Running Gemma 4 26B at 5 tokens/sec on a 13-year-old Xeon with no GPU (neomindlabs.com) | HN Screenshots

YHacker Newsscreenshots

Screenshot of neomindlabs.com: Running Gemma 4 26B at 5 tokens/sec on a 13-year-old Xeon with no GPU

First screen, captured 3 months ago.

Looks similar

Screenshot of blog.mattstuchlik.com: Summing ASCII encoded integers on Haswell at almost the speed of memcpy

Summing ASCII encoded integers on Haswell at almost the speed of memcpy (blog.mattstuchlik.com)

114 points by iliekcomputers 2 years ago | 34 comments

Screenshot of quesma.com: Benchmarking Qwen3.8 27B quantizations: 4-bit holds up, 1-bit collapses

Benchmarking Qwen3.8 27B quantizations: 4-bit holds up, 1-bit collapses (quesma.com)

271 points by stared 1 month ago | 128 comments

Screenshot of baseten.co: Running GPT-OSS-120B at 500 tokens per second on Nvidia GPUs

Running GPT-OSS-120B at 500 tokens per second on Nvidia GPUs (baseten.co)

215 points by philipkiely 1 year ago | 142 comments

Screenshot of fergusfinn.com: Speculative KV coding: losslessly compressing KV cache by up to ~4×

Speculative KV coding: losslessly compressing KV cache by up to ~4×(fergusfinn.com)

137 points by kkm 4 months ago | 28 comments

Screenshot of blogs.nvidia.com: H100 GPUs Set Standard for Gen AI in Debut MLPerf Benchmark

H100 GPUs Set Standard for Gen AI in Debut MLPerf Benchmark (blogs.nvidia.com)

137 points by Anon84 3 years ago | 62 comments

Screenshot of blog.imaginationtech.com: Imagination GPUs now support OpenGL 4.6

Imagination GPUs now support OpenGL 4.6 (blog.imaginationtech.com)

102 points by mfilion 3 years ago | 72 comments