stepfun-ai/Step-3.7-Flash-GGUF
Image-Text-to-Text • 197B • Updated • 29.7k • 62
Jacek Popławski
jacek2024
AI & ML interests
None yet
Recent Activity
liked a model 1 day ago
stepfun-ai/Step-3.7-Flash-GGUF reacted to danielhanchen's post with 🔥 25 days ago
We made a guide on how to run open LLMs in Claude Code, Codex and OpenClaw.
Use Gemma 4 and Qwen3.6 GGUFs for local agentic coding on 24GB RAM
Run with self-healing tool calls, code execution, web search via the Unsloth API endpoint and llama.cpp
Guide: https://unsloth.ai/docs/basics/api new activity 27 days ago
unsloth/gemma-4-31B-it-GGUF:chat template?Organizations
None yet
liked a
model 1 day ago
reacted to danielhanchen's post with 🔥 25 days ago
Post
8830
We made a guide on how to run open LLMs in Claude Code, Codex and OpenClaw.
Use Gemma 4 and Qwen3.6 GGUFs for local agentic coding on 24GB RAM
Run with self-healing tool calls, code execution, web search via the Unsloth API endpoint and llama.cpp
Guide: https://unsloth.ai/docs/basics/api
Use Gemma 4 and Qwen3.6 GGUFs for local agentic coding on 24GB RAM
Run with self-healing tool calls, code execution, web search via the Unsloth API endpoint and llama.cpp
Guide: https://unsloth.ai/docs/basics/api
chat template?
#19 opened 27 days ago
by jacek2024
https://huggingface.co/inclusionAI/Ling-2.6-flash
➕ 1
4
#2279 opened about 1 month ago
by 
Doctor-Chad-PhD
120B model?
👍 3
2
#21 opened about 1 month ago
by jacek2024
liked a
model about 1 month ago
Some info?
👍 1
2
#1 opened about 1 month ago
by jacek2024
liked a
model about 2 months ago
reacted to DavidAU's post with 🔥 about 2 months ago
Post
7657
THREE Gemma 4 , 31B Uncensored Fine Tunes (via Unsloth, inhouse datasets):
Uncensored first, then tuned.
Some benchmarks posted, others pending.
Examples posted, detailed instructions.
Some GGUFs are up; others pending as of this writing.
Enjoy:
DavidAU/gemma-4-31B-it-Mystery-Fine-Tune-HERETIC-UNCENSORED-Thinking
DavidAU/gemma-4-31B-it-Grand-Horror-X-INTENSE-HERETIC-UNCENSORED-Thinking
DavidAU/gemma-4-31B-it-The-DECKARD-HERETIC-UNCENSORED-Thinking
UPDATE:
DavidAU/gemma-4-E4B-it-The-DECKARD-Expresso-Universe-HERETIC-UNCENSORED-Thinking
Exceeds Gemma4 26B-A4B in critical benchmarks.
Uncensored first, then tuned.
Some benchmarks posted, others pending.
Examples posted, detailed instructions.
Some GGUFs are up; others pending as of this writing.
Enjoy:
DavidAU/gemma-4-31B-it-Mystery-Fine-Tune-HERETIC-UNCENSORED-Thinking
DavidAU/gemma-4-31B-it-Grand-Horror-X-INTENSE-HERETIC-UNCENSORED-Thinking
DavidAU/gemma-4-31B-it-The-DECKARD-HERETIC-UNCENSORED-Thinking
UPDATE:
DavidAU/gemma-4-E4B-it-The-DECKARD-Expresso-Universe-HERETIC-UNCENSORED-Thinking
Exceeds Gemma4 26B-A4B in critical benchmarks.
- 6 replies
I would like to have some Air
👍 46
11
#2 opened about 2 months ago
by jacek2024
liked a
model 3 months ago
more info?
1
#1 opened 3 months ago
by jacek2024
liked 2
models 3 months ago
crashes on llama.cpp (CUDA)
2
#1 opened 3 months ago
by jacek2024
liked a
model 3 months ago
CUDA error
#1 opened 3 months ago
by jacek2024
upvoted an article 3 months ago
Article
GGML and llama.cpp join HF to ensure the long-term progress of Local AI
- +4
ggerganov, ngxson, allozaur, lysandre, victor, julien-c
• • 507