Best local LLMs for the NVIDIA GeForce RTX 4090

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. 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. Gemma 4 26B-A4B Q6_K · 124 tok/s · Runs well (tight fit)
  2. 89Excellent quality (A+) · 89 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. Qwen3.6 27B Q4_K_M · 44.5 tok/s · Runs great
  3. 92Excellent quality (A+) · 92 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. Qwen3.8 27B Q5_K_M · 36.8 tok/s · Runs well (tight fit)
  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. Qwen3.5 27B Q4_K_M · 44.5 tok/s · Runs great
  5. 90Excellent quality (A+) · 90 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. Nanbeige4.3 33B Q4_K_M · 37.4 tok/s · Runs well (tight fit)

Coding at 32K context

  1. 87Excellent quality (A+) · 87 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. Gemma 4 26B-A4B Q4_K_M · 155 tok/s · Runs great
  2. 91Excellent quality (A+) · 91 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 99/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.6 27B Q5_K_M · 36.8 tok/s · Runs well (tight fit)
  3. 88Excellent quality (A+) · 88 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 98/100 (quality, fit, speed and memory use) sets the ranking. MiniCPM-V 4.7 35B-A3B Q4_K_M · 173 tok/s · Runs well (tight fit)
  4. 87Excellent quality (A+) · 87 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 98/100 (quality, fit, speed and memory use) sets the ranking. Muse Glimmer 30B Q4_K_M · 41.6 tok/s · Runs well (tight fit)
  5. 87Excellent quality (A+) · 87 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 98/100 (quality, fit, speed and memory use) sets the ranking. Nex N2 Mini (35B-A3B) Q4_K_M · 173 tok/s · Runs well (tight fit)

Reasoning at 32K context

  1. 91Excellent quality (A+) · 91 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 99/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.6 27B Q5_K_M · 36.8 tok/s · Runs well (tight fit)
  2. 88Excellent quality (A+) · 88 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 98/100 (quality, fit, speed and memory use) sets the ranking. MiniCPM-V 4.7 35B-A3B Q4_K_M · 173 tok/s · Runs well (tight fit)
  3. 87Excellent quality (A+) · 87 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 98/100 (quality, fit, speed and memory use) sets the ranking. Muse Glimmer 30B Q4_K_M · 41.6 tok/s · Runs well (tight fit)
  4. 87Excellent quality (A+) · 87 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 98/100 (quality, fit, speed and memory use) sets the ranking. Nex N2 Mini (35B-A3B) Q4_K_M · 173 tok/s · Runs well (tight fit)
  5. 86Excellent quality (A+) · 86 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 97/100 (quality, fit, speed and memory use) sets the ranking. KAT-Coder V2.5 Dev (35B-A3B) Q4_K_M · 173 tok/s · Runs well (tight fit)

Documents (RAG) at 32K context

  1. 92Excellent quality (A+) · 92 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. Qwen3.8 27B Q5_K_M · 36.8 tok/s · Runs well (tight fit)
  2. 87Excellent quality (A+) · 87 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. Gemma 4 26B-A4B Q4_K_M · 155 tok/s · Runs great
  3. 91Excellent quality (A+) · 91 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 99/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.6 27B Q5_K_M · 36.8 tok/s · Runs well (tight fit)
  4. 90Excellent quality (A+) · 90 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 98/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.5 27B Q5_K_M · 36.8 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 98/100 (quality, fit, speed and memory use) sets the ranking. MiniCPM-V 4.7 35B-A3B Q4_K_M · 173 tok/s · Runs well (tight fit)

Agents & tools at 64K context

  1. 89Excellent quality (A+) · 89 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 99/100 (quality, fit, speed and memory use) sets the ranking. Gemma 4 26B-A4B Q5_K_M · 139 tok/s · Runs well (tight fit)
  2. 89Excellent quality (A+) · 89 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. Qwen3.6 27B Q4_K_M · 44.5 tok/s · Runs well (tight fit)
  3. 87Excellent quality (A+) · 87 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 98/100 (quality, fit, speed and memory use) sets the ranking. Muse Glimmer 30B Q4_K_M · 41.6 tok/s · Runs well (tight fit)
  4. 83Great quality (A) · 83 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 97/100 (quality, fit, speed and memory use) sets the ranking. Raon-1 mini Preview (30B-A4B) Q4_K_M · 146 tok/s · Runs great
  5. 83Great quality (A) · 83 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. Gemma 4 12B Q8_0 · 52.7 tok/s · Runs great

Reverse engineering at 32K context

  1. 90Excellent quality (A+) · 90 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 98/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.5 27B Q5_K_M · 36.8 tok/s · Runs well (tight fit)
  2. 83Great quality (A) · 83 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 96/100 (quality, fit, speed and memory use) sets the ranking. GLM-4.7 Flash (30B-A3B) Q4_K_M · 173 tok/s · Runs well (tight fit)
  3. 78Great quality (A) · 78 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.5 35B-A3B Q3_K_M · 195 tok/s · Runs great
  4. 92Excellent quality (A+) · 92 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.8 27B Q5_K_M · 36.8 tok/s · Runs well (tight fit)
  5. 87Excellent quality (A+) · 87 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking. Gemma 4 26B-A4B Q4_K_M · 155 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?