Check my GPU

Best local LLMs for the Intel Core Ultra 200H (Arc 140T) (96 GB)

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. 94 ptsExcellent (S) · 94 of 100 points: Model quality 41.7/45, Memory fit 25.0/25, Speed 7.9/15, Memory use 14.6/15, workload match +5.0 Qwen3.6 35B-A3B Q6_K · 11.1 tok/s · Runs well
  2. 93 ptsExcellent (S) · 93 of 100 points: Model quality 41.4/45, Memory fit 25.0/25, Speed 7.9/15, Memory use 14.6/15, workload match +5.0 Qwen3.5 35B-A3B Q6_K · 11.1 tok/s · Runs well
  3. 92 ptsExcellent (S) · 92 of 100 points: Model quality 40.1/45, Memory fit 25.0/25, Speed 7.9/15, Memory use 14.6/15, workload match +5.0 Ornith 1.5 35B-A3B Q6_K · 11.1 tok/s · Runs well
  4. 92 ptsExcellent (S) · 92 of 100 points: Model quality 39.6/45, Memory fit 25.0/25, Speed 7.9/15, Memory use 14.6/15, workload match +5.0 Apodex 1.1 Mini (35B-A3B) Q6_K · 11.1 tok/s · Runs well
  5. 92 ptsExcellent (S) · 92 of 100 points: Model quality 39.6/45, Memory fit 25.0/25, Speed 7.9/15, Memory use 14.6/15, workload match +5.0 Ornith 1.0 35B-A3B Q6_K · 11.1 tok/s · Runs well

Coding at 32K context

  1. 94 ptsExcellent (S) · 94 of 100 points: Model quality 41.7/45, Memory fit 25.0/25, Speed 7.9/15, Memory use 14.8/15, workload match +5.0 Qwen3.6 35B-A3B Q6_K · 11.1 tok/s · Runs well
  2. 94 ptsExcellent (S) · 94 of 100 points: Model quality 41.4/45, Memory fit 25.0/25, Speed 7.9/15, Memory use 14.8/15, workload match +5.0 Qwen3.5 35B-A3B Q6_K · 11.1 tok/s · Runs well
  3. 92 ptsExcellent (S) · 92 of 100 points: Model quality 40.1/45, Memory fit 25.0/25, Speed 7.9/15, Memory use 14.8/15, workload match +5.0 Ornith 1.5 35B-A3B Q6_K · 11.1 tok/s · Runs well
  4. 92 ptsExcellent (S) · 92 of 100 points: Model quality 39.6/45, Memory fit 25.0/25, Speed 7.9/15, Memory use 14.8/15, workload match +5.0 Apodex 1.1 Mini (35B-A3B) Q6_K · 11.1 tok/s · Runs well
  5. 92 ptsExcellent (S) · 92 of 100 points: Model quality 39.6/45, Memory fit 25.0/25, Speed 7.9/15, Memory use 14.8/15, workload match +5.0 Ornith 1.0 35B-A3B Q6_K · 11.1 tok/s · Runs well

Reasoning at 32K context

  1. 94 ptsExcellent (S) · 94 of 100 points: Model quality 41.7/45, Memory fit 25.0/25, Speed 7.9/15, Memory use 14.8/15, workload match +5.0 Qwen3.6 35B-A3B Q6_K · 11.1 tok/s · Runs well
  2. 94 ptsExcellent (S) · 94 of 100 points: Model quality 41.4/45, Memory fit 25.0/25, Speed 7.9/15, Memory use 14.8/15, workload match +5.0 Qwen3.5 35B-A3B Q6_K · 11.1 tok/s · Runs well
  3. 92 ptsExcellent (S) · 92 of 100 points: Model quality 40.1/45, Memory fit 25.0/25, Speed 7.9/15, Memory use 14.8/15, workload match +5.0 Ornith 1.5 35B-A3B Q6_K · 11.1 tok/s · Runs well
  4. 92 ptsExcellent (S) · 92 of 100 points: Model quality 39.6/45, Memory fit 25.0/25, Speed 7.9/15, Memory use 14.8/15, workload match +5.0 Apodex 1.1 Mini (35B-A3B) Q6_K · 11.1 tok/s · Runs well
  5. 92 ptsExcellent (S) · 92 of 100 points: Model quality 39.6/45, Memory fit 25.0/25, Speed 7.9/15, Memory use 14.8/15, workload match +5.0 Ornith 1.0 35B-A3B Q6_K · 11.1 tok/s · Runs well

Documents (RAG) at 32K context

  1. 89 ptsExcellent (S) · 89 of 100 points: Model quality 41.2/45, Memory fit 25.0/25, Speed 7.0/15, Memory use 11.7/15, workload match +5.0 Gemma 4 26B-A4B Q6_K · 8.8 tok/s · Runs well
  2. 89 ptsExcellent (S) · 89 of 100 points: Model quality 41.7/45, Memory fit 25.0/25, Speed 7.9/15, Memory use 14.8/15 Qwen3.6 35B-A3B Q6_K · 11.1 tok/s · Runs well
  3. 89 ptsExcellent (S) · 89 of 100 points: Model quality 41.4/45, Memory fit 25.0/25, Speed 7.9/15, Memory use 14.8/15 Qwen3.5 35B-A3B Q6_K · 11.1 tok/s · Runs well
  4. 89 ptsExcellent (S) · 89 of 100 points: Model quality 40.5/45, Memory fit 25.0/25, Speed 3.5/15, Memory use 15.0/15, workload match +5.0 Gemma 4 31B Q6_K · 2.1 tok/s · Runs well
  5. 88 ptsExcellent (S) · 88 of 100 points: Model quality 42.6/45, Memory fit 25.0/25, Speed 3.7/15, Memory use 12.6/15, workload match +5.0 Qwen3.8 27B Q6_K · 2.4 tok/s · Runs well

Agents & tools at 64K context

  1. 94 ptsExcellent (S) · 94 of 100 points: Model quality 41.7/45, Memory fit 25.0/25, Speed 7.9/15, Memory use 15.0/15, workload match +5.0 Qwen3.6 35B-A3B Q6_K · 11.1 tok/s · Runs well
  2. 94 ptsExcellent (S) · 94 of 100 points: Model quality 41.4/45, Memory fit 25.0/25, Speed 7.9/15, Memory use 15.0/15, workload match +5.0 Qwen3.5 35B-A3B Q6_K · 11.1 tok/s · Runs well
  3. 92 ptsExcellent (S) · 92 of 100 points: Model quality 40.1/45, Memory fit 25.0/25, Speed 7.9/15, Memory use 15.0/15, workload match +5.0 Ornith 1.5 35B-A3B Q6_K · 11.1 tok/s · Runs well
  4. 92 ptsExcellent (S) · 92 of 100 points: Model quality 39.6/45, Memory fit 25.0/25, Speed 7.9/15, Memory use 15.0/15, workload match +5.0 Apodex 1.1 Mini (35B-A3B) Q6_K · 11.1 tok/s · Runs well
  5. 92 ptsExcellent (S) · 92 of 100 points: Model quality 39.6/45, Memory fit 25.0/25, Speed 7.9/15, Memory use 15.0/15, workload match +5.0 Ornith 1.0 35B-A3B Q6_K · 11.1 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.