What can the L4 run?
With 24 GB, 8 of 12 popular open models fit. The best pick is Qwen3 30B-A3B at about 53 tok/s, faster than you can read.
ollama run qwen3:30bFirst time? Install Ollama, then paste that into a terminal. Is this your machine? Check it on the homepage.
Every model the L4 can run
- Qwen3 4BQuick everyday chat and summaries~66 tok/sRuns great
qwen3:4b - Qwen3 8BA solid all-rounder for chat and writing~32 tok/sRuns great
qwen3:8b - Gemma 3 12BReads images as well as text~20 tok/sUsable
gemma3:12b - Qwen3 14BNoticeably smarter at reasoning and code~18 tok/sUsable
qwen3:14b - gpt-oss 20BOpenAI's open model. Fast, strong reasoning~53 tok/sRuns great
gpt-oss:20b - Gemma 3 27BGoogle's best open model for its size~10 tok/sSlow
gemma3:27b - Qwen3 30B-A3B30B smarts at small-model speed~53 tok/sRuns great
qwen3:30b - Qwen3 32BStrong coding and long answers~8 tok/sSlow
qwen3:32b - Llama 3.3 70BClose to the big cloud modelsneeds 45 GBToo big
llama3.3:70b - gpt-oss 120BOpenAI's largest open modelneeds 67 GBToo big
gpt-oss:120b - Qwen3 235B-A22BAlibaba's flagship open model, for multi-GPU rigsneeds 144 GBToo big
qwen3:235b - DeepSeek R1 671BThe full DeepSeek R1, for the biggest rigsneeds 406 GBToo big
deepseek-r1:671b
Can the L4 run it?
Can the L4 run Qwen3 30B-A3B?
Yes. Qwen3 30B-A3B needs about 21 GB and the L4 has 24 GB of VRAM. Expect about 53 tok/s, faster than you can read.
Can the L4 run Qwen3 32B?
Yes. Qwen3 32B needs about 22 GB and the L4 has 24 GB of VRAM. Expect about 8 tok/s, slow, but it works.
Can the L4 run Llama 3.3 70B?
No. Llama 3.3 70B needs about 45 GB and the L4 has at most 24 GB of VRAM. Ollama can still start it by putting part of the model in system RAM, but it runs several times slower. The most capable model it runs well is Qwen3 30B-A3B, at about 53 tok/s.
Real runs on the L4
Loading measured runs…
Generating a token reads the model's active weights from memory once, so speed is roughly memory bandwidth (300 GB/s) divided by the active weight size, with efficiency calibrated on our own rack. Sizes are Ollama's default 4-bit downloads plus about 1.2 GB for context. Real results are usually within about a third. Measured runs are on the leaderboard.
The Ryzen AI Max+ 395 mini PC, 128 GB runs gpt-oss 120B at about 31 tok/s, from $3,400 used.