Performance ranking by Epoch Capabilities Index (Epoch AI)

1. Rank Model Index (95% interval) Memory at 8K
2. 1
   Kimi-K3

   moonshotai 2,779.5B Kimi K3

   Index (95% interval) 158.5 156.5–160.7

   UD-Q1_0 468 GB

3. 2
   GLM-5.3

   zai-org 753.9B GLM-5.3

   Index (95% interval) 156.9 154.8–159.2

   UD-IQ1_S 218 GB

4. 3
   DeepSeek-V4-Pro-0813

   deepseek-ai 1,573B DeepSeek V4 Pro 0813

   Index (95% interval) 155.9 154.0–158.0

   UD-Q4_K_XL 851 GB

5. 4
   DeepSeek-V4-Flash-0731

   deepseek-ai 284.3B DeepSeek V4 Flash 0731

   Index (95% interval) 154.4 152.5–156.4

   UD-IQ1_S 83.4 GB

6. 5
   GLM-5.2

   zai-org 753.9B GLM-5.2

   Index (95% interval) 153.0 151.3–154.9

   UD-Q4_K_M 467 GB

7. 6
   Qwen3.8-27B

   Qwen 27.3B Qwen 3.8 27B

   Index (95% interval) 152.7 150.7–154.9

   UD-Q4_K_M 18.2 GB

8. 7
   Kimi-K2.6

   moonshotai 1,026.4B Kimi K2.6

   Index (95% interval) 151.5 149.8–153.4

   UD-Q2_K_XL 342 GB

9. 8
   Kimi-K2.7-Code

   moonshotai 1,026.4B Kimi K2.7 Code

   Index (95% interval) 151.1 149.1–153.2

   UD-IQ1_M 305 GB

10. 9
    Qwen3.5-397B-A17B

    Qwen 396.3B Qwen3.5 397B-A17B

    Index (95% interval) 147.9 145.8–150.2

    Q4_K_M 246 GB

11. 10
    DeepSeek-V4-Flash

    deepseek-ai 284.3B DeepSeek-V4-Flash

    Index (95% interval) 146.9 143.6–150.2

    UD-IQ1_S 83.4 GB

12. 11
    Qwen3.6-27B

    Qwen 26.9B Qwen3.6 27B

    Index (95% interval) 146.7 144.6–148.9

    Q4_K_M 18.6 GB

13. 12
    gemma-4-31B-it

    google 30.7B Gemma 4 31B IT

    Index (95% interval) 144.2 141.8–146.8

    Q4_K_M 21.3 GB

14. 13
    Qwen3.6-35B-A3B

    Qwen 34.7B Qwen 3.6 35B-A3B

    Index (95% interval) 144.1 142.1–145.9

    UD-Q4_K_M 23.4 GB

15. 14
    Qwen3.5-35B-A3B

    Qwen 34.7B Qwen3.5-35B-A3B

    Index (95% interval) 144.0 141.5–146.6

    Q4_K_M 23.3 GB

16. 15
    gemma-4-26B-A4B-it

    google 25.2B Gemma 4 26B A4B

    Index (95% interval) 141.7 139.2–144.2

    UD-Q4_K_M 18.5 GB

17. 16
    gpt-oss-120b

    openai 116.8B gpt-oss-120b

    Index (95% interval) 140.2 138.3–142.0

    MXFP4 64.7 GB

18. 17
    Qwen3.5-9B

    Qwen 9B Qwen3.5-9B

    Index (95% interval) 139.4 137.1–141.5

    Q4_K_M 7.05 GB

19. 18
    DeepSeek-R1

    deepseek-ai 671B DeepSeek-R1

    Index (95% interval) 138.7 136.7–140.4

    Q4_K_M 446 GB

20. 19
    Qwen3-30B-A3B-Thinking-2507

    Qwen 30.5B Qwen3-30B-A3B-Thinking (Jul 2025)

    Index (95% interval) 138.4 135.7–140.9

    Q4_K_M 20.2 GB

21. 20
    Qwen3-32B

    Qwen 32.8B Qwen3-32B

    Index (95% interval) 137.0 134.5–139.4

    Q4_K_M 22.8 GB

22. 21
    QwQ-32B

    Qwen 32.8B QwQ-32B

    Index (95% interval) 136.5 133.6–139.3

    Q4_K_M 22.8 GB

23. 22
    Qwen3-14B

    Qwen 14.8B Qwen3-14B

    Index (95% interval) 136.2 133.5–138.7

    Q4_K_M 11.2 GB

24. 23
    Qwen3-30B-A3B-Instruct-2507

    Qwen 30.5B Qwen3-30B-A3B-Instruct (Jul 2025)

    Index (95% interval) 135.2 132.3–138.0

    Q4_K_M 20.2 GB

25. 24
    gpt-oss-20b

    openai 20.9B gpt-oss-20b

    Index (95% interval) 135.0 132.4–137.5

    Q4_K_M 12.8 GB

26. 25
    Qwen3-30B-A3B

    Qwen 30.5B Qwen3-30B-A3B

    Index (95% interval) 134.2 131.3–136.9

    Q4_K_M 20.2 GB

27. 26
    Qwen3-8B

    Qwen 8.2B Qwen3-8B

    Index (95% interval) 132.2 129.1–135.1

    Q4_K_M 7.08 GB

28. 27
    phi-4

    microsoft 14.7B Phi-4

    Index (95% interval) 129.1 126.1–131.9

    Q4_K_M 11.5 GB

29. 28
    gemma-3-27b-it

    google 27B Gemma 3 27B

    Index (95% interval) 127.7 124.6–130.5

    Q4_K_M 18.9 GB

30. 29
    Llama-3.3-70B-Instruct

    meta-llama 70.6B Llama 3.3 70B

    Index (95% interval) 126.2 123.2–128.9

    Q4_K_M 46.0 GB

31. 30
    Qwen2.5-Coder-7B

    QuantFactory 7.6B Qwen2.5-Coder (7B)

    Index (95% interval) 108.0 98.7–116.4

    Q4_K_M 6.00 GB

32. 31
    Mistral-7B-v0.1

    mistralai 7.2B Mistral 7B v0.1

    Index (95% interval) 103.3 95.7–109.8

    Q4_K_M 6.04 GB

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