Check my GPU

Best local LLMs for the NVIDIA RTX A5500

Each list assumes the context length that task usually needs, so a model that fits for chat may drop down the list for long documents.

General chat at 8K context

  1. 100 ptsExcellent (S) · 100 of 100 points: Model quality 41.2/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 Gemma 4 26B-A4B Q6_K · 86.1 tok/s · Tight fit
  2. 99 ptsExcellent (S) · 99 of 100 points: Model quality 40.9/45, Memory fit 25.0/25, Speed 13.8/15, Memory use 15.0/15, workload match +5.0 Qwen3.8 27B Q4_K_M · 33.9 tok/s · Runs well
  3. 99 ptsExcellent (S) · 99 of 100 points: Model quality 40.2/45, Memory fit 25.0/25, Speed 13.8/15, Memory use 15.0/15, workload match +5.0 Qwen3.6 27B Q4_K_M · 33.9 tok/s · Runs well
  4. 98 ptsExcellent (S) · 98 of 100 points: Model quality 40.0/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 Qwen3.6 35B-A3B Q4_K_M · 157 tok/s · Tight fit
  5. 98 ptsExcellent (S) · 98 of 100 points: Model quality 39.8/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 Qwen3.5 35B-A3B Q4_K_M · 157 tok/s · Tight fit

Coding at 32K context

  1. 99 ptsExcellent (S) · 99 of 100 points: Model quality 39.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 Gemma 4 26B-A4B Q4_K_M · 124 tok/s · Runs well
  2. 98 ptsExcellent (S) · 98 of 100 points: Model quality 40.9/45, Memory fit 24.0/25, Speed 13.8/15, Memory use 15.0/15, workload match +5.0 Qwen3.8 27B Q4_K_M · 33.9 tok/s · Tight fit
  3. 98 ptsExcellent (S) · 98 of 100 points: Model quality 40.2/45, Memory fit 24.0/25, Speed 13.8/15, Memory use 15.0/15, workload match +5.0 Qwen3.6 27B Q4_K_M · 33.9 tok/s · Tight fit
  4. 97 ptsExcellent (S) · 97 of 100 points: Model quality 39.8/45, Memory fit 24.0/25, Speed 13.8/15, Memory use 15.0/15, workload match +5.0 Qwen3.5 27B Q4_K_M · 33.9 tok/s · Tight fit
  5. 96 ptsExcellent (S) · 96 of 100 points: Model quality 37.6/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 GLM-4.7 Flash (30B-A3B) Q4_K_M · 157 tok/s · Tight fit

Reasoning at 32K context

  1. 98 ptsExcellent (S) · 98 of 100 points: Model quality 40.9/45, Memory fit 24.0/25, Speed 13.8/15, Memory use 15.0/15, workload match +5.0 Qwen3.8 27B Q4_K_M · 33.9 tok/s · Tight fit
  2. 98 ptsExcellent (S) · 98 of 100 points: Model quality 40.2/45, Memory fit 24.0/25, Speed 13.8/15, Memory use 15.0/15, workload match +5.0 Qwen3.6 27B Q4_K_M · 33.9 tok/s · Tight fit
  3. 97 ptsExcellent (S) · 97 of 100 points: Model quality 39.8/45, Memory fit 24.0/25, Speed 13.8/15, Memory use 15.0/15, workload match +5.0 Qwen3.5 27B Q4_K_M · 33.9 tok/s · Tight fit
  4. 96 ptsExcellent (S) · 96 of 100 points: Model quality 38.5/45, Memory fit 24.0/25, Speed 13.9/15, Memory use 15.0/15, workload match +5.0 TMax 27B Q4_K_M · 34.5 tok/s · Tight fit
  5. 96 ptsExcellent (S) · 96 of 100 points: Model quality 37.2/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 Agents-A1 35B-A3B Q4_K_M · 157 tok/s · Tight fit

Documents (RAG) at 32K context

  1. 99 ptsExcellent (S) · 99 of 100 points: Model quality 39.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 Gemma 4 26B-A4B Q4_K_M · 124 tok/s · Runs well
  2. 98 ptsExcellent (S) · 98 of 100 points: Model quality 40.9/45, Memory fit 24.0/25, Speed 13.8/15, Memory use 15.0/15, workload match +5.0 Qwen3.8 27B Q4_K_M · 33.9 tok/s · Tight fit
  3. 97 ptsExcellent (S) · 97 of 100 points: Model quality 39.8/45, Memory fit 24.0/25, Speed 13.8/15, Memory use 15.0/15, workload match +5.0 Qwen3.5 27B Q4_K_M · 33.9 tok/s · Tight fit
  4. 97 ptsExcellent (S) · 97 of 100 points: Model quality 37.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 Gemma 4 12B Q8_0 · 40.1 tok/s · Runs well
  5. 93 ptsExcellent (S) · 93 of 100 points: Model quality 34.4/45, Memory fit 24.0/25, Speed 14.8/15, Memory use 15.0/15, workload match +5.0 Gemma 4 31B Q3_K_M · 39.0 tok/s · Tight fit

Agents & tools at 64K context

  1. 99 ptsExcellent (S) · 99 of 100 points: Model quality 40.4/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 Gemma 4 26B-A4B Q5_K_M · 102 tok/s · Tight fit
  2. 98 ptsExcellent (S) · 98 of 100 points: Model quality 40.9/45, Memory fit 24.0/25, Speed 13.8/15, Memory use 15.0/15, workload match +5.0 Qwen3.8 27B Q4_K_M · 33.9 tok/s · Tight fit
  3. 98 ptsExcellent (S) · 98 of 100 points: Model quality 40.2/45, Memory fit 24.0/25, Speed 13.8/15, Memory use 15.0/15, workload match +5.0 Qwen3.6 27B Q4_K_M · 33.9 tok/s · Tight fit
  4. 97 ptsExcellent (S) · 97 of 100 points: Model quality 39.8/45, Memory fit 24.0/25, Speed 13.8/15, Memory use 15.0/15, workload match +5.0 Qwen3.5 27B Q4_K_M · 33.9 tok/s · Tight fit
  5. 97 ptsExcellent (S) · 97 of 100 points: Model quality 37.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 Gemma 4 12B Q8_0 · 40.1 tok/s · Runs well

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.