Average speeds at Q4 quantization. Actual performance varies by model architecture and context length.
3B
—
1.7GB needed
7B
—
3.9GB needed
14B
—
7.9GB needed
32B
—
18.0GB needed
70B
—
39.4GB needed
Measured rig reports
We rent the machine and time every model on it: decode, VRAM peak, concurrency, watts and cost per million tokens. Yours may already be one of them — and two are free to read in full.
Neighbours in memory rather than in price: memory decides whether a card can do the job at all, so two cards of the same size at different prices is the comparison you are making. Ordered by memory, then bandwidth — not by the value column, which is worked out from bandwidth and price alone and therefore rewards a cheap card whatever its software stack does to that bandwidth in practice. Read it as one input, not as a ranking.
Device under test
NVIDIA GeForce GTX 285 — 1 GB VRAM.
GeForce GTX 285 spec
Brand
NVIDIA
VRAM
1 GB GDDR3
Bandwidth
159 GB/s
FP16 Compute
0.7 TFLOPS
FP32 Compute
0.7 TFLOPS
CUDA Cores
240
TDP
204 W
Architecture
Tesla 2.0
AI capability
4/ 498 models @ Q4
With 1 GB VRAM and 159 GB/s bandwidth, this GPU handles models up to 0.14B parameters.
Speed ≈ bandwidth / model_size × efficiency. A 7B model at Q4 runs at ~18 tok/s.