← Best models

Best model for a 12 GB graphics card

Ranked models that need at most 12 GB, best Overall score first, then the fastest of those within 10 points of the best one that fits. The memory a model needs is an estimate: the model file size plus about 20% for the context of a single conversation.

What this page assumes. The page counts the card's whole 12 GB as available for a model. A card that also drives your screen or runs other programs has less. A model is listed when its estimated memory need is at most that budget. Most models here were run with a context window of 16,384 tokens, so a longer context needs more memory than shown.

Speeds are not for this machine. Every speed on this page is tokens per second measured on the benchmark's own laptop, an AMD Ryzen AI Max+ 395 with 128 GB of unified memory. That is not a 12 GB graphics card, so only the memory figures carry over; its speed will differ.

The best model that fits scores 98.6, so the fastest list covers Overall 88.6 to 98.6. 20 models are inside it.

164 of 227 ranked models fit. 5 ranked models have no file size on record, so their memory need cannot be estimated and they are not listed.

Read the memory figure as an estimate, not a guarantee. The memory a model needs is estimated from its file: the weights plus about 20% for the context of a single conversation. It is not a measurement, and a long conversation or several at once needs more. A model with no file size on record is not counted as fitting any amount of memory. Speeds, and the GPU memory shown on the speed page, were measured on this benchmark's server, not on yours. That server kept 1 to 8 answers in flight at a time and loaded a context window of 16,384 tokens for most models; 42 of the models ranked ran at a shorter context. Speeds were measured on one laptop and are comparable only between models on the same backend. See the settings and the memory method.

Up to 12 GB

Gemma 4 12B IT is the top-scoring ranked model that fits the 12 GB this page assumes: Overall 98.6 (95% interval 97.0–99.8), rank range 1–12, needing about 8.9 GB (file size plus 20%). It is not clearly ahead of Gemma4 E4B IT, the second: with this battery the two cannot be told apart with confidence.

Up to 12 GB: the top 5 of 164.
Place Model Overall Rank range Decode (tok/s) Memory needed (GB, est.) Size class
1 Gemma 4 12B IT 98.697.0–99.8 1–12 8.1ROCm 7.1 8.9 9–16B
2 Gemma4 E4B IT 95.593.0–97.7 2–51 13.2ROCm 7.1 7.9 4–9B
3 Qwen3-VL-8B-Instruct 94.992.4–97.1 4–48 9.4ROCm 7.1 7.4 4–9B
4 Gemma4 E2B IT 93.891.0–96.1 4–61 17.2ROCm 7.1 5.5 4–9B
5 gemma-3-12b-it 92.789.7–95.4 8–66 6.1ROCm 7.1 9.8 9–16B

Fastest of the good ones that fit

Qwen2.5-14B-Instruct is the fastest of the 20 models in the window: 21.7 tokens per second on our laptop (measured on ROCm 7.1; speeds on different backends are not directly comparable), with an Overall of 91.3 (95% interval 88.0–94.2), 7.3 points below the best model that fits, Gemma 4 12B IT (98.6).

Fastest of the good ones that fit: the top 5 of 20.
Place Model Overall Rank range Decode (tok/s) Memory needed (GB, est.) Size class
1 Qwen2.5-14B-Instruct 91.388.0–94.2 11–72 21.7ROCm 7.1 10.8 9–16B
2 Qwen3-VL-4B-Instruct 89.986.4–93.1 12–76 17.3ROCm 7.1 4.0 4–9B
3 Gemma4 E2B IT 93.891.0–96.1 4–61 17.2ROCm 7.1 5.5 4–9B
4 Qwen3-4B-Instruct-2507 90.387.2–93.3 13–73 17.1ROCm 7.1 3.0 4–9B
5 Qwen3-4B 89.285.6–92.4 18–81 17.0ROCm 7.1 3.1 4–9B

A higher place is not always a clear win. When two models have overlapping rank ranges, this battery cannot tell them apart; see how sure a score is. A dash means not measured or not scored, which is different from 0. Speeds were measured on one laptop and are comparable only between models on the same backend.

More: all the best-model pages, the hardware picker, speed and memory for every model.