Best local LLMs for the NVIDIA RTX 4000 SFF Ada Generation

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. 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. Gemma 4 26B-A4B Q4_K_M · 69.3 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. Raon-1 mini Preview (30B-A4B) Q4_K_M · 63.0 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 94/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.6 35B-A3B Q3_K_M · 100 tok/s · Runs well (tight fit)
  4. 78Great quality (A) · 78 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking. MiniCPM-V 4.7 35B-A3B Q3_K_M · 100 tok/s · Runs well (tight fit)
  5. 78Great quality (A) · 78 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.5 35B-A3B Q3_K_M · 100 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 98/100 (quality, fit, speed and memory use) sets the ranking. Gemma 4 26B-A4B Q4_K_M · 69.3 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. Raon-1 mini Preview (30B-A4B) Q4_K_M · 63.0 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 94/100 (quality, fit, speed and memory use) sets the ranking. MiniCPM-V 4.7 35B-A3B Q3_K_M · 100 tok/s · Runs well (tight fit)
  4. 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. Nex N2 Mini (35B-A3B) Q3_K_M · 100 tok/s · Runs well (tight fit)
  5. 76Great quality (A) · 76 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. KAT-Coder V2.5 Dev (35B-A3B) Q3_K_M · 100 tok/s · Runs well (tight fit)

Reasoning at 32K context

  1. 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. Raon-1 mini Preview (30B-A4B) Q4_K_M · 63.0 tok/s · Runs well (tight fit)
  2. 78Great quality (A) · 78 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking. MiniCPM-V 4.7 35B-A3B Q3_K_M · 100 tok/s · Runs well (tight fit)
  3. 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. Nex N2 Mini (35B-A3B) Q3_K_M · 100 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 93/100 (quality, fit, speed and memory use) sets the ranking. Gemma 4 26B-A4B Q4_K_M · 69.3 tok/s · Runs well (tight fit)
  5. 76Great quality (A) · 76 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. KAT-Coder V2.5 Dev (35B-A3B) Q3_K_M · 100 tok/s · Runs well (tight fit)

Documents (RAG) 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 98/100 (quality, fit, speed and memory use) sets the ranking. Gemma 4 26B-A4B Q4_K_M · 69.3 tok/s · Runs well (tight fit)
  2. 78Great quality (A) · 78 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.6 35B-A3B Q3_K_M · 100 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 94/100 (quality, fit, speed and memory use) sets the ranking. MiniCPM-V 4.7 35B-A3B Q3_K_M · 100 tok/s · Runs well (tight fit)
  4. 78Great quality (A) · 78 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.5 35B-A3B Q3_K_M · 100 tok/s · Runs well (tight fit)
  5. 75Great quality (A) · 75 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. Ornith 1.5 35B-A3B Q3_K_M · 100 tok/s · Runs well (tight fit)

Agents & tools at 64K context

  1. 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. Raon-1 mini Preview (30B-A4B) Q4_K_M · 63.0 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 93/100 (quality, fit, speed and memory use) sets the ranking. Gemma 4 26B-A4B Q3_K_M · 84.8 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 93/100 (quality, fit, speed and memory use) sets the ranking. K2 Horizon 7B Q4_K_M · 38.2 tok/s · Runs great
  4. 76Great quality (A) · 76 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. KAT-Coder V2.5 Dev (35B-A3B) Q3_K_M · 100 tok/s · Runs well (tight fit)
  5. 78Great quality (A) · 78 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. Gemma 4 12B Q4_K_M · 28.7 tok/s · Runs well

Reverse engineering at 32K context

  1. 78Great quality (A) · 78 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.5 35B-A3B Q3_K_M · 100 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 93/100 (quality, fit, speed and memory use) sets the ranking. Gemma 4 26B-A4B Q4_K_M · 69.3 tok/s · Runs well (tight fit)
  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. GLM-4.7 Flash (30B-A3B) Q3_K_M · 100 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 91/100 (quality, fit, speed and memory use) sets the ranking. Raon-1 mini Preview (30B-A4B) Q4_K_M · 63.0 tok/s · Runs well (tight fit)
  5. 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 · 76.0 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?