Performance ranking of models that run in 8 GB of VRAM (LMArena)

1. Rank Model Score (95% interval) Quantization that fits 8 GB
2. 1
   Qwen3.8-27B

   Qwen 27.3B qwen3.8-27b

   Score (95% interval) 1,433 1,429–1,438

   32,659 votes

   UD-IQ1_M 8.47 GB

3. 2
   gemma-3-12b-it

   google 11.8B Gemma 3 12B IT

   Score (95% interval) 1,342 1,332–1,351

   3,829 votes

   UD-Q3_K_XL 8.26 GB

4. 3
   gemma-3n-E4B-it

   google 6.9B Gemma 3n E4B IT

   Score (95% interval) 1,317 1,312–1,323

   22,106 votes

   Q8_0 8.53 GB

5. 4
   gemma-3-4b-it

   google 3.9B Gemma 3 4B IT

   Score (95% interval) 1,303 1,294–1,313

   4,171 votes

   UD-Q8_K_XL 6.59 GB

6. 5
   granite-4.2-8b

   ibm-granite 8.8B Granite 4.2 8B

   Score (95% interval) 1,290 1,278–1,301

   3,196 votes

   Q5_K_M 8.34 GB

7. 6
   granite-4.2-3b

   ibm-granite 3.7B Granite 4.2 3B

   Score (95% interval) 1,289 1,277–1,301

   3,185 votes

   Q8_0 5.31 GB

8. 7
   gemma-2-9b-it

   google 9.2B Gemma 2 9B IT

   Score (95% interval) 1,267 1,263–1,271

   54,611 votes

   IQ4_XS 8.45 GB

9. 8
   phi-4

   microsoft 14.7B phi-4

   Score (95% interval) 1,256 1,252–1,261

   24,126 votes

   Q2_K 7.97 GB

10. 9
    gemma-2-2b-it

    google 2.6B Gemma 2 2B IT

    Score (95% interval) 1,200 1,196–1,204

    46,616 votes

    F16 6.98 GB

11. 10
    Llama-3.2-3B-Instruct

    meta-llama 3.2B Llama 3.2 3B Instruct

    Score (95% interval) 1,167 1,159–1,175

    7,936 votes

    F16 8.17 GB

12. 11
    Mistral-7B-Instruct-v0.2

    mistralai 7.2B Mistral 7B Instruct v0.2

    Score (95% interval) 1,149 1,143–1,156

    19,402 votes

    Q6_K 7.62 GB

13. 12
    Llama-3.2-1B-Instruct

    meta-llama 1.2B Llama 3.2 1B Instruct

    Score (95% interval) 1,111 1,103–1,119

    8,045 votes

    F16 3.55 GB

14. 13
    gemma-2b-it

    lmstudio-ai 2.5B Gemma 2B IT

    Score (95% interval) 1,094 1,082–1,105

    4,780 votes

    Q8_0 3.89 GB

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