Check my GPU

Best local LLMs for the Intel Core Ultra 200H (Arc 140T) (32 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. 91 ptsExcellent (S) · 91 of 100 points: Model quality 39.5/45, Memory fit 24.0/25, Speed 8.4/15, Memory use 15.0/15, workload match +5.0 Gemma 4 26B-A4B Q4_K_M · 12.6 tok/s · Tight fit
  2. 88 ptsExcellent (S) · 88 of 100 points: Model quality 33.3/45, Memory fit 24.0/25, Speed 10.8/15, Memory use 15.0/15, workload match +5.0 GLM-4.7 Flash (30B-A3B) Q3_K_M · 20.7 tok/s · Tight fit
  3. 87 ptsExcellent (S) · 87 of 100 points: Model quality 37.0/45, Memory fit 25.0/25, Speed 5.6/15, Memory use 15.0/15, workload match +5.0 Gemma 4 12B Q6_K · 5.6 tok/s · Runs well
  4. 85 ptsExcellent (S) · 85 of 100 points: Model quality 29.5/45, Memory fit 24.0/25, Speed 12.2/15, Memory use 15.0/15, workload match +5.0 Qwen3.6 35B-A3B Q2_K · 26.3 tok/s · Tight fit
  5. 85 ptsExcellent (S) · 85 of 100 points: Model quality 33.3/45, Memory fit 24.0/25, Speed 8.2/15, Memory use 15.0/15, workload match +5.0 DiffusionGemma 26B-A4B IT Q4_K_M · 12.0 tok/s · Tight fit

Coding at 32K context

  1. 88 ptsExcellent (S) · 88 of 100 points: Model quality 35.0/45, Memory fit 24.0/25, Speed 9.6/15, Memory use 15.0/15, workload match +5.0 Gemma 4 26B-A4B Q3_K_M · 16.3 tok/s · Tight fit
  2. 85 ptsExcellent (S) · 85 of 100 points: Model quality 29.5/45, Memory fit 24.0/25, Speed 12.2/15, Memory use 15.0/15, workload match +5.0 Qwen3.6 35B-A3B Q2_K · 26.3 tok/s · Tight fit
  3. 85 ptsExcellent (S) · 85 of 100 points: Model quality 29.3/45, Memory fit 24.0/25, Speed 12.2/15, Memory use 15.0/15, workload match +5.0 Qwen3.5 35B-A3B Q2_K · 26.3 tok/s · Tight fit
  4. 85 ptsExcellent (S) · 85 of 100 points: Model quality 36.1/45, Memory fit 24.0/25, Speed 5.0/15, Memory use 15.0/15, workload match +5.0 Qwen3.8 27B Q3_K_M · 4.5 tok/s · Tight fit
  5. 85 ptsExcellent (S) · 85 of 100 points: Model quality 30.2/45, Memory fit 24.0/25, Speed 10.8/15, Memory use 15.0/15, workload match +5.0 North Mini Code 1.0 (30B-A3B) Q3_K_M · 20.7 tok/s · Tight fit

Reasoning at 32K context

  1. 85 ptsExcellent (S) · 85 of 100 points: Model quality 29.5/45, Memory fit 24.0/25, Speed 12.2/15, Memory use 15.0/15, workload match +5.0 Qwen3.6 35B-A3B Q2_K · 26.3 tok/s · Tight fit
  2. 85 ptsExcellent (S) · 85 of 100 points: Model quality 31.5/45, Memory fit 25.0/25, Speed 9.0/15, Memory use 15.0/15, workload match +5.0 gpt-oss 20B MXFP4 · 14.3 tok/s · Runs well
  3. 85 ptsExcellent (S) · 85 of 100 points: Model quality 29.3/45, Memory fit 24.0/25, Speed 12.2/15, Memory use 15.0/15, workload match +5.0 Qwen3.5 35B-A3B Q2_K · 26.3 tok/s · Tight fit
  4. 85 ptsExcellent (S) · 85 of 100 points: Model quality 36.1/45, Memory fit 24.0/25, Speed 5.0/15, Memory use 15.0/15, workload match +5.0 Qwen3.8 27B Q3_K_M · 4.5 tok/s · Tight fit
  5. 84 ptsGreat (A) · 84 of 100 points: Model quality 35.5/45, Memory fit 24.0/25, Speed 5.0/15, Memory use 15.0/15, workload match +5.0 Qwen3.6 27B Q3_K_M · 4.5 tok/s · Tight fit

Documents (RAG) at 32K context

  1. 88 ptsExcellent (S) · 88 of 100 points: Model quality 35.0/45, Memory fit 24.0/25, Speed 9.6/15, Memory use 15.0/15, workload match +5.0 Gemma 4 26B-A4B Q3_K_M · 16.3 tok/s · Tight fit
  2. 87 ptsExcellent (S) · 87 of 100 points: Model quality 37.0/45, Memory fit 25.0/25, Speed 5.6/15, Memory use 15.0/15, workload match +5.0 Gemma 4 12B Q6_K · 5.6 tok/s · Runs well
  3. 85 ptsExcellent (S) · 85 of 100 points: Model quality 36.1/45, Memory fit 24.0/25, Speed 5.0/15, Memory use 15.0/15, workload match +5.0 Qwen3.8 27B Q3_K_M · 4.5 tok/s · Tight fit
  4. 84 ptsGreat (A) · 84 of 100 points: Model quality 35.2/45, Memory fit 24.0/25, Speed 5.0/15, Memory use 15.0/15, workload match +5.0 Qwen3.5 27B Q3_K_M · 4.5 tok/s · Tight fit
  5. 84 ptsGreat (A) · 84 of 100 points: Model quality 33.9/45, Memory fit 25.0/25, Speed 6.2/15, Memory use 14.0/15, workload match +5.0 Qwen3.5 9B Q6_K · 6.9 tok/s · Runs well

Agents & tools at 64K context

  1. 88 ptsExcellent (S) · 88 of 100 points: Model quality 35.0/45, Memory fit 24.0/25, Speed 9.6/15, Memory use 15.0/15, workload match +5.0 Gemma 4 26B-A4B Q3_K_M · 16.3 tok/s · Tight fit
  2. 87 ptsExcellent (S) · 87 of 100 points: Model quality 35.5/45, Memory fit 25.0/25, Speed 6.7/15, Memory use 15.0/15, workload match +5.0 Gemma 4 12B Q4_K_M · 8.0 tok/s · Runs well
  3. 85 ptsExcellent (S) · 85 of 100 points: Model quality 29.5/45, Memory fit 24.0/25, Speed 12.2/15, Memory use 15.0/15, workload match +5.0 Qwen3.6 35B-A3B Q2_K · 26.3 tok/s · Tight fit
  4. 85 ptsExcellent (S) · 85 of 100 points: Model quality 34.3/45, Memory fit 25.0/25, Speed 6.2/15, Memory use 15.0/15, workload match +5.0 Ornith 1.5 9B Q6_K · 6.9 tok/s · Runs well
  5. 85 ptsExcellent (S) · 85 of 100 points: Model quality 29.3/45, Memory fit 24.0/25, Speed 12.2/15, Memory use 15.0/15, workload match +5.0 Qwen3.5 35B-A3B Q2_K · 26.3 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.