Thireus's picture

Thireus PRO

Thireus

·

https://gguf.thireus.com/

AI & ML interests

None yet

Recent Activity

updated a model about 3 hours ago

Thireus/Kimi-K2-Instruct-0905-THIREUS-Q8_0-SPECIAL_SPLIT

new activity about 7 hours ago

ubergarm/Kimi-K2-Instruct-0905-GGUF:IQ2_KS

updated a collection about 8 hours ago

Kimi-K2-Instruct-0905-THIREUS-SPECIAL_SPLIT

View all activity

Organizations

None yet

New activity in ubergarm/Kimi-K2-Instruct-0905-GGUF about 7 hours ago

IQ2_KS

#1 opened about 22 hours ago by

New activity in ubergarm/DeepSeek-V3.1-GGUF 14 days ago

quant req: 256 GB RAM + 96 GB VRAM

#1 opened 16 days ago by

New activity in ubergarm/GLM-4.5-Air-GGUF 24 days ago

Good job

#2 opened about 1 month ago by

New activity in Thireus/Qwen3-Coder-480B-A35B-Instruct-THIREUS-IQ3_K-SPECIAL_SPLIT 25 days ago

Not working as expected?

#1 opened 27 days ago by

New activity in Thireus/DeepSeek-R1-0528-THIREUS-IQ1_KT-SPECIAL_SPLIT about 1 month ago

what is this ?

#1 opened about 1 month ago by

New activity in ubergarm/Qwen3-235B-A22B-Instruct-2507-GGUF about 1 month ago

qwen3 2507 test

#6 opened about 2 months ago by

New activity in ubergarm/Qwen3-235B-A22B-Instruct-2507-GGUF about 2 months ago

imatrix-eaddario-combined-all-medium-Qwen3-235B-A22B-Instruct-2507-BF16.dat ?

#7 opened about 2 months ago by

New activity in mlx-community/DeepSeek-R1-0528-4bit 2 months ago

Is there a chance to get the AWQ or DWQ model? Mac Studio (512GB) has a 3-bit honey point.

#1 opened 3 months ago by

New activity in ubergarm/DeepSeek-R1-0528-GGUF 3 months ago

DeepSeek-R1-256x21B-0528-BF16 GGUF?

#12 opened 3 months ago by

New activity in Qwen/Qwen3-Embedding-0.6B 3 months ago

ONNX version planned?

#17 opened 3 months ago by

New activity in anikifoss/DeepSeek-R1-0528-DQ4_K_R4 3 months ago

Metrics for 110k context size?

#4 opened 3 months ago by

New activity in ubergarm/DeepSeek-R1-0528-GGUF 3 months ago

Scripts to produce PPL and KLD diagrams?

#10 opened 3 months ago by

New activity in anikifoss/DeepSeek-R1-0528-DQ4_K_R4 3 months ago

DeepSeek-R1-0528-DQ2_K_R4

#3 opened 3 months ago by

New activity in kalomaze/Qwen3-16B-A3B 3 months ago

DeepSeek R1 0528?

#15 opened 3 months ago by

This model almost completely loses Chinese ablities

#14 opened 4 months ago by

New activity in unsloth/Qwen3-32B-GGUF 4 months ago

Potentially still broken?

#8 opened 4 months ago by

New activity in kalomaze/Qwen3-16B-A3B 4 months ago

Brainstorming

#6 opened 4 months ago by

New activity in unsloth/Qwen3-32B-128K-GGUF 4 months ago

UD version not doing great with YaRN compared to non-UD of the same size

#4 opened 4 months ago by

New activity in unsloth/Qwen3-32B-GGUF 4 months ago

PPL vs model size - safe to assume larger size == better accuracy regardless of UD vs non-UD?

#6 opened 4 months ago by

New activity in Qwen/Qwen3-32B 4 months ago

Potential issue with large context sizes - can someone confirm?

#18 opened 4 months ago by