Here i would the LFM2 fine tunes that i am proud of.
Daniel Fox PRO
FlameF0X
AI & ML interests
Pre-training text generator.
(Brother, im 18)
Please don't try to contact me.
Recent Activity
updated a dataset about 2 hours ago
FlameF0X/Banner-dataset updated a dataset about 2 hours ago
FlameF0X/assets repliedto their post about 2 hours ago
My models on the Intel Low-Bit LLM Leaderboard
Figured I'd share where my quantized models landed on https://huggingface.co/spaces/Intel/low_bit_open_llm_leaderboard since I hadn't posted about it yet.
https://huggingface.co/FlameF0X/Qwen3-4B-Distilled-Claude-4.6 (NVFP4 and MXFP4) sit at ranks 23 and 24 with 62.68% and 61.18% average, right below the base Qwen3-4B. Not bad considering they were distilled from Claude 4.6 rather than trained from scratch.
https://huggingface.co/FlameF0X/LFM2.5-1.2B-Distilled-Claude-4.6 and https://huggingface.co/FlameF0X/LFM2.5-1.2B-Thinking-CodeX land around rank 47-49, competitive with MiniCPM5-1B and the Qwen3 sub-1B models despite being a larger base architecture.
The funny one is https://huggingface.co/FlameF0X/Qwen2-0.2B-pt and https://huggingface.co/FlameF0X/Qwen2-0.2B-it. They're not properly trained — genuinely undertrained, basically undefined — and they still beat openai/gpt-oss-20b at rank 66. The 20B model. Not sure what that says but it's something.
https://huggingface.co/FlameF0X/LFM2-Research is at the bottom of my lineup but it's a research artifact, not meant to be competitive.
Chart below showing my models vs nearby competitors, with size vs performance on the left.
Chart made by ClaudeOrganizations
Liquid Claude is a small series of LiquidAI/LFM2.5-1.2B-Thinking model that have been fine tuned on Claude chats/data.
-
FlameF0X/LFM2.5-1.2B-Distilled-Claude-4.6
Text Generation • 1B • Updated • 991 • 2 -
FlameF0X/LFM2.5-1.2B-Distilled-Claude-4.6-GGUF
1B • Updated • 618 • 4 -
FlameF0X/Qwen3-4B-Distilled-Claude-4.6
Text Generation • 4B • Updated • 149 • • 1 -
FlameF0X/LFM2.5-1.2B-Distilled-Claude-GGUF
Text Generation • 1B • Updated • 315
A collection of all the Nano models I made. Nano Stuff contains from SR to music generation and so on.
Note: The models are listed in the default order set by Hugging Face, so the latest model appears at the botSeries
All the RL agent i made
Here i would the LFM2 fine tunes that i am proud of.
Liquid Claude is a small series of LiquidAI/LFM2.5-1.2B-Thinking model that have been fine tuned on Claude chats/data.
-
FlameF0X/LFM2.5-1.2B-Distilled-Claude-4.6
Text Generation • 1B • Updated • 991 • 2 -
FlameF0X/LFM2.5-1.2B-Distilled-Claude-4.6-GGUF
1B • Updated • 618 • 4 -
FlameF0X/Qwen3-4B-Distilled-Claude-4.6
Text Generation • 4B • Updated • 149 • • 1 -
FlameF0X/LFM2.5-1.2B-Distilled-Claude-GGUF
Text Generation • 1B • Updated • 315
A collection for build-small-hackathon :)
A collection of all the Nano models I made. Nano Stuff contains from SR to music generation and so on.
A collection dedicated to my pre-train LMs for chess.
Note: The models are listed in the default order set by Hugging Face, so the latest model appears at the botSeries
All the RL agent i made