Best local LLMs for the NVIDIA RTX A400

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. 64Good quality (B) · 64 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. Nemotron Labs Dory 1.0 4B Q4_K_M · 29.6 tok/s · Runs well (tight fit)
  2. 58Good quality (B) · 58 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. MiniCPM5 2B Q5_K_M · 38.6 tok/s · Runs great
  3. 58Good quality (B) · 58 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. Gemma 4 E2B Q4_K_M · 51.2 tok/s · Runs well (tight fit)
  4. 62Good quality (B) · 62 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. Spark-X2.6 4B Q4_K_M · 28.7 tok/s · Runs well (tight fit)
  5. 55Good quality (B) · 55 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. LFM3 1.7B Q6_K · 47.3 tok/s · Runs great

Coding at 32K context

  1. 58Good quality (B) · 58 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. MiniCPM5 2B Q5_K_M · 38.6 tok/s · Runs well (tight fit)
  2. 55Good quality (B) · 55 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. LFM3 1.7B Q6_K · 47.3 tok/s · Runs great
  3. 46Fair quality (C) · 46 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. Spark-X2.6 4B Q2_K · 47.1 tok/s · Runs well (tight fit)
  4. 52Fair quality (C) · 52 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. Gemma 4 E2B Q3_K_M · 66.2 tok/s · Runs well (tight fit)
  5. 49Fair quality (C) · 49 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. LFM3-VL 2B Q6_K · 42.6 tok/s · Runs great

Reasoning at 32K context

  1. 58Good quality (B) · 58 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. MiniCPM5 2B Q5_K_M · 38.6 tok/s · Runs well (tight fit)
  2. 55Good quality (B) · 55 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. LFM3 1.7B Q6_K · 47.3 tok/s · Runs great
  3. 46Fair quality (C) · 46 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. Spark-X2.6 4B Q2_K · 47.1 tok/s · Runs well (tight fit)
  4. 42Fair quality (C) · 42 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. Nemotron 3 Nano 4B Q3_K_M · 38.4 tok/s · Runs great
  5. 43Fair quality (C) · 43 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.5 4B Q2_K · 41.5 tok/s · Runs well (tight fit)

Documents (RAG) at 32K context

  1. 55Good quality (B) · 55 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. LFM3 1.7B Q6_K · 47.3 tok/s · Runs great
  2. 52Fair quality (C) · 52 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. Gemma 4 E2B Q3_K_M · 66.2 tok/s · Runs well (tight fit)
  3. 49Fair quality (C) · 49 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. LFM3-VL 2B Q6_K · 42.6 tok/s · Runs great
  4. 51Fair quality (C) · 51 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. TMax 4B Q3_K_M · 36.2 tok/s · Runs well (tight fit)
  5. 58Good quality (B) · 58 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. MiniCPM5 2B Q5_K_M · 38.6 tok/s · Runs well (tight fit)

Agents & tools at 64K context

  1. 55Good quality (B) · 55 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. LFM3 1.7B Q6_K · 47.3 tok/s · Runs great
  2. 39Basic quality (D) · 39 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. TMax 2B Q6_K · 43.5 tok/s · Runs great
  3. 52Fair quality (C) · 52 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. Gemma 4 E2B Q3_K_M · 66.2 tok/s · Runs well (tight fit)
  4. 49Fair quality (C) · 49 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. LFM3-VL 2B Q6_K · 42.6 tok/s · Runs great
  5. 35Basic quality (D) · 35 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. MiniCPM5 1B Q6_K · 75.7 tok/s · Runs great

Reverse engineering at 32K context

  1. 55Good quality (B) · 55 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. LFM3 1.7B Q6_K · 47.3 tok/s · Runs great
  2. 58Good quality (B) · 58 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. MiniCPM5 2B Q5_K_M · 38.6 tok/s · Runs well (tight fit)
  3. 52Fair quality (C) · 52 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. Gemma 4 E2B Q3_K_M · 66.2 tok/s · Runs well (tight fit)
  4. 49Fair quality (C) · 49 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. LFM3-VL 2B Q6_K · 42.6 tok/s · Runs great
  5. 51Fair quality (C) · 51 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. TMax 4B Q3_K_M · 36.2 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?