Original benchmark dataset
Local LLM benchmarks
Tokens-per-second measurements collected on owner hardware and from cited community sources. Every row ships with a confidence badge so you know which numbers to trust for purchasing decisions.
Latest 3 runs
Sorted by date. Click a model or hardware name to drill into the full record.
| Model | Hardware | Conf. | Quant | Ctx | Tokens / sec | VRAM | TTFT | Date |
|---|---|---|---|---|---|---|---|---|
| Mixtral 8x7B Instruct | NVIDIA GeForce RTX 4090(Ollama) | M | Q4_K_M | 8K | 31.4tok/s | 23.1 GB | 248 ms | Apr 23, 26 |
| Llama 3.1 8B Instruct | NVIDIA GeForce RTX 4090(Ollama) | M | Q4_K_M | 8K | 104.7tok/s | 5.4 GB | 78 ms | Apr 22, 26 |
| Mistral 7B Instruct v0.3 | NVIDIA GeForce RTX 4090(Ollama) | M | Q4_K_M | 4K | 112.3tok/s | 5.1 GB | 64 ms | Apr 22, 26 |