PiD Image Upscaler
🥖
55
Pixel Diffusion Decoder
Maho S
Jagerfly
·
AI & ML interests
None yet
Recent Activity
liked a Space 21 days ago
prithivMLmods/PiD-Image-Upscaler liked a model 23 days ago
gaston-parravicini/LFM2.5-8B-A1B-Uncensored-Gaston-GGUF liked a model about 1 month ago
mradermacher/GRM-2.5-GGUFOrganizations
None yet
liked a
Space 21 days ago
liked a
model 23 days ago
liked 8
models about 1 month ago
mradermacher/GRM-2.5-GGUF
4B • Updated • 158 • 1
treadon/gemma4-E2B-it-Abliterated-AND-Disinhibited-USE-THIS
Image-Text-to-Text • 5B • Updated • 197 • 9
prithivMLmods/gemma-4-E2B-it-Uncensored-MAX-GGUF
Image-Text-to-Text • 5B • Updated • 3.23k • 4
artificialguybr/FILMGRAIN-REDMOND-FLUXKLEIN9B
Text-to-Image • Updated • 114 • 9
artificialguybr/ANALOG-REDMOND-FLUXKLEIN9B
Text-to-Image • Updated • 69 • 7
artificialguybr/CINEMATIC-FILMSTILL-REDMOND-FLUXKLEIN9B
Text-to-Image • Updated • 1.07k • 28
Minthy/ToriiGate-0.5
Image-Text-to-Text • 5B • Updated • 3.86k • 89
MaxedOut/ComfyUI-Starter-Packs
Text-to-Image • 5B • Updated • 3.11k • 269
liked a
dataset about 1 month ago
liked 3
models 3 months ago
reacted to SeaWolf-AI's post with ❤️ 3 months ago
Post
11145
🏟️ Smol AI WorldCup: A 4B Model Just Beat 8B — Here's the Data
We evaluated 18 small language models from 12 makers on 125 questions across 7 languages. The results challenge the assumption that bigger is always better.
Community Article: https://huggingface.co/blog/FINAL-Bench/smol-worldcup
Live Leaderboard: ginigen-ai/smol-worldcup
Dataset: ginigen-ai/smol-worldcup
What we found:
→ Gemma-3n-E4B (4B, 2GB RAM) outscores Qwen3-8B (8B, 5.5GB). Doubling parameters gained only 0.4 points. RAM cost: 2.75x more.
→ GPT-OSS-20B fits in 1.5GB yet matches Champions-league dense models requiring 8.5GB. MoE architecture is the edge AI game-changer.
→ Thinking models hurt structured output. DeepSeek-R1-7B scores 8.7 points below same-size Qwen3-8B and runs 2.7x slower.
→ A 1.3B model fabricates confident fake content 80% of the time when prompted with nonexistent entities. Qwen3 family hits 100% trap detection across all sizes.
→ Qwen3-1.7B (1.2GB) outscores Mistral-7B, Llama-3.1-8B, and DeepSeek-R1-14B. Latest architecture at 1.7B beats older architecture at 14B.
What makes this benchmark different?
Most benchmarks ask "how smart?" — we measure five axes simultaneously: Size, Honesty, Intelligence, Fast, Thrift (SHIFT). Our ranking metric WCS = sqrt(SHIFT x PIR_norm) rewards models that are both high-quality AND efficient. Smart but massive? Low rank. Tiny but poor? Also low.
Top 5 by WCS:
1. GPT-OSS-20B — WCS 82.6 — 1.5GB — Raspberry Pi tier
2. Gemma-3n-E4B — WCS 81.8 — 2.0GB — Smartphone tier
3. Llama-4-Scout — WCS 79.3 — 240 tok/s — Fastest model
4. Qwen3-4B — WCS 76.6 — 2.8GB — Smartphone tier
5. Qwen3-1.7B — WCS 76.1 — 1.2GB — IoT tier
Built in collaboration with the FINAL Bench research team. Interoperable with ALL Bench Leaderboard for full small-to-large model comparison.
Dataset is open under Apache 2.0 (125 questions, 7 languages). We welcome new model submissions.
We evaluated 18 small language models from 12 makers on 125 questions across 7 languages. The results challenge the assumption that bigger is always better.
Community Article: https://huggingface.co/blog/FINAL-Bench/smol-worldcup
Live Leaderboard: ginigen-ai/smol-worldcup
Dataset: ginigen-ai/smol-worldcup
What we found:
→ Gemma-3n-E4B (4B, 2GB RAM) outscores Qwen3-8B (8B, 5.5GB). Doubling parameters gained only 0.4 points. RAM cost: 2.75x more.
→ GPT-OSS-20B fits in 1.5GB yet matches Champions-league dense models requiring 8.5GB. MoE architecture is the edge AI game-changer.
→ Thinking models hurt structured output. DeepSeek-R1-7B scores 8.7 points below same-size Qwen3-8B and runs 2.7x slower.
→ A 1.3B model fabricates confident fake content 80% of the time when prompted with nonexistent entities. Qwen3 family hits 100% trap detection across all sizes.
→ Qwen3-1.7B (1.2GB) outscores Mistral-7B, Llama-3.1-8B, and DeepSeek-R1-14B. Latest architecture at 1.7B beats older architecture at 14B.
What makes this benchmark different?
Most benchmarks ask "how smart?" — we measure five axes simultaneously: Size, Honesty, Intelligence, Fast, Thrift (SHIFT). Our ranking metric WCS = sqrt(SHIFT x PIR_norm) rewards models that are both high-quality AND efficient. Smart but massive? Low rank. Tiny but poor? Also low.
Top 5 by WCS:
1. GPT-OSS-20B — WCS 82.6 — 1.5GB — Raspberry Pi tier
2. Gemma-3n-E4B — WCS 81.8 — 2.0GB — Smartphone tier
3. Llama-4-Scout — WCS 79.3 — 240 tok/s — Fastest model
4. Qwen3-4B — WCS 76.6 — 2.8GB — Smartphone tier
5. Qwen3-1.7B — WCS 76.1 — 1.2GB — IoT tier
Built in collaboration with the FINAL Bench research team. Interoperable with ALL Bench Leaderboard for full small-to-large model comparison.
Dataset is open under Apache 2.0 (125 questions, 7 languages). We welcome new model submissions.
- 1 reply
liked 5
models 4 months ago
llmfan46/Qwen3.5-9B-ultra-uncensored-heretic-v1
Image-Text-to-Text • 9B • Updated • 411 • 20
mradermacher/qwen3.5-9b-null-space-abliterated-GGUF
9B • Updated • 182 • 6
llmfan46/Qwen3.5-9B-ultra-uncensored-heretic-v1-GGUF
Image-Text-to-Text • 9B • Updated • 1.29k • 19
filvyb/Qwen3.5-9B-heretic-v2-GGUF
Image-Text-to-Text • 9B • Updated • 765 • 7
Crowfeather/Crow-9B-Opus-4.6-Distill-Heretic_Qwen3.5
9B • Updated • 270 • 4