In a Training Loop 🔄

50 32 349

Markus PRO

marksverdhei

marksverdhei

AI & ML interests

NLP

Recent Activity

liked a model about 4 hours ago

marksverdhei/Qwen3-Omni-30B-A3B-FP8

published a model about 4 hours ago

marksverdhei/Qwen3-Omni-30B-A3B-FP8

updated a model about 5 hours ago

marksverdhei/Qwen3-Omni-30B-A3B-FP8

View all activity

Organizations

liked a model about 4 hours ago

marksverdhei/Qwen3-Omni-30B-A3B-FP8

Any-to-Any • 35B • Updated about 5 hours ago • 1

published a model about 4 hours ago

marksverdhei/Qwen3-Omni-30B-A3B-FP8

Any-to-Any • 35B • Updated about 5 hours ago • 1

updated a model about 5 hours ago

marksverdhei/Qwen3-Omni-30B-A3B-FP8

Any-to-Any • 35B • Updated about 5 hours ago • 1

updated a collection about 6 hours ago

FP8 quants

Collection

A collection of my FP8 quants for models missing this. • 2 items • Updated about 6 hours ago • 1

reacted to danielhanchen's post with 🔥🔥 about 7 hours ago

Post

581

Run GLM-4.7-Flash locally on your device with 24GB RAM!🔥

It's the best performing 30B model on SWE-Bench and GPQA. With 200K context, it excels at coding, agents, chat & reasoning.

GGUF: unsloth/GLM-4.7-Flash-GGUF

Guide: https://unsloth.ai/docs/models/glm-4.7-flash

New activity in marksverdhei/GLM-4.7-Flash-FP8 about 7 hours ago

mtp support?

#4 opened about 15 hours ago by

CHNtentes

upvoted 2 changelogs about 8 hours ago

Changelog

Set your primary organization on your profile

Dec 19, 2025

• 103

Changelog

HuggingChat for Papers

13 days ago

• 93

updated a model about 8 hours ago

marksverdhei/GLM-4.7-Flash-FP8

Text Generation • Updated about 8 hours ago • 785 • 10

New activity in marksverdhei/wordnet-definitions-en-2021 about 8 hours ago

[bot] Conversion to Parquet

#2 opened 8 months ago by

parquet-converter

liked a model about 8 hours ago

bartowski/zai-org_GLM-4.7-Flash-GGUF

Text Generation • 30B • Updated about 14 hours ago • 1.98k • 12

updated a collection about 8 hours ago

FP8 quants

Collection

A collection of my FP8 quants for models missing this. • 2 items • Updated about 6 hours ago • 1

upvoted a collection about 8 hours ago

FP8 quants

Collection

A collection of my FP8 quants for models missing this. • 2 items • Updated about 6 hours ago • 1

updated a collection about 8 hours ago

FP8 quants

Collection

A collection of my FP8 quants for models missing this. • 2 items • Updated about 6 hours ago • 1

New activity in marksverdhei/GLM-4.7-Flash-FP8 about 8 hours ago

If 8bit, why shaped like 16 bit

#2 opened about 21 hours ago by

zenmagnets

posted an update about 8 hours ago

Post

386

Inspired by the heroes of day zero quants ( @TheBloke @danielhanchen @shimmyshimmer @bartowski ), I decided to join the race by releasing the first FP8 quant of glm-4.7-flash! Not as easy as i expected, but I'm happy i was still able to have it working within a few hours after the original model was released! Interested in feedback if anyone wants to try it out!

marksverdhei/GLM-4.7-Flash-FP8

Note: If my PR to vLLM isn't merged yet you might have to use my fork. Cheers! 🤗