Span Spek

spanspek's activity

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

New activity in nvidia/Nemotron-Cascade-14B-Thinking 3 days ago

Excellent model

#3 opened 3 days ago by

spanspek

New activity in Nanbeige/Nanbeige4.1-3B 11 days ago

Insane performance

❤️ 9

3

#4 opened 13 days ago by

AntDX316

New activity in lovedheart/Qwen3-Coder-Next-REAP-40B-A3B-GGUF 18 days ago

Information about the dataset is needed

👍 1

2

#1 opened 20 days ago by

Blizado

New activity in Qwen/Qwen3-Coder-Next 21 days ago

FP-8 version please 🥺

3

#7 opened 21 days ago by

nikhilfande

New activity in moonshotai/Kimi-K2.5 29 days ago

What quantization is the base model?

2

#8 opened 29 days ago by

spanspek

New activity in nvidia/Nemotron-Cascade-14B-Thinking about 1 month ago

Extremely misleading benchmarks

➕ 1

5

#1 opened 2 months ago by

rombodawg

New activity in noctrex/LightOnOCR-2-1B-ocr-soup-GGUF about 1 month ago

Phenomenal model

2

#1 opened about 1 month ago by

spanspek

New activity in ngxson/GLM-4.7-Flash-GGUF about 1 month ago

Deepseek architecture?

7

#1 opened about 1 month ago by

spanspek

New activity in noctrex/Nemotron-Cascade-14B-Thinking-MXFP4-GGUF about 1 month ago

Feedback from testing

👍 1

1

#1 opened about 1 month ago by

spanspek

New activity in noctrex/GLM-4.7-Flash-MXFP4_MOE-GGUF about 1 month ago

Feedback from running in LM Studio 0.39.3 with v1.103.2 of llama.cpp

29

#1 opened about 1 month ago by

spanspek

New activity in nvidia/Qwen2.5-CascadeRL-RM-72B about 1 month ago

Possible use-cases?

#1 opened about 1 month ago by

spanspek

New activity in lmstudio-community/GLM-4.7-Flash-GGUF about 1 month ago

A few observations - Memory estimation & thinking is getting stuck in loops

#1 opened about 1 month ago by

spanspek

New activity in unsloth/GLM-4.7-Flash-GGUF about 1 month ago

DeepSeek architecture?

5

#2 opened about 1 month ago by

spanspek

New activity in cyankiwi/GLM-4.7-Flash-AWQ-4bit about 1 month ago

Can I run this with 36gb VRAM+ 192gb ram

10

#1 opened about 1 month ago by

nimishchaudhari

New activity in marksverdhei/GLM-4.7-Flash-FP8 about 1 month ago

Question on size of model weights

4

#1 opened about 1 month ago by

spanspek

New activity in 0xSero/GLM-4.7-REAP-50-W4A16 about 2 months ago

APPLE SILICON

1

#6 opened about 2 months ago by

Igarzonalva

New activity in unsloth/Nemotron-3-Nano-30B-A3B-GGUF 2 months ago

1 M‑token context running smoothly at ~25 t/s on a 12 GB RX 6700 XT is nothing short of impressive.

👍 2

2

#6 opened 2 months ago by

Jbulger82

New activity in cerebras/Qwen3-Coder-REAP-25B-A3B 4 months ago

Hardware question

5

#3 opened 4 months ago by

spanspek

New activity in Intel/GLM-4.6-gguf-q2ks-mixed-AutoRound 4 months ago

Model quality relative to other quantization techniques?

1

#1 opened 4 months ago by

spanspek

New activity in Qwen/Qwen3-VL-4B-Instruct-FP8 4 months ago

VRAM usage not making sense

1

#2 opened 4 months ago by

spanspek