What can you run on an 8GB graphics card?
With 8GB VRAM you can run 12 of the 51 open-source models we track — up to about 9.7B parameters at Q4 quantization. The most popular that fits is MiniCPM5-1B, needing 1.3 GB and generating around ~271 tok/s on typical hardware of this size.
Typical machines: RTX 4060 · RTX 3070 · RTX 3060 Ti · RX 7600. After the operating system takes its share, about 7.7 GB is free for a model.
Having the memory is not the same as having the speed
8GB VRAM decides whether a model loads. How fast it answers is decided by memory bandwidth — how quickly your machine can read the model, which it must do once for every word it writes. Machines with 8GB VRAM span 272–448 GB/s, so the fastest is about 1.6× quicker than the slowest with identical capacity. The table quotes a RTX 4060; pick yours below to see the difference. Why bandwidth and not the processor →
Models that run on 8GB VRAM in 2026
| Model↕ | Size↕ | Memory↑ | Est. speed↕ | Downloads↕ | Feels like |
|---|---|---|---|---|---|
| LFM2.5-230MLiquid Ai | 230M | 808 MBRuns well | ~1152 tok/s | 58,011 | Fast |
| MiniCPM5-1BOpenBMB | 1.1B | 1.3 GBRuns well | ~271 tok/s | 667,154 | Fast |
| MiniCPM5-2BOpenBMB | 2.5B | 2.3 GBRuns well | ~113 tok/s | 206,774 | Fast |
| LFM2.5-2.6BLiquid Ai | 2.7B | 2.5 GBRuns well | ~106 tok/s | 98,713 | Fast |
| LFM2.5-VL-3BLiquid Ai | 3.1B | 2.5 GBRuns well | ~106 tok/s | 31,296 | Fast |
| North-Micro-Vision-InstructCohere | 2.5B | 2.5 GBRuns well | ~118 tok/s | 120,354 | Fast |
| granite-4.2-3bIbm | 3.7B | 3.1 GBRuns well | ~79 tok/s | 32,017 | Fast |
| Mage-VLMicrosoft | 4.7B | 3.9 GBRuns well | ~65 tok/s | 29,690 | Fast |
| LFM2.5-8B-A1BLiquid Ai · MoE | 8.5B | 5.9 GBRuns well | ~290 tok/s1B active | 80,632 | Fast |
| Ling-3.0-tinyInclusionai · MoE | 7.9B | 6.2 GBRuns well | ~183 tok/s1.6B active | 25,727 | Fast |
| granite-4.2-8bIbm | 8.8B | 6.6 GBRuns well | ~33 tok/s | 52,946 | Fast |
| Ornith-1.5-9BDeepreinforce | 9.7B | 6.9 GBTight | ~31 tok/s | 453,339 | Fast |
Sorted by memory, smallest first — click any column to change it.
Step up to 12GB VRAM and 1 more model come within reach
Including gemma-4-12B-it (12B) — around ~45 tok/s on a typical machine that size.
See everything 12GB VRAM runs →All figures at Q4_K_M quantization, 4K context. “Memory” includes the model, its context cache and runtime overhead. Speed is calculated, not benchmarked: 272 GB/s × 0.65 ÷ bytes read per token, assuming a RTX 4060. Scale it by your own machine's bandwidth from the list above. Mixture-of-experts models read only their active parameters per token, which is why some large ones outrun smaller dense models.
What you'd need more memory for
The next models up, and what they ask for.