phak

phakio's activity

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

New activity in GrEarl/Kimi-K3-GGUF-IQ1_S about 5 hours ago

Working Results + Quick Benchmark

❤️ 5

3

#1 opened about 14 hours ago by

pwdz

New activity in sokann/GLM-5.2-GGUF-2.244bpw 26 days ago

Pretty solid results with ik_llama and OpenCode!

🔥 1

11

#2 opened about 1 month ago by

phakio

New activity in antirez/deepseek-v4-gguf 27 days ago

Running with recently merged llama.cpp PR

👍 6

6

#16 opened 29 days ago by

ubergarm

New activity in unsloth/GLM-5.2-GGUF about 1 month ago

Issues with UD-Q2_K_XL quant

5

#9 opened about 1 month ago by

labhraighlep

New activity in icecubetr/GLM-5.2-REAM-GGUF about 1 month ago

Q2_K has endless thinking loop issue

2

#2 opened about 1 month ago by

phakio

New activity in ubergarm/Kimi-K2.6-GGUF about 1 month ago

really awesome speeds! running at 256k context.

🔥 1

6

#11 opened 3 months ago by

mtcl

New activity in unsloth/GLM-5.2-GGUF about 1 month ago

GLM-5.2 GGUF Benchmarks!

❤️🔥 14

26

#3 opened about 1 month ago by

danielhanchen

New activity in AesSedai/Kimi-K2.7-Code-GGUF about 1 month ago

Thanks for the quick quants! Reccomended mmproj?

2

#1 opened about 1 month ago by

phakio

New activity in ubergarm/Qwen3.5-397B-A17B-GGUF 2 months ago

Any plans for reviving this model with MTP support?

👍 1

3

#14 opened 2 months ago by

phakio

New activity in bartowski/Qwen_Qwen3.5-397B-A17B-GGUF 2 months ago

Thanks for the quantizations, can we get MTP Qwen 3.5 397B GGUF?

2

#5 opened 2 months ago by

tidjei43

New activity in teamblobfish/DeepSeek-V4-Flash-GGUF 2 months ago

Running good on full GPU offload (1x4090, 3x3090) (Multi-GPU Offload Crash Fix)

🔥 1

#2 opened 2 months ago by

phakio

New activity in cyberneurova/CyberNeurova-DeepSeek-V4-Flash-abliterated-GGUF 3 months ago

The model is working okay! (Temporary fix for stop token being ignored)

5

#1 opened 3 months ago by

phakio

New activity in ubergarm/Qwen3.6-27B-GGUF 3 months ago

How to use MTP in GGUF?

20

#2 opened 3 months ago by

Friedland

New activity in batiai/DeepSeek-V4-Flash-GGUF 3 months ago

Running great on my Intel QYFS and DDR5 only! (CUDA gives error)

2

#1 opened 3 months ago by

phakio

New activity in AesSedai/MiMo-V2.5-GGUF 3 months ago

Working good on 96GB VRAM + DDR5 Setup

❤️ 1

5

#2 opened 3 months ago by

phakio

New activity in ubergarm/Qwen3.6-27B-GGUF 3 months ago

Great model for single GPU use cases.

🔥 4

16

#1 opened 3 months ago by

phakio

New activity in mlx-community/LongCat-Next-4bit 4 months ago

A fun, quick little model!

#1 opened 4 months ago by

phakio

New activity in AesSedai/Kimi-K2.5-GGUF 4 months ago

Performance on Intel QYFS, 512GB DDR5 and 96GB VRAM

👍 1

6

#3 opened 6 months ago by

phakio

New activity in ubergarm/GLM-5-GGUF 4 months ago

IQ3_KS on EPYC 9355 + 1x RTX 5090

🔥 2

5

#5 opened 5 months ago by

sousekd

New activity in AesSedai/NVIDIA-Nemotron-3-Super-120B-A12B-GGUF 5 months ago

This model is a gem for agentic work flows.

👍 2

1

#1 opened 5 months ago by

phakio