Discrete GPU
GeForce RTX 4060 Ti
Data as of
- Source
- Checked:
With 8 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-IQ1_MContext length 8,192 Estimated 8.47 GB 0.12 GB left (tight)
-
Ornith-1.5-9B Q5_K_MContext length 16,384 Estimated 8.49 GB 0.10 GB left (tight)
-
Context length 8,192 Estimated 8.49 GB 0.10 GB left (tight)
-
Ornith-1.0-9B Q5_K_MContext length 16,384 Estimated 8.13 GB 0.46 GB left
-
Context length 512 Estimated 2.41 GB 6.18 GB left
-
Context length 8,192 Estimated 8.35 GB 0.24 GB left (tight)
-
MOSS-Music-8B-Instruct Q4_K_MContext length 16,384 Estimated 8.45 GB 0.14 GB left (tight)
-
Context length 8,192 Estimated 7.94 GB 0.65 GB left
-
Context length 8,192 Estimated 8.48 GB 0.11 GB left (tight)
-
Ornith-1.5-9B-uncensored Q5_K_MContext length 16,384 Estimated 8.10 GB 0.49 GB left
-
Context length 32,768 Estimated 8.12 GB 0.47 GB left
-
Wan2.1 Q4_K_MContext length 16,384 Estimated 8.08 GB 0.51 GB left
-
Context length 16,384 Estimated 6.82 GB 1.77 GB left
-
Context length 131,072 Estimated 8.42 GB 0.17 GB left (tight)
-
Context length 131,072 Estimated 8.07 GB 0.52 GB left
-
Context length 65,536 Estimated 8.34 GB 0.25 GB left (tight)
-
Hy-MT2-7B Q6_KContext length 8,192 Estimated 8.04 GB 0.55 GB left
-
Context length 262,144 Estimated 4.83 GB 3.76 GB left
-
Context length 16,384 Estimated 8.51 GB 0.08 GB left (tight)
-
Context length 16,384 Estimated 8.10 GB 0.49 GB left
-
Sharp-Spark-X2.5-4B Q6_K_XLContext length 65,536 Estimated 6.95 GB 1.64 GB left
-
AdaVaR-3B F16Context length 32,768 Estimated 8.23 GB 0.36 GB left (tight)
-
Qwen3-8B Q5_K_LContext length 8,192 Estimated 8.29 GB 0.30 GB left (tight)
-
Qwen3.5-9B-Kimi-k3-Distilled Q5_K_MContext length 16,384 Estimated 8.28 GB 0.31 GB left (tight)
-
Qwen3-4B-Instruct-2507 UD-Q8_K_XLContext length 16,384 Estimated 8.32 GB 0.27 GB left (tight)
-
B1-9B Q5_K_MContext length 16,384 Estimated 8.28 GB 0.31 GB left (tight)
-
Context length 16,384 Estimated 8.32 GB 0.27 GB left (tight)
-
Qwen2.5-7B-Instruct Q6_K_LContext length 16,384 Estimated 8.31 GB 0.28 GB left (tight)
-
Qwen3-4B UD-Q8_K_XLContext length 16,384 Estimated 8.32 GB 0.27 GB left (tight)
-
Context length 8,192 Estimated 8.34 GB 0.25 GB left (tight)
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_SContext length 8,192 Estimated 17.1 GB 0.08 GB left (tight)
-
Ornith-1.5-9B Q8_0Context length 131,072 Estimated 15.2 GB 1.97 GB left
-
Context length 131,072 Estimated 17.0 GB 0.14 GB left (tight)
-
Context length 8,192 Estimated 17.2 GB 0.02 GB left (tight)
-
Context length 65,536 Estimated 16.5 GB 0.66 GB left (tight)
-
Context length 65,536 Estimated 16.3 GB 0.89 GB left
-
Qwen3.8-27B-Uncensored IQ4_XSContext length 8,192 Estimated 17.0 GB 0.13 GB left (tight)
-
Ornith-1.0-9B Q8_0Context length 131,072 Estimated 14.9 GB 2.23 GB left
-
Context length 512 Estimated 2.41 GB 14.8 GB left
-
Context length 32,768 Estimated 17.1 GB 0.05 GB left (tight)
-
Context length 131,072 Estimated 16.1 GB 1.05 GB left
-
Context length 40,960 Estimated 15.6 GB 1.58 GB left
-
Context length 32,768 Estimated 16.8 GB 0.39 GB left (tight)
-
Context length 32,768 Estimated 16.8 GB 0.36 GB left (tight)
-
Context length 32,768 Estimated 16.5 GB 0.68 GB left (tight)
-
Context length 65,536 Estimated 16.2 GB 0.96 GB left
-
Context length 131,072 Estimated 14.9 GB 2.26 GB left
-
Context length 8,192 Estimated 17.0 GB 0.14 GB left (tight)
-
Ternary-Bonsai-2-27B Q2_0Context length 65,536 Estimated 13.1 GB 4.06 GB left
-
Context length 32,768 Estimated 15.5 GB 1.71 GB left
-
Context length 131,072 Estimated 14.1 GB 3.12 GB left
-
Context length 8,192 Estimated 17.0 GB 0.13 GB left (tight)
-
Context length 8,192 Estimated 17.1 GB 0.08 GB left (tight)
-
Wan2.1 IQ3_SContext length 32,768 Estimated 16.0 GB 1.21 GB left
-
Context length 32,768 Estimated 15.5 GB 1.71 GB left
-
Context length 65,536 Estimated 12.5 GB 4.72 GB left
-
Context length 65,536 Estimated 16.3 GB 0.89 GB left
-
Context length 16,384 Estimated 16.9 GB 0.29 GB left (tight)
-
Context length 131,072 Estimated 8.42 GB 8.76 GB left
-
Context length 262,144 Estimated 12.4 GB 4.82 GB left
Frequently asked questions
- Which local LLMs run on GeForce RTX 4060 Ti?
- On this site, 834 models have a quantization that fits in 16 GB at 8,192 tokens (estimated). Popular ones include Qwen3.8-27B, Ornith-1.5-9B, Huihui-Qwen3.6-35B-A3B-abliterated-MTP, Ornith-1.5-35B-A3B, Huihui-Qwen3.8-27B-abliterated.
- What is the largest model that runs on GeForce RTX 4060 Ti?
- Among the models listed here, Qwen3.8-Flash-Next-FP4-Local-Strata (about 51.2B); BF16 fits in 16 GB (estimated at 8,192 tokens).