i smell a pretty useless yet exciting new model
🏗️ Building on HF
SolsticeAI
SolsticeAI
AI & ML interests
Real Intelligence,
Built for the real world.
Recent Activity
repliedto DedeProGames's post about 12 hours ago
Meet Supra2.5-Ultra-Preview-001. 230M parameters, ~40.4B training tokens.
SupraLabs has released the first preview of its Supra2.5-Ultra family: a compact, Llama-style base model for text completion and small-model experimentation.
What's inside?
• 230M parameters
• 32 transformer layers
• 2,048-token context window
• Grouped Query Attention: 12 attention heads, 4 KV heads
• 49,152-token vocabulary
• SwiGLU activation, RoPE and tied embeddings
• BF16 weights and Hugging Face Transformers support
• Apache 2.0 license
Training
The model was trained on approximately 40.4B tokens from FineWeb-Edu, DCLM-Baseline and FineMath using a single A100 SXM.
Reported zero-shot results
• HellaSwag: 37.18% normalized accuracy
• PIQA: 65.78% accuracy
• ARC-Easy: 57.11% accuracy
• ARC-Challenge: 26.28% normalized accuracy
Want to experiment?
Code on REPO.
Model, weights and usage example:
SupraLabs/Supra2.5-Ultra-Preview-001 new activity about 12 hours ago
nerkyor/Qwen3.8-27B-Coder390-EfficientThink-Opus5.5-GPT6Astra-Grok4.7-DSV4Pro-K3-SFT-RLOO-MTP-DFlash2:Q2/Q3 what doas that mean? updated a model about 16 hours ago
Solstice-AI/Protium-1.0Organizations
replied to DedeProGames's post about 12 hours ago
New activity in nerkyor/Qwen3.8-27B-Coder390-EfficientThink-Opus5.5-GPT6Astra-Grok4.7-DSV4Pro-K3-SFT-RLOO-MTP-DFlash2 about 12 hours ago
Q2/Q3 what doas that mean?
4
#10 opened 3 days ago
by 
kalle07
updated a
model about 16 hours ago
updated a
model about 18 hours ago
effectivity
➕ 1
2
#22 opened 1 day ago
by SolsticeAI
liked 2
models 1 day ago
published a
model 1 day ago
liked a
model 1 day ago
replied to SeaWolf-AI's post 1 day ago
im concerned most of these replies are claude like
reacted to DavidAU's post with 😔 2 days ago
Post
4,713
TURBO-BRILLIANCE 50X - Qwen 3.8 27B, LFM, and more coming soon...
15 AI CONSTRUCTS:
Each a precision engineered "consciousness" to help you in every task, using fewer tokens and generating better answers.
This model has significant internal upgrades under user control that are "on the fly" (you set in your prompt(s) and/or API).
Please read this model card carefully to get the most from it - including all the reasoning and instruct modes (27+27+9 xhigh) that feature model suggestions ("context help") for all use cases.
The Turbo Brilliance system will begin appearing in other model sizes/types shortly (IE: Qwen, Gemma, Mistral, GLM, Llama, ... including our strongest fine tunes too). The "rollout" is now in progress...
DavidAU/Qwen3.8-27B-Turbo-Brilliance-50X-Reasoning-Instruct-NEO-MAX-MTP-GGUF
Qwen 3.5 9B The Defiant (1000+likes, 2m+ downloads) [ Limited 12x]:
DavidAU/Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-NEO-IMATRIX-MAX-MTP-GGUF
LFMs [Limited, 12x]:
DavidAU/LFM2.5-2.6B-Qwen3.8-Turbo-Brilliance-Power-X12-NEO-MAX-GGUF
DavidAU/LFM2.5-8B-A1B-Qwen3.8-Turbo-Brilliance-Power-X12-NEO-MAX-GGUF
PS: Qwen Next, LFM2.5 24B-A2B, Qwen 3.6 35B-A3B and others in testing now.
COLLECTION:
https://huggingface.co/collections/DavidAU/turbo-brilliance-ai-constructs-50x-reasoning-instruct
Please see our support page for breakdown of models (sort), info on projects and a lot more information:
DavidAU/support
15 AI CONSTRUCTS:
Each a precision engineered "consciousness" to help you in every task, using fewer tokens and generating better answers.
This model has significant internal upgrades under user control that are "on the fly" (you set in your prompt(s) and/or API).
Please read this model card carefully to get the most from it - including all the reasoning and instruct modes (27+27+9 xhigh) that feature model suggestions ("context help") for all use cases.
The Turbo Brilliance system will begin appearing in other model sizes/types shortly (IE: Qwen, Gemma, Mistral, GLM, Llama, ... including our strongest fine tunes too). The "rollout" is now in progress...
DavidAU/Qwen3.8-27B-Turbo-Brilliance-50X-Reasoning-Instruct-NEO-MAX-MTP-GGUF
Qwen 3.5 9B The Defiant (1000+likes, 2m+ downloads) [ Limited 12x]:
DavidAU/Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-NEO-IMATRIX-MAX-MTP-GGUF
LFMs [Limited, 12x]:
DavidAU/LFM2.5-2.6B-Qwen3.8-Turbo-Brilliance-Power-X12-NEO-MAX-GGUF
DavidAU/LFM2.5-8B-A1B-Qwen3.8-Turbo-Brilliance-Power-X12-NEO-MAX-GGUF
PS: Qwen Next, LFM2.5 24B-A2B, Qwen 3.6 35B-A3B and others in testing now.
COLLECTION:
https://huggingface.co/collections/DavidAU/turbo-brilliance-ai-constructs-50x-reasoning-instruct
Please see our support page for breakdown of models (sort), info on projects and a lot more information:
DavidAU/support
updated 9
models 2 days ago
SolsticeAI/Qwen3.8-27B-pi-mlx-6Bit
Text Generation • 27B • Updated • 237
Solstice-AI/DeepSeek-V4.1-Flash-GGUF
Text Generation • 748B • Updated • 3.11k • 1
Solstice-AI/Qwen3.8-27B-TTURBO-Cold-Fusion-709-L-Uncensored-mlx-oQ8e-1M
Image-Text-to-Text • 28B • Updated • 794 • 4
Solstice-AI/Qwen3.8-27B-TTURBO-Cold-Fusion-709-L-Uncensored-mlx-oQ8e
Image-Text-to-Text • 28B • Updated • 180
Solstice-AI/Qwen3.8-27B-TTURBO-Cold-Fusion-709-L-Uncensored-mlx-oQ6e-1M
Image-Text-to-Text • 28B • Updated • 190
Solstice-AI/Qwen3.8-27B-TTURBO-Cold-Fusion-709-L-Uncensored-mlx-oQ6e
Image-Text-to-Text • 28B • Updated • 158
Solstice-AI/Qwen3.8-27B-TTURBO-Cold-Fusion-709-L-Uncensored-mlx-oQ4e
Image-Text-to-Text • 28B • Updated • 337 • 2
Solstice-AI/Qwen3.8-27B-TTURBO-Cold-Fusion-709-L-Uncensored-UltraOptimised-VariableThinking-1M
Image-Text-to-Text • 0.5B • Updated • 1.98k • 4
Solstice-AI/Qwen3.8-27B-TTURBO-Cold-Fusion-709-L-NM-DAU-UltraOptimised-VariableThinking-GGUF
Image-Text-to-Text • 27B • Updated • 1.98k • 2