PollardWeights/Penjing-27B-Pollard
Image-Text-to-Text • 27B • Updated • 1.1k • 4
AI & ML interests
Memory-fit quantization · role-aware GGUF builds · running frontier LLMs on small hardware · MoE expert placement
Recent Activity
View all activity
Organization Card
Frontier models. Small hardware. No compromise.
Pollard Weights builds a model measured to fit your target device — phone to wafer — and ships it to any runtime: GGUF · GPTQ · MLX · EXL3 · MX/NVFP4.
- 🔧 The tool: github.com/WestWaters/pollard-weights
- 📦 This org hosts Pollard-built model repos (know-what-fits-before-you-download).
- One measured allocation, five lanes, opt-in gold-method calibration.
models 20
PollardWeights/gemma-4-12B-it-Pollard
Text Generation • 12B • Updated • 953 • 1
PollardWeights/FlyBrain-Pollard-VL-CNSv1
2B • Updated • 423
PollardWeights/HumanBrain-Pollard-H01
0.5B • Updated • 530 • 8
PollardWeights/FlyBrain-Pollard-CNSv1
0.5B • Updated • 396
PollardWeights/Carnice-V3-27b-Pollard
Image-Text-to-Text • 27B • Updated • 3.16k • 1
PollardWeights/Qwen3.8-27B-Pollard
Image-Text-to-Text • 27B • Updated • 1.2k
PollardWeights/Qwen2.5-7B-Instruct-Pollard
Text Generation • 8B • Updated • 2.68k
PollardWeights/Qwen2.5-14B-Instruct-Pollard
Text Generation • 15B • Updated • 2.74k
PollardWeights/Spark-X2.5-4B-Pollard
Text Generation • 4B • Updated • 963 • 1
datasets 0
None public yet