Performance ranking of models that run in 12 GB of VRAM (GPQA Diamond (Epoch AI))

1. Rank Model Accuracy (95% interval) Quantization that fits 12 GB
2. 1
   Qwen3.6-27B

   Qwen 26.9B qwen3.6-27b

   Accuracy (95% interval) 85.9% 81.0%–90.7%

   IQ2_M 12.8 GB

3. 2
   Qwen3.6-35B-A3B

   Qwen 34.7B qwen3.6-35b-a3b

   Accuracy (95% interval) 83.8% 78.7%–89.0%

   UD-IQ2_M 12.8 GB

4. 3
   Qwen3.5-35B-A3B

   Qwen 34.7B qwen3.5-35b-a3b

   Accuracy (95% interval) 83.5% 79.2%–87.7%

   UD-IQ2_M 12.7 GB

5. 4
   Qwen3.5-9B

   Qwen 9B qwen3.5-9B

   Accuracy (95% interval) 79.0% 74.3%–83.6%

   Q8_0 11.2 GB

6. 5
   Qwen3-30B-A3B-Thinking-2507

   Qwen 30.5B qwen3-30b-a3b-thinking-2507

   Accuracy (95% interval) 70.1% 64.5%–75.6%

   UD-IQ2_M 12.5 GB

7. 6
   Qwen3-32B

   Qwen 32.8B Qwen3-32B

   Accuracy (95% interval) 65.7% 60.3%–71.2%

   UD-IQ2_XXS 12.3 GB

8. 7
   DeepSeek-R1-Distill-Qwen-32B

   deepseek-ai 32.8B DeepSeek-R1-Distill-Qwen-32B

   Accuracy (95% interval) 64.1% 58.7%–69.5%

   IQ2_XXS 12.0 GB

9. 8
   Qwen3-14B

   Qwen 14.8B qwen3-14b

   Accuracy (95% interval) 63.8% 58.0%–69.5%

   UD-Q5_K_XL 12.7 GB

10. 9
    Qwen3-30B-A3B

    Qwen 30.5B Qwen3-30B-A3B

    Accuracy (95% interval) 61.7% 55.9%–67.5%

    UD-IQ2_M 12.5 GB

11. 10
    gpt-oss-20b

    openai 20.9B gpt-oss-20b_medium

    Accuracy (95% interval) 60.8% 55.9%–65.7%

    Q5_K_S 12.9 GB

12. 11
    Qwen3-8B

    Qwen 8.2B qwen3-8b

    Accuracy (95% interval) 56.8% 51.0%–62.5%

    UD-Q8_K_XL 12.9 GB

13. 12
    phi-4

    microsoft 14.7B phi-4

    Accuracy (95% interval) 56.1% 51.0%–61.1%

    Q5_K_S 12.6 GB

14. 13
    Qwen3-30B-A3B-Instruct-2507

    Qwen 30.5B qwen3-30b-a3b-instruct-2507

    Accuracy (95% interval) 55.6% 50.0%–61.3%

    Q2_K_L 12.9 GB

15. 14
    Qwen3-4B

    Qwen 4B qwen3-4b

    Accuracy (95% interval) 52.3% 46.4%–58.2%

    BF16 10.1 GB

16. 15
    Mistral-Small-3.2-24B-Instruct-2506

    mistralai 23.6B mistral-small-3.2-2506

    Accuracy (95% interval) 49.1% 43.6%–54.5%

    IQ3_M 12.8 GB

17. 16
    gemma-3-27b-it

    google 27B gemma-3-27b-it

    Accuracy (95% interval) 47.7% 42.4%–53.0%

    UD-IQ2_M 12.0 GB

18. 17
    Qwen2.5-32B-Instruct

    Qwen 32.8B qwen2.5-32b-instruct

    Accuracy (95% interval) 46.1% 41.0%–51.2%

    IQ2_XXS 12.0 GB

19. 18
    DeepSeek-R1-Distill-Qwen-14B

    deepseek-ai 14.8B DeepSeek-R1-Distill-Qwen-14B

    Accuracy (95% interval) 44.7% 39.1%–50.3%

    Q5_K_S 12.7 GB

20. 19
    gemma-3-12b-it

    google 11.8B gemma-3-12b-it

    Accuracy (95% interval) 39.5% 34.5%–44.4%

    UD-Q6_K_XL 12.7 GB

21. 20
    Qwen3-1.7B

    Qwen 1.7B qwen3-1.7b

    Accuracy (95% interval) 38.0% 32.6%–43.4%

    BF16 5.86 GB

22. 21
    gemma-2-27b-it

    google 27.2B gemma-2-27b-it

    Accuracy (95% interval) 36.5% 31.8%–41.2%

    IQ2_M 12.9 GB

23. 22
    Qwen2.5-7B-Instruct

    Qwen 7.6B qwen2.5-7b-instruct

    Accuracy (95% interval) 35.5% 31.0%–40.0%

    Q8_0 9.42 GB

24. 23
    DeepSeek-R1-Distill-Qwen-1.5B

    deepseek-ai 1.8B DeepSeek-R1-Distill-Qwen-1.5B

    Accuracy (95% interval) 33.6% 29.5%–37.6%

    F32 8.20 GB

25. 24
    gemma-2-9b-it

    google 9.2B gemma-2-9b-it

    Accuracy (95% interval) 27.5% 22.9%–32.0%

    Q6_K 11.1 GB

26. 25
    Llama-3.2-1B-Instruct

    meta-llama 1.2B Llama-3.2-1B-Instruct

    Accuracy (95% interval) 23.9% 20.7%–27.1%

    F16 3.55 GB

27. 26
    gemma-3-4b-it

    google 3.9B gemma-3-4b-it

    Accuracy (95% interval) 23.2% 19.6%–26.9%

    BF16 9.19 GB

28. 27
    gemma-3-1b-it

    google 1B gemma-3-1b-it

    Accuracy (95% interval) 19.9% 17.0%–22.9%

    F16 3.14 GB

Estimated Memory at 8K: Estimated with a formula. Actual usage depends on your setup and settings.