0
Quantized builds
30
Benchmark records
Quantized builds
Community and official quantized releases; "linked records" counts only benchmarks tied to that exact release.
No quantized builds cataloged yet.
Benchmark data
30 configurations
| Hardware | Framework | Quant | Decode | VRAM used | Samples | Evidence |
|---|---|---|---|---|---|---|
| NVIDIA RTX 4090 | Ollama | Q3_K_S | 142.1 tok/s | 13.02 GB | 1 | L2 Cross-framework verified |
| NVIDIA RTX 4090 | Strata | IQ2_M | 230.9 tok/s | 10.84 GB | 1 | L2 Cross-framework verified |
| NVIDIA RTX 3090 | vLLM | Q4_K_S | 94.2 tok/s | 15.2 GB | 1 | L2 Cross-framework verified |
| NVIDIA RTX 3090 | Strata | Q3_K_S | 133.3 tok/s | 13.02 GB | 1 | L2 Cross-framework verified |
| AMD Radeon RX 7900 XTX | vLLM | Q5_K_M | 70.4 tok/s | 17.72 GB | 1 | L2 Cross-framework verified |
| AMD Radeon RX 7900 XTX | Ollama | IQ3_S | 86.7 tok/s | 13.19 GB | 1 | L2 Cross-framework verified |
| NVIDIA RTX 5090 | llama.cpp | IQ1_S | 381.9 tok/s | 9.16 GB | 1 | L2 Cross-framework verified |
| NVIDIA RTX 5090 | vLLM | Q3_K_S | 337.4 tok/s | 13.02 GB | 1 | L2 Cross-framework verified |
| NVIDIA RTX 5080 | llama.cpp | Q4_K_S | 176.1 tok/s | 15.2 GB | 1 | L2 Cross-framework verified |
| NVIDIA RTX 4080 Super | vLLM | IQ3_XS | 194.2 tok/s | 12.52 GB | 1 | L2 Cross-framework verified |
| NVIDIA RTX 4080 Super | Ollama | Q3_K_S | 155.2 tok/s | 13.02 GB | 1 | L2 Cross-framework verified |
| AMD Ryzen AI Max+ 395 | llama.cpp | Q2_K | 42.1 tok/s | 11.34 GB | 1 | L2 Cross-framework verified |
| AMD Ryzen AI Max+ 395 | Ollama | Q3_K_L | 32.5 tok/s | 14.2 GB | 1 | L2 Cross-framework verified |
| Apple M5 Max | llama.cpp | IQ4_XS | 75.7 tok/s | 14.53 GB | 1 | L2 Cross-framework verified |
| Apple M5 Max | Ollama | IQ4_XS | 67.2 tok/s | 14.53 GB | 1 | L2 Cross-framework verified |
| Apple M5 Ultra | llama.cpp | Q5_K_M | 84.6 tok/s | 17.72 GB | 1 | L2 Cross-framework verified |
| Apple M5 Ultra | Ollama | Q3_K_S | 125.1 tok/s | 13.02 GB | 1 | L2 Cross-framework verified |
| NVIDIA H100 80GB HBM3 | llama.cpp | Q8_0 | 271.7 tok/s | 21.42 GB | 1 | L2 Cross-framework verified |
| NVIDIA H100 80GB HBM3 | vLLM | Q3_K_M | 321.7 tok/s | 13.52 GB | 1 | L2 Cross-framework verified |
| NVIDIA H20 | vLLM | Q5_K_S | 49.6 tok/s | 17.22 GB | 1 | L2 Cross-framework verified |
| NVIDIA H20 | Strata | Q4_K_M | 73.5 tok/s | 15.88 GB | 1 | L2 Cross-framework verified |
| NVIDIA RTX PRO 6000 Blackwell 96GB | vLLM | Q2_K | 326.5 tok/s | 11.34 GB | 1 | L2 Cross-framework verified |
| NVIDIA RTX PRO 6000 Blackwell 96GB | Strata | Q5_K_M | 252.2 tok/s | 17.72 GB | 1 | L2 Cross-framework verified |
| Intel Arc B580 | Ollama | Q2_K | 60.7 tok/s | 11.34 GB | 1 | L2 Cross-framework verified |
| Apple M2 Ultra | llama.cpp | Q3_K_M | 119.5 tok/s | 13.52 GB | 1 | L2 Cross-framework verified |
| Apple M2 Ultra | Ollama | IQ3_S | 108.3 tok/s | 13.19 GB | 1 | L2 Cross-framework verified |
| NVIDIA RTX Spark | llama.cpp | IQ3_XS | 72.8 tok/s | 12.52 GB | 1 | L2 Cross-framework verified |
| NVIDIA RTX Spark | Ollama | IQ3_XS | 66.4 tok/s | 12.52 GB | 1 | L2 Cross-framework verified |
| NVIDIA RTX 5070 | Strata | IQ4_XS | 156.3 tok/s | 4.8 GB | 1 | L0 Self-reported |
| NVIDIA RTX 3060 12GB | llama.cpp | Q4_K_M | 57.3 tok/s | 5.4 GB | 1 | L0 Self-reported |
30 of these records are not linked to a specific quantized build; the full set is on the search page.
Community discussion
No discussions yet — start the first one.
Start a discussion