Best local LLMs for the NVIDIA L40

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. 89Excellent quality (A+) · 89 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. Flint (40B-A2.5B) Q6_K · 143 tok/s · Runs great
  2. 89Excellent quality (A+) · 89 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 35B-A3B Q6_K · 130 tok/s · Runs great
  3. 90Excellent quality (A+) · 90 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. Sage-A1.5 35B-A3B Q6_K · 130 tok/s · Runs great
  4. 88Excellent quality (A+) · 88 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. Apodex 1.1 Mini (35B-A3B) Q6_K · 130 tok/s · Runs great
  5. 88Excellent quality (A+) · 88 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 1.0 35B-A3B Q6_K · 130 tok/s · Runs great

Coding at 32K context

  1. 89Excellent quality (A+) · 89 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. Flint (40B-A2.5B) Q6_K · 143 tok/s · Runs great
  2. 91Excellent quality (A+) · 91 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 100/100 (quality, fit, speed and memory use) sets the ranking. KAT-Coder V2.5 Dev (35B-A3B) Q8_0 · 107 tok/s · Runs great
  3. 90Excellent quality (A+) · 90 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. Sage-A1.5 35B-A3B Q6_K · 130 tok/s · Runs great
  4. 88Excellent quality (A+) · 88 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. Apodex 1.1 Mini (35B-A3B) Q6_K · 130 tok/s · Runs great
  5. 88Excellent quality (A+) · 88 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 99/100 (quality, fit, speed and memory use) sets the ranking. GLM-4.7 Flash (30B-A3B) Q8_0 · 107 tok/s · Runs great

Reasoning at 32K context

  1. 89Excellent quality (A+) · 89 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. Flint (40B-A2.5B) Q6_K · 143 tok/s · Runs great
  2. 91Excellent quality (A+) · 91 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 100/100 (quality, fit, speed and memory use) sets the ranking. KAT-Coder V2.5 Dev (35B-A3B) Q8_0 · 107 tok/s · Runs great
  3. 90Excellent quality (A+) · 90 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. Sage-A1.5 35B-A3B Q6_K · 130 tok/s · Runs great
  4. 88Excellent quality (A+) · 88 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. Apodex 1.1 Mini (35B-A3B) Q6_K · 130 tok/s · Runs great
  5. 88Excellent quality (A+) · 88 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 99/100 (quality, fit, speed and memory use) sets the ranking. Raon-1 mini Preview (30B-A4B) Q8_0 · 85.0 tok/s · Runs great

Documents (RAG) at 32K context

  1. 89Excellent quality (A+) · 89 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 35B-A3B Q6_K · 130 tok/s · Runs great
  2. 90Excellent quality (A+) · 90 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 35B-A3B Q5_K_M · 144 tok/s · Runs great
  3. 88Excellent quality (A+) · 88 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. Apodex 1.1 Mini (35B-A3B) Q6_K · 130 tok/s · Runs great
  4. 88Excellent quality (A+) · 88 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 1.0 35B-A3B Q6_K · 130 tok/s · Runs great
  5. 90Excellent quality (A+) · 90 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. Qwen3.5 35B-A3B Q5_K_M · 144 tok/s · Runs great

Agents & tools at 64K context

  1. 89Excellent quality (A+) · 89 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. Flint (40B-A2.5B) Q6_K · 143 tok/s · Runs great
  2. 90Excellent quality (A+) · 90 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. KAT-Coder V2.5 Dev (35B-A3B) Q6_K · 130 tok/s · Runs great
  3. 90Excellent quality (A+) · 90 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. Sage-A1.5 35B-A3B Q6_K · 130 tok/s · Runs great
  4. 90Excellent quality (A+) · 90 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. MiniCPM-V 4.7 35B-A3B Q5_K_M · 144 tok/s · Runs great
  5. 88Excellent quality (A+) · 88 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. Apodex 1.1 Mini (35B-A3B) Q6_K · 130 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 99/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.5 35B-A3B Q5_K_M · 144 tok/s · Runs great
  2. 88Excellent quality (A+) · 88 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 99/100 (quality, fit, speed and memory use) sets the ranking. GLM-4.7 Flash (30B-A3B) Q8_0 · 107 tok/s · Runs great
  3. 92Excellent quality (A+) · 92 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 96/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.6 35B-A3B Q6_K · 130 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. Gemma 4 26B-A4B Q8_0 · 92.2 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 96/100 (quality, fit, speed and memory use) sets the ranking. MiniCPM-V 4.7 35B-A3B Q6_K · 130 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?