Arc B570

With 10 GB

One entry per model, up to 30, sorted by popularity. For each model we show the largest (most precise) quantization that fits in this memory with a context of at least 8K tokens. The context length is the longest one that quantization fits (for models whose maximum is under 8K, such as embedding models, that maximum). Models that are not for chat or text generation are labelled with their use. "Left" is the memory minus the estimate; under 5% of the memory is marked "tight" (not a guarantee that it fits).

• Qwen3.8-27B IQ2_XXS Image input
  Context length 8,192 Estimated 10.7 GB 0.02 GB left (tight) Speed 25–34
• Ornith-1.5-9B Q6_K Image input
  Context length 32,768 Estimated 10.7 GB 0.01 GB left (tight) Speed 27–36
• Huihui-Qwen3.8-27B-abliterated UD-IQ2_S Image input
  Context length 8,192 Estimated 10.5 GB 0.22 GB left (tight) Speed 26–35
• gemma-4-12B-it Q5_K_L Image input
  Context length 8,192 Estimated 10.7 GB 0.01 GB left (tight) Speed 25–34
• Ornith-1.0-9B Q6_K
  Context length 65,536 Estimated 10.6 GB 0.10 GB left (tight) Speed 31–41
• mxbai-embed-large-v1 F32 Embedding (not for chat)
  Context length 512 Estimated 2.41 GB 8.33 GB left Speed 171–227
• Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-NEO-IMATRIX-MAX-MTP Q6_K Image input
  Context length 16,384 Estimated 10.4 GB 0.34 GB left (tight) Speed 26–35
• MOSS-Music-8B-Instruct Q4_K_M
  Context length 16,384 Estimated 8.45 GB 2.29 GB left Speed 44–59
• Qwen3-VL-8B-Instruct UD-Q6_K_XL Image input
  Context length 8,192 Estimated 9.55 GB 1.19 GB left Speed 30–41
• Qwen3.5-9B UD-Q6_K_XL Image input
  Context length 16,384 Estimated 10.4 GB 0.35 GB left (tight) Speed 26–35
• Ornith-1.5-9B-uncensored Q6_K
  Context length 65,536 Estimated 10.6 GB 0.13 GB left (tight) Speed 31–41
• Ternary-Bonsai-2-27B Q2_0
  Context length 16,384 Estimated 9.90 GB 0.84 GB left Speed 30–40
• Swift-1.5-Qwen3.8-27B-GSQ-RCO IQ2_XS
  Context length 8,192 Estimated 10.5 GB 0.23 GB left (tight) Speed 26–35
• Qwen3.5-4B BF16 Image input
  Context length 16,384 Estimated 10.3 GB 0.44 GB left (tight) Speed 26–35
• Dirk-Qwen3.8-27B IQ2_XS Image input
  Context length 8,192 Estimated 10.5 GB 0.23 GB left (tight) Speed 26–35
• Wan2.1 Q4_K_M
  Context length 32,768 Estimated 9.16 GB 1.58 GB left Speed 39–53
• Qwen3.8-27B-GSQ-RCO IQ2_XS Image input
  Context length 8,192 Estimated 10.5 GB 0.23 GB left (tight) Speed 26–35
• Qwen3-ASR-1.7B F16 Speech / audio
  Context length 32,768 Estimated 8.70 GB 2.04 GB left Speed 56–74
• gemma-4-E4B-it-qat-q4_0 Q4_0 Image input
  Context length 131,072 Estimated 8.42 GB 2.32 GB left Speed 44–59
• Ternary-Bonsai-2-9B Q8_0 Image input
  Context length 131,072 Estimated 8.07 GB 2.67 GB left Speed 85–114
• HyperCLOVAX-SEED-Text-Instruct-1.5B-Q4_K_M Q4_K_M
  Context length 65,536 Estimated 8.34 GB 2.40 GB left Speed 201–268
• gemma-4-12B-it-qat-q4_0 Q4_0 Image input
  Context length 131,072 Estimated 10.7 GB 0.04 GB left (tight) Speed 33–44
• Hy-MT2-7B Q8_0
  Context length 8,192 Estimated 9.86 GB 0.88 GB left Speed 29–38
• Qwen3.8-27B-Heretic-Abliterated-Uncensored IQ2_XXS
  Context length 8,192 Estimated 10.6 GB 0.11 GB left (tight) Speed 26–34
• Ternary-Bonsai-2-2B Q2_0 Image input
  Context length 262,144 Estimated 4.83 GB 5.90 GB left Speed 417–556
• Qwen3.8-27B-Turbo-Brilliance-50X-Reasoning-Instruct-NEO-MAX-MTP IQ2_XS Image input
  Context length 8,192 Estimated 10.5 GB 0.23 GB left (tight) Speed 26–35
• MiMo-V2.6-Distill-Qwen-9B Q6_K_L Image input
  Context length 32,768 Estimated 10.3 GB 0.46 GB left (tight) Speed 28–38
• Cyber-Ornith-1.5-9B-OBLITERATED Q6_K
  Context length 65,536 Estimated 10.6 GB 0.13 GB left (tight) Speed 31–41
• Sharp-Spark-X2.5-4B Q6_K_XL
  Context length 131,072 Estimated 9.36 GB 1.37 GB left Speed 63–84
• AdaVaR-3B F16
  Context length 65,536 Estimated 9.44 GB 1.30 GB left Speed 37–49