Runs well
  3. 74Great quality (A) · 74 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. SenseNova Loop 9B Preview Q4_K_M · 31.5 tok/s · Runs great
  4. 65Good quality (B) · 65 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. DiffusionGemma 26B-A4B IT Q3_K_M · 74.6 tok/s · Runs well (tight fit)
  5. 69Good quality (B) · 69 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. Nemotron 3.5 Bolt E4B Q6_K · 46.9 tok/s · Runs great

Agents & tools at 64K context

  1. 74Great quality (A) · 74 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. SenseNova Loop 9B Preview Q4_K_M · 31.5 tok/s · Runs great
  2. 78Great quality (A) · 78 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. Gemma 4 12B Q4_K_M · 25.5 tok/s · Runs well (tight fit)
  3. 69Good quality (B) · 69 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. Mellum2.1 Thinking (12B-A2.5B) Q6_K · 64.7 tok/s · Runs great
  4. 70Great quality (A) · 70 of 100: how capable the model is at MXFP4, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking. gpt-oss 20B MXFP4 · 69.4 tok/s · Runs well (tight fit)
  5. 74Great quality (A) · 74 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking. MiMo V2.6 Distill Qwen 9B Q4_K_M · 32.4 tok/s · Runs great

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 90/100 (quality, fit, speed and memory use) sets the ranking. gpt-oss 20B MXFP4 · 69.4 tok/s · Runs well (tight fit)
  2. 77Great quality (A) · 77 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. Gemma 4 26B-A4B Q3_K_M · 77.5 tok/s · Runs well (tight fit)
  3. 76Great quality (A) · 76 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. K2 Horizon 7B Q4_K_M · 33.8 tok/s · Runs great
  4. 78Great quality (A) · 78 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. Gemma 4 12B Q4_K_M · 25.5 tok/s · Runs well
  5. 73Great quality (A) · 73 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. Raon-1 mini Preview (30B-A4B) Q3_K_M · 70.6 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?