GeForce RTX 4080 SUPER

With 16 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 UD-Q4_K_S
  Context length 8,192 Estimated 17.1 GB 0.08 GB left (tight) Speed 29–38
• Ornith-1.5-9B Q8_0
  Context length 131,072 Estimated 15.2 GB 1.97 GB left Speed 45–60
• Huihui-Qwen3.6-35B-A3B-abliterated-MTP Q2_K Image input
  Context length 131,072 Estimated 17.0 GB 0.14 GB left (tight) Speed not estimated (MoE)
• Huihui-Qwen3.8-27B-abliterated IQ4_XS
  Context length 8,192 Estimated 17.2 GB 0.02 GB left (tight) Speed 29–38
• Tiel-Coder-35B-A3B-GGUF-MTP UD-IQ3_S Image input
  Context length 65,536 Estimated 16.5 GB 0.66 GB left (tight) Speed not estimated (MoE)
• gemma-4-12B-it UD-Q8_K_XL Image input
  Context length 65,536 Estimated 16.3 GB 0.89 GB left Speed 32–43
• Qwen3.8-27B-Uncensored IQ4_XS
  Context length 8,192 Estimated 17.0 GB 0.13 GB left (tight) Speed 29–38
• Ornith-1.0-9B Q8_0
  Context length 131,072 Estimated 14.9 GB 2.23 GB left Speed 46–62
• mxbai-embed-large-v1 F32 Embedding (not for chat)
  Context length 512 Estimated 2.41 GB 14.8 GB left Speed 330–440
• Qwen3.6-35B-A3B-MTP UD-IQ3_S Image input
  Context length 32,768 Estimated 17.1 GB 0.05 GB left (tight) Speed not estimated (MoE)
• Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-NEO-IMATRIX-MAX-MTP Q8_0 Image input
  Context length 131,072 Estimated 16.1 GB 1.05 GB left Speed 41–55
• MOSS-Music-8B-Instruct Q8_0 Speech / audio
  Context length 40,960 Estimated 15.6 GB 1.58 GB left Speed 51–68
• Qwen3.8-27B-Uncensored-HauhauCS-Aggressive-MTP Q3_K Image input
  Context length 32,768 Estimated 16.8 GB 0.39 GB left (tight) Speed 33–44
• gemma-4-26B-A4B-it Q4_0 Image input
  Context length 32,768 Estimated 16.8 GB 0.36 GB left (tight) Speed not estimated (MoE)
• Qwen3-VL-8B-Instruct UD-Q8_K_XL Image input
  Context length 32,768 Estimated 16.5 GB 0.68 GB left (tight) Speed 41–54
• Qwen3.5-9B UD-Q8_K_XL Image input
  Context length 65,536 Estimated 16.2 GB 0.96 GB left Speed 34–45
• Ornith-1.5-9B-uncensored Q8_0
  Context length 131,072 Estimated 14.9 GB 2.26 GB left Speed 46–62
• Qwen3.6-35B-A3B IQ3_XXS Image input
  Context length 8,192 Estimated 17.0 GB 0.14 GB left (tight) Speed not estimated (MoE)
• Ternary-Bonsai-2-27B Q2_0
  Context length 65,536 Estimated 13.1 GB 4.06 GB left Speed 58–77
• Swift-1.5-Qwen3.8-27B-GSQ-RCO IQ3_S
  Context length 32,768 Estimated 15.5 GB 1.71 GB left Speed 36–49
• Qwen3.5-4B BF16 Image input
  Context length 131,072 Estimated 14.1 GB 3.12 GB left Speed 51–68
• Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NEO-CODER-MAX-MTP IQ4_XS Image input
  Context length 8,192 Estimated 17.0 GB 0.13 GB left (tight) Speed 29–38
• Dirk-Qwen3.8-27B UD-Q4_K_S Image input
  Context length 8,192 Estimated 17.1 GB 0.08 GB left (tight) Speed 29–38
• Wan2.1 IQ3_S
  Context length 32,768 Estimated 16.0 GB 1.21 GB left Speed 35–47
• Qwen3.8-27B-GSQ-RCO IQ3_S Image input
  Context length 32,768 Estimated 15.5 GB 1.71 GB left Speed 36–49
• Qwen3-ASR-1.7B F16 Speech / audio
  Context length 65,536 Estimated 12.5 GB 4.72 GB left Speed 108–144
• Qwen3.8-35B-A3B-Distill Q2_K
  Context length 65,536 Estimated 16.3 GB 0.89 GB left Speed not estimated (MoE)
• Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive IQ3_M Image input
  Context length 16,384 Estimated 16.9 GB 0.29 GB left (tight) Speed not estimated (MoE)
• gemma-4-E4B-it-qat-q4_0 Q4_0 Image input
  Context length 131,072 Estimated 8.42 GB 8.76 GB left Speed 86–114
• Ternary-Bonsai-2-9B Q8_0 Image input
  Context length 262,144 Estimated 12.4 GB 4.82 GB left Speed 165–220