Check my GPU

Best local LLMs for the NVIDIA GeForce GTX 1660 Ti

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. 88 ptsExcellent (S) · 88 of 100 points: Model quality 29.1/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 Ornith 1.5 9B Q3_K_M · 47.4 tok/s · Tight fit
  2. 88 ptsExcellent (S) · 88 of 100 points: Model quality 29.1/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 Gemma 4 E4B Q4_K_M · 44.2 tok/s · Tight fit
  3. 87 ptsExcellent (S) · 87 of 100 points: Model quality 28.7/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 Qwen3.5 9B Q3_K_M · 47.4 tok/s · Tight fit
  4. 87 ptsExcellent (S) · 87 of 100 points: Model quality 27.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 Qwen3.5 4B Q6_K · 52.6 tok/s · Runs well
  5. 87 ptsExcellent (S) · 87 of 100 points: Model quality 28.4/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 Ornith 1.0 9B Q3_K_M · 47.4 tok/s · Tight fit

Coding at 32K context

  1. 83 ptsGreat (A) · 83 of 100 points: Model quality 24.3/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 Ornith 1.5 9B Q2_K · 60.2 tok/s · Tight fit
  2. 82 ptsGreat (A) · 82 of 100 points: Model quality 23.6/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 Ornith 1.0 9B Q2_K · 60.2 tok/s · Tight fit
  3. 82 ptsGreat (A) · 82 of 100 points: Model quality 27.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 Gemma 4 E2B Q5_K_M · 57.0 tok/s · Runs well
  4. 81 ptsGreat (A) · 81 of 100 points: Model quality 26.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 TMax 4B Q5_K_M · 69.4 tok/s · Runs well
  5. 81 ptsGreat (A) · 81 of 100 points: Model quality 27.6/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15 Qwen3.5 4B Q6_K · 52.6 tok/s · Tight fit

Reasoning at 32K context

  1. 86 ptsExcellent (S) · 86 of 100 points: Model quality 27.6/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 Qwen3.5 4B Q6_K · 52.6 tok/s · Tight fit
  2. 83 ptsGreat (A) · 83 of 100 points: Model quality 24.3/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 Ornith 1.5 9B Q2_K · 60.2 tok/s · Tight fit
  3. 82 ptsGreat (A) · 82 of 100 points: Model quality 23.9/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 Qwen3.5 9B Q2_K · 60.2 tok/s · Tight fit
  4. 82 ptsGreat (A) · 82 of 100 points: Model quality 23.6/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 Ornith 1.0 9B Q2_K · 60.2 tok/s · Tight fit
  5. 82 ptsGreat (A) · 82 of 100 points: Model quality 23.3/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 TMax 9B Q2_K · 64.9 tok/s · Tight fit

Documents (RAG) at 32K context

  1. 84 ptsGreat (A) · 84 of 100 points: Model quality 25.7/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 Gemma 4 E4B Q3_K_M · 57.1 tok/s · Tight fit
  2. 82 ptsGreat (A) · 82 of 100 points: Model quality 23.9/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 Qwen3.5 9B Q2_K · 60.2 tok/s · Tight fit
  3. 82 ptsGreat (A) · 82 of 100 points: Model quality 27.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 Gemma 4 E2B Q5_K_M · 57.0 tok/s · Runs well
  4. 81 ptsGreat (A) · 81 of 100 points: Model quality 26.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 TMax 4B Q5_K_M · 69.4 tok/s · Runs well
  5. 81 ptsGreat (A) · 81 of 100 points: Model quality 27.6/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15 Qwen3.5 4B Q6_K · 52.6 tok/s · Tight fit

Agents & tools at 64K context

  1. 85 ptsExcellent (S) · 85 of 100 points: Model quality 26.1/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 TMax 4B Q4_K_M · 84.0 tok/s · Tight fit
  2. 84 ptsGreat (A) · 84 of 100 points: Model quality 25.7/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 Agents-A1 4B Q4_K_M · 77.9 tok/s · Tight fit
  3. 83 ptsGreat (A) · 83 of 100 points: Model quality 24.8/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 Fara 1.5 4B Q4_K_M · 77.9 tok/s · Tight fit
  4. 82 ptsGreat (A) · 82 of 100 points: Model quality 27.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 Gemma 4 E2B Q5_K_M · 57.0 tok/s · Runs well
  5. 80 ptsGreat (A) · 80 of 100 points: Model quality 26.5/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15 Qwen3.5 4B Q4_K_M · 75.9 tok/s · 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.