Thireus PRO

Thireus's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

New activity in msuiche/DeepSeek-V4.1-Flash-1017-abliterated-cyber-GLP-27-L11-37-a3.5 1 day ago

Where can I find weaponize32?

1

#1 opened 1 day ago by

Thireus

New activity in msuiche/DeepSeek-V4.1-Flash-1017-abliterated-cyber-GLP-39-L1-39-a0.75 1 day ago

hi, does this only work on the base model?

2

#1 opened 18 days ago by

apple4red

New activity in deepseek-ai/DeepSeek-V4.1-Flash-1017 22 days ago

Did you know that you can run this model with 24 GB of VRAM and 64 GB of RAM?

🔥 7

18

#2 opened 26 days ago by

lucyferorg

I make a patch on Sglang v0.5.22 and successfully run the model on 4xPro6000

4

#20 opened 23 days ago by

Scott309

New activity in 0xSero/glm-5.3-reap-fidelity-study 26 days ago

Quantization × Pruning: Mapping the Sweet Spot for Model Fidelity

1

#1 opened 26 days ago by

Thireus

New activity in ubergarm/Kimi-K2.6-GGUF 5 months ago

Kimi 2.7 GGUF?

❤️ 3

7

#14 opened 5 months ago by

ChuckMcSneed

New activity in ubergarm/GLM-4.7-Flash-GGUF 5 months ago

Ultra-low PPL for recipes between 3.6bpw and 4.6bpw - not limited to MXFP4

👍 1

#7 opened 5 months ago by

Thireus

New activity in ubergarm/Kimi-K2.6-GGUF 6 months ago

MTP Support

👍 2

9

#13 opened 6 months ago by

anikifoss

New activity in ubergarm/Qwen3.5-397B-A17B-GGUF 7 months ago

Check out Thireus GGUF-Tool-Suite quants!

❤️🤗 5

8

#13 opened 7 months ago by

ubergarm

New activity in Gammaception/Qwen3.5-27B-Thireus-16gb-optimized-GGUF 7 months ago

Seeing GGUF-Tool-Suite Outputs in the Wild — Thank You!

👍 2

#1 opened 7 months ago by

Thireus

New activity in ubergarm/Qwen3.5-35B-A3B-GGUF 8 months ago

Testing Q4_0

🔥 1

2

#2 opened 9 months ago by

shewin

New activity in ubergarm/Qwen3.5-122B-A10B-GGUF 8 months ago

Found block with mismatching importance/model weights

1

#11 opened 8 months ago by

Thireus

New activity in ubergarm/Kimi-K2-Thinking-GGUF about 1 year ago

Imatrix from BF16 ?

👀 1

2

#6 opened about 1 year ago by

bobchenyx

New activity in ubergarm/GLM-4.6-GGUF about 1 year ago

Should ffn_down experts be quantized the same as ffn_up/ffn_gate?

5

#2 opened about 1 year ago by

Downtown-Case

New activity in ubergarm/GLM-4.5-GGUF about 1 year ago

Any chance for an IQ3_K?

👍 2

34

#6 opened over 1 year ago by

original-el8

New activity in yairpatch/Qwen3-VL-30B-A3B-Thinking-GGUF about 1 year ago

llama.cpp/tools/mtmd/mtmd.cpp - Missing PROJECTOR_TYPE_QWEN3VL

1

#1 opened about 1 year ago by

Thireus

New activity in ubergarm/DeepSeek-V3.1-Terminus-GGUF about 1 year ago

imatrix coming soon? 🫣

🤝 1

8

#1 opened about 1 year ago by

Thireus

New activity in ubergarm/Kimi-K2-Instruct-0905-GGUF about 1 year ago

IQ2_KS

79

#1 opened about 1 year ago by

gghfez

New activity in ubergarm/DeepSeek-V3.1-GGUF about 1 year ago

quant req: 256 GB RAM + 96 GB VRAM

👍 1

28

#1 opened about 1 year ago by

whoisjeremylam

New activity in ubergarm/GLM-4.5-Air-GGUF about 1 year ago

Good job

56

#2 opened over 1 year ago by

huccjj