RTX 4060 Ti 16GB for local LLMs

4 measured results from 3 builds, each linked to its source.

Can it run? LFM2.5 24B-A2B on RTX 4060 Ti 16GB Qwen3.8 27B on RTX 4060 Ti 16GB

All builds with the RTX 4060 Ti 16GB

All measured results

Hide speculative-decoding results ⚡ (MTP, DFlash, DSpark and similar draft-and-verify methods give much higher tok/s on predictable text and are not comparable 1:1 with plain decode)

All RTX 4060 Ti 16GB builds: see also all GPUs · best LLMs by memory size · download the dataset.

FAQ

How fast is the RTX 4060 Ti 16GB for local LLMs?

The fastest plain-decode result we have is 131-150 tok/s on LFM2.5 24B-A2B (llama-bench tg128 (quant per result), llama.cpp) in RTX 4060 Ti 16GB: 2026 models (llamabench community). Speed depends heavily on the model, quant and engine, so compare like with like in the table. RigBase lists 4 measured results from 3 builds.

How much memory does the RTX 4060 Ti 16GB have?

16 GB per card. Memory bandwidth: 288 GB/s (memory bandwidth as listed on llamabench).

Which models have been measured on the RTX 4060 Ti 16GB?

LFM2.5 24B-A2B, Llama 3.3 70B, Qwen3.8 27B.

Where do these numbers come from?

Every row links to a build page with its original public source (benchmark logs, READMEs, forum posts). RigBase does not re-run the benchmarks. Results marked ⚡ use speculative decoding and are not comparable 1:1 with plain decode.