Hugging Face's logo
Cahlen Humphreys's picture
💼 Hiring

Cahlen Humphreys PRO

cahlen
4 85 255
jmfi's profile picture webxos's profile picture 9tryV's profile picture
·
https://bigcompute.science

AI & ML interests

☠️💻

Recent Activity

posted an update 2 days ago
I published the serving setup and benchmark results I’ve been using for GLM-5.3-Flash UD-IQ1_S on a single NVIDIA DGX Spark. The biggest finding was not throughput — it was reliability. With llama.cpp’s default unrestricted reasoning, a real ~18K-token OpenCode request with 53 tools failed to produce any actionable output in 9/20 runs. Adding: --reasoning-budget 2048 changed that to 20/20 successful tool-call responses. A few other measured results: * 27.5–29 tok/s decode with MTP vs 18.7 without * MTP depth 2 outperformed the default depth 3 * 131K context uses ~90.9 GiB resident memory * 256K context also works on the Spark * CPU MoE offload does not meaningfully free memory on GB10 unified memory * newer llama.cpp builds were slightly faster, but introduced tool-call serialization failures, so the repo pins the stable commit Everything in the README is backed by the benchmark scripts and raw results in the repo. If you're running GLM-5.3-Flash on a DGX Spark for agentic coding, this should give you a solid starting point. https://github.com/cahlen/glm-5.3-flash-GGUF-1bit-dgx-spark https://huggingface.co/unsloth/GLM-5.3-Flash-GGUF
liked a model 6 days ago
unsloth/Qwen3.8-Flash-Next-GGUF
liked a model 6 days ago
zai-org/GLM-5.3
View all activity

Organizations

Enfuse.io's profile picture