Grouped by reported model identity. Exact weights, quantizations and software can differ. How results are reviewed
Documented results
24 selected tests| View ReportGeneric LLM | Llama-3.2-1B-Instruct | Token speed | — | 5,776.99 tok/sPrefill · mean · unknown | 172.28 tok/sGeneration · mean · unknown | GPU count unknownUnknown · 24 GB VRAM/GPUConfiguration
|
|---|---|---|---|---|---|---|
| View ReportGeneric LLM | Llama-3.2-1B-Instruct | Token speed | — | 3,787.39 tok/sPrefill · mean · unknown | 138.8 tok/sGeneration · mean · unknown | GPU count unknownUnknown · 16 GB VRAM/GPUConfiguration
|
| View ReportGeneric LLM | Llama-3.2-1B-Instruct | Token speed | — | 3,395.56 tok/sPrefill · mean · unknown | 138.01 tok/sGeneration · mean · unknown | GPU count unknownUnknown · 16 GB VRAM/GPUConfiguration
|
| View ReportGeneric LLM | Llama-3.2-1B-Instruct | Token speed | — | 3,885.2 tok/sPrefill · mean · unknown | 129.53 tok/sGeneration · mean · unknown | GPU count unknownUnknown · 16 GB VRAM/GPUConfiguration
|
| View ReportGeneric LLM | Llama-3.2-1B-Instruct | Token speed | — | 5,076.32 tok/sPrefill · mean · unknown | 16.43 tok/sGeneration · mean · unknown | GPU count unknownUnknown · 24 GB VRAM/GPUConfiguration
|
| View ReportLocalMaxxing | Llama-3.2-1B-Instruct | Token speed | — | — | 287.3 tok/sGeneration · median · per request | 1 × Ryzen AI Max+ 395Single GPU · Unified memory · 96 GB RAMConfiguration
|
| View ReportGeneric LLM | Llama-3.2-1B-Instruct | Relative performance | 1.53 x vs RTX 4500 BlackwellRelative performance per dollar · Whole system | — | — | 1 × R9700Single GPU · 32 GB VRAM/GPUConfiguration
|
| View ReportGeneric LLM | Llama-3.2-1B-Instruct | Token speed | — | 4,151.93 tok/sPrefill · mean · unknown | 128.38 tok/sGeneration · mean · unknown | GPU count unknownUnknown · 24 GB VRAM/GPUConfiguration
|
| View ReportGeneric LLM | Llama-3.2-1B-Instruct | Token speed | — | 2,585.45 tok/sPrefill · mean · unknown | 29.68 tok/sGeneration · mean · unknown | GPU count unknownUnknown · 16 GB VRAM/GPUConfiguration
|
| View ReportGeneric LLM | Llama-3.2-1B-Instruct | Token speed | — | 2,579.64 tok/sPrefill · mean · unknown | 29.62 tok/sGeneration · mean · unknown | GPU count unknownUnknown · 16 GB VRAM/GPUConfiguration
|
| View ReportGeneric LLM | Llama-3.2-1B-Instruct | Token speed | — | 2,563.97 tok/sPrefill · mean · unknown | 28.98 tok/sGeneration · mean · unknown | GPU count unknownUnknown · 16 GB VRAM/GPUConfiguration
|
| View ReportGeneric LLM | Llama-3.2-1B-Instruct | Token speed | — | 3,156.12 tok/sPrefill · mean · unknown | 4.47 tok/sGeneration · mean · unknown | GPU count unknownUnknown · 24 GB VRAM/GPUConfiguration
|
| View ReportLocalMaxxing | Llama-3.2-1B-Instruct | Token speed | 6,792 tok/sEstimated prefill rate · median · per request | — | — | 1 × Ryzen AI Max+ 395Single GPU · Unified memory · 96 GB RAMConfiguration
|
| View ReportGeneric LLM | Llama-3.2-1B-Instruct | Token speed | — | 5,156.03 tok/sPrefill · mean · unknown | 117.62 tok/sGeneration · mean · unknown | GPU count unknownUnknown · 24 GB VRAM/GPUConfiguration
|
| View ReportGeneric LLM | Llama-3.2-1B-Instruct | Token speed | — | 3,232.92 tok/sPrefill · mean · unknown | 52.23 tok/sGeneration · mean · unknown | GPU count unknownUnknown · 16 GB VRAM/GPUConfiguration
|
| View ReportGeneric LLM | Llama-3.2-1B-Instruct | Token speed | — | 3,233.2 tok/sPrefill · mean · unknown | 97.4 tok/sGeneration · mean · unknown | GPU count unknownUnknown · 16 GB VRAM/GPUConfiguration
|
| View ReportGeneric LLM | Llama-3.2-1B-Instruct | Token speed | — | 3,170.2 tok/sPrefill · mean · unknown | 91.64 tok/sGeneration · mean · unknown | GPU count unknownUnknown · 16 GB VRAM/GPUConfiguration
|
| View ReportGeneric LLM | Llama-3.2-1B-Instruct | Token speed | — | 4,230.02 tok/sPrefill · mean · unknown | 11.69 tok/sGeneration · mean · unknown | GPU count unknownUnknown · 24 GB VRAM/GPUConfiguration
|
| View ReportGeneric LLM | Llama-3.2-1B-Instruct | Token speed | — | 5,170.98 tok/sPrefill · mean · unknown | 110.94 tok/sGeneration · mean · unknown | GPU count unknownUnknown · 24 GB VRAM/GPUConfiguration
|
| View ReportGeneric LLM | Llama-3.2-1B-Instruct | Token speed | — | 3,261.39 tok/sPrefill · mean · unknown | 92.77 tok/sGeneration · mean · unknown | GPU count unknownUnknown · 16 GB VRAM/GPUConfiguration
|
| View ReportGeneric LLM | Llama-3.2-1B-Instruct | Token speed | — | 3,244.61 tok/sPrefill · mean · unknown | 92.26 tok/sGeneration · mean · unknown | GPU count unknownUnknown · 16 GB VRAM/GPUConfiguration
|
| View ReportGeneric LLM | Llama-3.2-1B-Instruct | Token speed | — | 3,241.58 tok/sPrefill · mean · unknown | 87.81 tok/sGeneration · mean · unknown | GPU count unknownUnknown · 16 GB VRAM/GPUConfiguration
|
| View ReportGeneric LLM | Llama-3.2-1B-Instruct | Token speed | — | 4,226.87 tok/sPrefill · mean · unknown | 10.66 tok/sGeneration · mean · unknown | GPU count unknownUnknown · 24 GB VRAM/GPUConfiguration
|
| View ReportGeneric LLM | Llama-3.2-1B-Instruct | Token speed | — | 5,662.81 tok/sPrefill · mean · unknown | 144.36 tok/sGeneration · mean · unknown | GPU count unknownUnknown · 24 GB VRAM/GPUConfiguration
|
Quantizations and software
Quantizations: Q4_K_M, Q6_K, Q8_0
Engines: llamafile, Loculus Core
This is a selection across sources, not a ranking or a matched experiment. Reading benchmark reports
GPU benchmark pages: R9700 · RX 7900 XTX · RX 7800 XT · Ryzen AI Max+ 395