BeeLlama

mentions 2 type Organization feed RSS

// recent coverage 2 mentions

03:39

2026-05-23

dev.to

large-language-models

BeeLlama v0.2.0: 164 tok/s on a 27B model, one RTX 3090

BeeLlama v0.2.0 demonstrates that speculative decoding can achieve a 4.4x to 4.93x throughput multiplier on a single RTX 3090, running 27B and 31B parameter models at 37-36 tokens per second baseline …

21:35

2026-05-22

dev.to

large-language-models

RTX 5090 Cooling, BeeLlama VRAM Opts, Resizable BAR Performance Gains

The article covers two main topics: NVIDIA's upcoming RTX 5090 cooling solutions, with AORUS claiming a maximum GPU temperature of 77°C under load, and the release of BeeLlama v0.2.0, which achieves s…

// co-occurs with top 8 entities

Qwen 2 Gemma 2 RTX 3090 2 llama.cpp 1 Hugging Face 1 Ryzen 7 5700X3D 1 Apache 2.0 1 NVIDIA 1