Radeon RX 6750 XT

With 12 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_S Image input
  Context length 8,192 Estimated 12.9 GB 0.00 GB left (tight) Speed 23–31
• Ornith-1.5-9B Q8_0
  Context length 32,768 Estimated 12.0 GB 0.90 GB left Speed 26–35
• Huihui-Qwen3.8-27B-abliterated UD-IQ3_XXS Image input
  Context length 8,192 Estimated 12.8 GB 0.12 GB left (tight) Speed 24–31
• gemma-4-12B-it UD-Q6_K_XL Image input
  Context length 32,768 Estimated 12.8 GB 0.09 GB left (tight) Speed 24–32
• Qwen3.8-27B-Uncensored IQ2_M
  Context length 8,192 Estimated 12.4 GB 0.52 GB left (tight) Speed 24–33
• Ornith-1.0-9B Q8_0
  Context length 65,536 Estimated 12.8 GB 0.08 GB left (tight) Speed 27–36
• mxbai-embed-large-v1 F32 Embedding (not for chat)
  Context length 512 Estimated 2.41 GB 10.5 GB left Speed 194–258
• Qwen3.6-35B-A3B-MTP UD-IQ1_M Image input
  Context length 16,384 Estimated 12.8 GB 0.07 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 16,384 Estimated 12.4 GB 0.51 GB left (tight) Speed 24–32
• MOSS-Music-8B-Instruct Q8_0 Speech / audio
  Context length 16,384 Estimated 12.0 GB 0.91 GB left Speed 30–40
• Qwen3.8-27B-Uncensored-HauhauCS-Aggressive-MTP Q2_K Image input
  Context length 8,192 Estimated 12.4 GB 0.47 GB left (tight) Speed 24–32
• gemma-4-26B-A4B-it UD-IQ3_S Image input
  Context length 8,192 Estimated 12.8 GB 0.04 GB left (tight) Speed not estimated (MoE)
• Qwen3-VL-8B-Instruct UD-Q8_K_XL Image input
  Context length 8,192 Estimated 12.9 GB 0.00 GB left (tight) Speed 24–32
• Qwen3.5-9B Q8_0 Image input
  Context length 32,768 Estimated 12.0 GB 0.91 GB left Speed 26–35
• Ornith-1.5-9B-uncensored Q8_0
  Context length 65,536 Estimated 12.8 GB 0.11 GB left (tight) Speed 27–36
• Qwen3.6-35B-A3B UD-IQ2_M Image input
  Context length 8,192 Estimated 12.8 GB 0.08 GB left (tight) Speed not estimated (MoE)
• Ternary-Bonsai-2-27B Q2_0
  Context length 32,768 Estimated 11.0 GB 1.91 GB left Speed 34–45
• Swift-1.5-Qwen3.8-27B-GSQ-RCO IQ3_XXS
  Context length 16,384 Estimated 12.7 GB 0.17 GB left (tight) Speed 25–33
• Qwen3.5-4B BF16 Image input
  Context length 65,536 Estimated 11.9 GB 0.97 GB left Speed 30–40
• Dirk-Qwen3.8-27B IQ3_XXS Image input
  Context length 16,384 Estimated 12.7 GB 0.17 GB left (tight) Speed 25–33
• Wan2.1 IQ2_M
  Context length 8,192 Estimated 12.4 GB 0.49 GB left (tight) Speed 24–33
• Qwen3.8-27B-GSQ-RCO IQ3_XXS Image input
  Context length 16,384 Estimated 12.7 GB 0.17 GB left (tight) Speed 25–33
• Qwen3-ASR-1.7B F16 Speech / audio
  Context length 65,536 Estimated 12.5 GB 0.43 GB left (tight) Speed 63–84
• Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive IQ2_M Image input
  Context length 4,096 Estimated 12.9 GB 0.03 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 4.47 GB left Speed 50–67
• Ternary-Bonsai-2-9B Q8_0 Image input
  Context length 262,144 Estimated 12.4 GB 0.52 GB left (tight) Speed 97–129
• HyperCLOVAX-SEED-Text-Instruct-1.5B-Q4_K_M Q4_K_M
  Context length 65,536 Estimated 8.34 GB 4.55 GB left Speed 229–305
• gemma-4-12B-it-qat-q4_0 Q4_0 Image input
  Context length 262,144 Estimated 12.8 GB 0.04 GB left (tight) Speed 37–50
• Hy-MT2-7B Q8_0
  Context length 16,384 Estimated 10.9 GB 1.96 GB left Speed 32–43
• Swift-1.5-Qwen3.8-27B-heretic-GSQ-RCO IQ3_XXS Image input
  Context length 16,384 Estimated 12.7 GB 0.17 GB left (tight) Speed 25–33