What can the Radeon 780M run?
With 16 GB, 3 of 12 popular open models fit. The best pick is Gemma 3 12B at about 6 tok/s, slow, but it works.
ollama run gemma3:12bFirst time? Install Ollama, then paste that into a terminal. Is this your machine? Check it on the homepage.
Every model the Radeon 780M 16 GB can run
3 of 12 fit. Best pick: Gemma 3 12B.
- Qwen3 4BQuick everyday chat and summaries~20 tok/sUsable
qwen3:4b - Qwen3 8BA solid all-rounder for chat and writing~10 tok/sSlow
qwen3:8b - Gemma 3 12BReads images as well as text~6 tok/sSlow
gemma3:12b - Qwen3 14BNoticeably smarter at reasoning and codeneeds 11 GBToo big
qwen3:14b - gpt-oss 20BOpenAI's open model. Fast, strong reasoningneeds 16 GBToo big
gpt-oss:20b - Gemma 3 27BGoogle's best open model for its sizeneeds 19 GBToo big
gemma3:27b - Qwen3 30B-A3B30B smarts at small-model speedneeds 21 GBToo big
qwen3:30b - Qwen3 32BStrong coding and long answersneeds 22 GBToo big
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
Every model the Radeon 780M 32 GB can run
6 of 12 fit. Best pick: Gemma 3 27B.
- Qwen3 4BQuick everyday chat and summaries~20 tok/sUsable
qwen3:4b - Qwen3 8BA solid all-rounder for chat and writing~10 tok/sSlow
qwen3:8b - Gemma 3 12BReads images as well as text~6 tok/sSlow
gemma3:12b - Qwen3 14BNoticeably smarter at reasoning and code~5 tok/sSlow
qwen3:14b - gpt-oss 20BOpenAI's open model. Fast, strong reasoning~16 tok/sUsable
gpt-oss:20b - Gemma 3 27BGoogle's best open model for its size~3 tok/sSlow
gemma3:27b - Qwen3 30B-A3B30B smarts at small-model speedneeds 21 GBToo big
qwen3:30b - Qwen3 32BStrong coding and long answersneeds 22 GBToo big
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 Radeon 780M run it?
Can the Radeon 780M run gpt-oss 20B?
Yes, with 32 GB or more. gpt-oss 20B needs about 16 GB and the Radeon 780M with 32 GB of system memory leaves about 19 GB for models. Expect about 16 tok/s, about reading speed. The 16 GB version doesn't have room.
Can the Radeon 780M run Gemma 3 27B?
Yes, with 32 GB or more. Gemma 3 27B needs about 19 GB and the Radeon 780M with 32 GB of system memory leaves about 19 GB for models. Expect about 3 tok/s, slow, but it works. The 16 GB version doesn't have room.
Can the Radeon 780M run Qwen3 30B-A3B?
No. Qwen3 30B-A3B needs about 21 GB and the Radeon 780M has at most 32 GB of system memory, of which about 19 GB is usable for models. The most capable model it fits is Gemma 3 27B, at about 3 tok/s.
Real runs on the Radeon 780M
Loading measured runs…
Generating a token reads the model's active weights from memory once, so speed is roughly memory bandwidth (90 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. Built-in graphics share system memory, so we count about 60% of it. The easiest start is a small model in your browser in the Studio. Real results are usually within about a third. Measured runs are on the leaderboard.
The Used desktop + RTX 3060 12 GB runs Qwen3 14B at about 21 tok/s, from $600 used.