llamaperf

TensorSharp benchmarks

An inference engine for running open-weight LLMs locally.

17 community reports

TensorSharp results by GPU

Hardware with reported TensorSharp results, with each report's model, quant and speed, newest first. Runs on several cards, with speculative decoding, with batched requests or with part of the model in system RAM say so, since each describes a different setup. Prompt processing is how fast the input is read, not how long you wait for the first word. How to measure time to first token.

This engine doesn't yet have an editorial profile on llamaperf. The community reports below show how it's been used in practice across different hardware.

Compare GPUs running TensorSharp

Every card is compared on one model, Qwen3.8 27B at 4-bit, the size and bit class that most cards here have plain runs of. A card with no run of that model shows none rather than a figure from a different model.

GPUVRAMReportsMedian speed, Qwen3.8 27B 4-bit
NVIDIA A40 48GBnvidia48GB8no Qwen3.8 27B 4-bit run reported
M5 Pro 48GBapple48GB3no Qwen3.8 27B 4-bit run reported
NVIDIA RTX 5090nvidia32GB2Gen 80.0 t/s
NVIDIA A100 80GBnvidia80GB1no Qwen3.8 27B 4-bit run reported
NVIDIA RTX 2000 Adanvidia16GB1no Qwen3.8 27B 4-bit run reported
NVIDIA RTX 3080 Laptop 16GBnvidia16GB1no Qwen3.8 27B 4-bit run reported
NVIDIA RTX Pro 6000 Blackwellnvidia96GB1no Qwen3.8 27B 4-bit run reported

TensorSharp against other engines

Pairs of plain runs on the same card, of the same model size at the same bit class: one device, one request, no speculative decoding, the whole model in memory. Context length and build still differ between the two sides, and each side shows its own.

Model and GPUTensorSharpOther engine
Qwen3.8 27B 4-bitNVIDIA RTX 509080.0 t/sone generation report, 40K contextllama.cpp84.2 t/smedian of 3 generation reports, 40K to 120K context, 1 not stated
Qwen3.8 27B 4-bitNVIDIA RTX 509080.0 t/sone generation report, 40K contextvLLM73.2 t/sone generation report, context not stated

Top models on TensorSharp

Frequently asked

Is TensorSharp faster than other engines?

llamaperf has 2 matched pairs of TensorSharp and other-engine runs on the same card, model size and bit class, but none is comparable enough to say which engine is faster: the sides have too few reports or were run at different context lengths. A pair counts toward a direction only when each side has at least 3 generation reports with a stated context, and the two sides' contexts overlap. The measured figures and their conditions are in the table on this page.