ToolSite

What LLMs can an RTX 4090 run?

An RTX 4090 gives a model 24 GB of memory and 1,008 GB/s of bandwidth. Of the 40 open models tracked here, 18 fit at Q4_K_M with an 8,192-token context.

Models that fit on one RTX 4090

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
Qwen3.6 35B-A3B 36.0B, 3B active GGUF Q4_K_M 23.0 GB 56K 124–226
Nemotron 3 Nano 30B-A3B 31.6B, 3.5B active GGUF Q5_K_M 23.5 GB 88K 101–181
Gemma 4 31B 31.3B GGUF Q4_K_M 21.1 GB 75K 26–37
GLM-4.7 Flash 31.2B, 3B active GGUF Q5_K_M 23.6 GB 14K 100–179
Xing 4.0 29B-A4B 31.2B, 4B active GGUF Q5_K_M 23.6 GB 17K 82–145
Qwen3 30B-A3B 30.5B, 3.3B active GGUF Q5_K_M 23.5 GB 12K 84–148
Muse Glimmer 30B 29.8B GGUF Q5_K_M 22.3 GB 128K (full) 25–35
Qwen3.6 27B 27.8B GGUF Q5_K_M 21.2 GB 48K 26–37
Qwen3.8 27B 27.8B GGUF Q5_K_M 21.2 GB 48K 26–37
Gemma 4 26B-A4B 25.8B, 4B active GGUF Q6_K 22.5 GB 149K 75–132
gpt-oss-20b 20.9B, 3.6B active GGUF Q8_0 23.5 GB 28K 67–118
Gemma 4 12B 12.0B GGUF Q8_0 13.9 GB 256K (full) 40–56
Qwen3.5 9B 9.7B FP16 / BF16 20.6 GB 108K 27–38
Qwen3 8B 8.2B FP16 / BF16 18.5 GB 40K (full) 30–42
Llama 3.1 8B 8.0B FP16 / BF16 18.1 GB 51K 31–43
Gemma 4 E4B 8.0B FP16 / BF16 17.0 GB 128K (full) 33–46
Nemotron 3 Nano 4B 4.0B FP16 / BF16 8.78 GB 256K (full) 62–89
MiniCPM5 2B 2.5B FP16 / BF16 6.02 GB 128K (full) 89–131

Too big for one card

How many RTX 4090 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 .