GLM-5.3-Flash @ DGX Station GB300: ~206 tok/s (single stream), 1M context
Summary
The user benchmarks the GLM-5.3-Flash AI model on a DGX Station, achieving ~206 tokens per second in single-stream inference with a 1 million context window, and shares a Docker command for setup.
Similar Articles
@TechMDAI: GLM-5.3-Flash EXL3-3.0bpw by @0xSero @BrandonMusicKy @LottoLabs @localmaxxing 193.8 tk/s
The article highlights the GLM-5.3-Flash EXL3-3.0bpw AI model with an inference speed of 193.8 tokens per second, attributed to multiple contributors.
@MiaAI_lab: GLM 5.3 Flash on 2x DGX Sparks Look at the tok/s at the top :) This is prose. Releasing soon
GLM 5.3 Flash is an upcoming AI model that showcases high token-per-second performance on 2x DGX Spark systems, with an imminent release.
My GLM-5.2-FP8 HGX-H200 SGLang docker deploy config
A user shares their Docker deployment configuration for running the GLM-5.2-FP8 model on HGX-H200 hardware using SGLang, achieving 262k context and 70 tokens/s.
@no_stp_on_snek: Same two GB10s. GLM-5.3-Flash, two stacks. One streamed call each, temperature 0.2, 384 tokens, prompts around 3.7k tok…
A head-to-head benchmark of two community inference stacks running the 320B GLM-5.3-Flash on a pair of NVIDIA DGX Sparks, comparing Entrpi's EXL3 setup against TensorFold with DFlash2 drafters across prose, code, and prefill workloads.
@0xSero: GLM-5.1-478B-NVFP4 Running on: - 4x RTX Pro 6000 - Sglang - 370,000 max tokens (1.75x full context) - p10 27.7 | p90 45…
A quantized 478B-parameter GLM-5.1 model runs on 4×RTX Pro 6000 GPUs via SGLang, delivering 370k-token context at up to 45 tok/s decode and 1340 tok/s prefill, and is demoed driving Figma.