0xSero

0xSero's activity

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

New activity in 0xSero/GLM-5.3-Flash-EXL3-Q4 33 minutes ago

Independent KLD measurement of this Q4 on a sealed 25-window panel: 0.027263 nats (5 bitwise-identical runs)

2

#1 opened 10 days ago by

malaiwah

New activity in AtomicChat/Ling-3.0-flash-NVFP4 about 1 month ago

Amazing KLD how?

❤️ 1

1

#2 opened about 1 month ago by

0xSero

New activity in 0xSero/deepseek-v4-flash-0731-spark about 1 month ago

VLLM ?

5

#1 opened about 1 month ago by

TeAmErX

New activity in 0xSero/GLM-5.2-504B about 1 month ago

Slop

1

#4 opened about 1 month ago by

Defetya

New activity in brandonmusic/GLM-5.2-EXL3-TR3-3.0bpw about 1 month ago

Terminal-Bench-2.1 & Throughput on 4x RTX PRO 6000 (gen 4 system)

❤️ 1

1

#1 opened about 1 month ago by

0xSero

New activity in 0xSero/Qwen3.5-99B 2 months ago

Donation cost to run Heretic or otherwise Abliterate this?

3

#3 opened 2 months ago by

dissociativity

New activity in brandonmusic/GLM-5.2-NVFP4-REAP-Recall-N172 2 months ago

Axis 4 reasoning/termination: 3,057 -- Can you share this calibration data?

👍 1

3

#2 opened 2 months ago by

0xSero

New activity in 0xSero/Gemma-4-19B 3 months ago

Korean Multilingual is broken.

4

#6 opened 3 months ago by

DFveloper

New activity in 0xSero/GLM-5.1-555B-W4A16 3 months ago

Starting GPTQ model on H200 fails

3

#2 opened 3 months ago by

hjjg85

New activity in 0xSero/Qwen3.6-28B 4 months ago

error with vLLM

6

#3 opened 4 months ago by

bnjmnmarie

New activity in deepseek-ai/DeepSeek-V4-Flash 4 months ago

Running models with vLLM on the RTX Pro 6000 - SM120

👀👍 2

12

#28 opened 4 months ago by

liku2001

New activity in 0xSero/Qwen3.6-35B-GGUF 4 months ago

What kind of token per second can we expect if running Windows and llama.cpp on Framework Desktop?

2

#2 opened 4 months ago by

Clauscdotcom

New activity in 0xSero/Qwen3.6-28B 4 months ago

Thank you 🙏

4

#1 opened 5 months ago by

BlueNipples

New activity in tencent/Hy3-preview 5 months ago

Special Token Disaster: Your Tech Lead Has Zero Design Taste

👀🔥 3

4

#6 opened 5 months ago by

ytgui

New activity in 0xSero/Qwen3.5-264B-W4A16 5 months ago

How are you running this?

5

#1 opened 5 months ago by

richardhundt

New activity in 0xSero/Gemma-4-19B 5 months ago

use chat template here or the new one from google?

1

#5 opened 5 months ago by

Grandys

New activity in 0xSero/Gemma-4-21B 5 months ago

Repetition loops with llama.cpp defaults

1

#2 opened 5 months ago by

todaymare

New activity in atbender/Qwen3.5-REAP-212B-A17B-W4A16 6 months ago

"vLLM Launch Failed - Kernel Incompatibility with RTX 3090"

5

#3 opened 6 months ago by

steppi

Add recovery report for VLM fix

#1 opened 6 months ago by

0xSero

VLM recovery: multimodal config/index + clean vision encoder + manifest

#2 opened 6 months ago by

0xSero