Which LLMs can your hardware run?
Verified specs for GPUs, Macs and mini PCs, memory needs for every popular open model, and estimated speed: all in one place, with sources.
Quick check
✓ Runs: best at FP16, needs 17.6 GiB, about 43 tokens/s
| Quantization | Weights | KV | Total | Usable | Result | tok/s (est.) |
|---|---|---|---|---|---|---|
| Q4_K_M | 4.6 | 1.1 | 6.5 GiB | 24.0 GiB | Fits | 142 |
| Q5_K_M | 5.4 | 1.1 | 7.3 GiB | 24.0 GiB | Fits | 121 |
| Q6_K | 6.3 | 1.1 | 8.2 GiB | 24.0 GiB | Fits | 105 |
| Q8_0 | 8.1 | 1.1 | 10.1 GiB | 24.0 GiB | Fits | 81 |
| FP16 | 15.3 | 1.1 | 17.6 GiB | 24.0 GiB | Fits | 43 |
Estimates, not benchmarks. How we estimate · DeepSeek-R1-0528-Qwen3-8B · GeForce RTX 4090
Popular hardware
- GeForce RTX 509032 GB · 1792 GB/s
- GeForce RTX 309024 GB · 936 GB/s
- GeForce RTX 409024 GB · 1008 GB/s
- Radeon RX 7900 XTX24 GB · 960 GB/s
- Radeon RX 7900 XT20 GB · 800 GB/s
- GeForce RTX 4060 Ti 16GB16 GB · 288 GB/s
Popular models
- Qwen3.8-27BQ4 · 17.0 GiB
- Qwen3.8-Flash-NextQ4 · 107.4 GiB
- Gemma 4 12B Unified ITQ4 · 8.0 GiB
- Qwen3.6-27BQ4 · 17.0 GiB
- Qwen3.6-35B-A3BQ4 · 21.4 GiB
- DeepSeek-V4-FlashQ4 · 168.9 GiB
- Kimi K2.6Q4 · 593.9 GiB
- Qwen3.5-9BQ4 · 6.1 GiB