Joakim Palm

Joakimpalm-Zen

·

https://xyntetik.com/

AI & ML interests

Building Xyntetik Runner, a local inference engine, and using it as a research platform for quantization, LoRA on GGUF weights, model surgery and reproducible inference. This profile is the evidence trail: runnable releases, compatibility reports, experiments and failures. If you just want something to run, start with the Runner Releases collection.

Recent Activity

updated a model about 2 hours ago

Joakimpalm-Zen/Cloudflare-clef-IQ3_S-recovered-GGUF

updated a dataset about 3 hours ago

Joakimpalm-Zen/Xyntetik-Genesis-Language-record

updated a dataset about 18 hours ago

Joakimpalm-Zen/Xyntetik-Genesis-Existence-record

View all activity

Organizations

New activity in meta-models/Muse-Glimmer-30B about 1 month ago

Render a bare tool name as an exact recipient, not a namespace pattern

#60 opened 2 months ago by

An autopsy of a «king.» I read Muse-Glimmer-30B’s config so you don’t have to.

#57 opened 2 months ago by

WE REALLY NEED 9B-12B OR 35B A3B MOE🔥🔥🔥

#15 opened 3 months ago by

Correct Samplers Order?

#64 opened about 1 month ago by

Training LoRAs on Muse-Glimmer for llama.cpp: 5 things that cost us a week (label format, reasoning_strength, peg-native 500s, convert_lora_to_gguf crash, recipe)

#63 opened about 2 months ago by

Distilling Muse Glimmer to 14B, looking for the right contact for a small compute extension

#66 opened about 1 month ago by

New activity in Joakimpalm-Zen/Qwen3.8-27B-GSQ-RCO-IQ3_S-recovered-GGUF about 1 month ago

Hi guy

#1 opened about 1 month ago by

New activity in meta-models/Muse-Glimmer-30B-GGUF 3 months ago

Muse Glimmer 30B now runs on Xyntetik Runner, if you need an option to Llama/ollama for built-in schema support.

#4 opened 3 months ago by