ToolSite

What LLMs can an RTX 4060 8GB run?

An RTX 4060 8GB gives a model 8 GB of memory and 272 GB/s of bandwidth. Of the 40 open models tracked here, 6 fit at Q4_K_M with an 8,192-token context, and 1 more at a lower precision.

Models that fit on one RTX 4060 8GB

The most precise weights that still fit with 8K tokens of context and one request, the memory that takes, the longest context at that precision and the writing speed. Bigger models come first.

Model Best precision Memory Longest context Tokens/s
Gemma 4 12B 12.0B GGUF Q3_K_M 6.90 GB 135K 23–32
Qwen3.5 9B 9.7B GGUF Q5_K_M 7.78 GB 14K 20–28
Qwen3 8B 8.2B GGUF Q5_K_M 7.68 GB 9K 21–29
Llama 3.1 8B 8.0B GGUF Q5_K_M 7.43 GB 11K 21–30
Gemma 4 E4B 8.0B GGUF Q6_K 7.38 GB 44K 22–30
Nemotron 3 Nano 4B 4.0B GGUF Q8_0 4.96 GB 184K 33–46
MiniCPM5 2B 2.5B FP16 / BF16 6.02 GB 51K 27–37

Too big for one card

How many RTX 4060 8GB cards these need at Q4_K_M in one tensor-parallel group; some need more than 8.

How these numbers are worked out

Memory is the weights at each precision plus the KV cache for 8,192 tokens in FP16 and runtime overhead (0.5 GB plus 10%), computed from each model's files on Hugging Face with the LLM VRAM Calculator. Speed is estimated from memory bandwidth and the parameters read per token with the LLM Speed Calculator. Both tools take any other model from Hugging Face.

Other GPUs and Macs

Model numbers read from Hugging Face on .