Organization

Pollard Weights

PollardWeights

Memory-fit quantization · role-aware GGUF builds · running frontier LLMs on small hardware · MoE expert placement

Models in Library2

Datasets in Library0

Models on Hugging Face24

Followers35

Compare the published evidence

This profile connects the 2 model and dataset records shown below to their upstream cards and sources. The library counts describe SAVRN's coverage, rather than this publisher's entire output.

Published tasks: Image and text to text, Text generation.

Reported licenses: apache-2.0, mit. Open a record to review its specific license and conditions.

Compare model specifications, source dates, and hardware estimates on the individual records. Publisher identity verification is separate from a model's quality, deployment readiness, or suitability for your work.

Models

Model · Image and text to text

FrogNano-4B-2609-Pollard

Pollard Weights

Pollard builds of microsoft/FrogNano-4B-2609 made with Pollard Weights -- a ladder of measured-allocation quants (bits placed by per-layer sensitivity, not a uniform crush). Standard GGUF -- runs in stock llama.cpp / ikllama.cpp, Ollama, LM Studio, except where noted. IQ2KT needs ikllama.cpp: its allocation puts ikllama-only atoms on the tensors it protects. The rest run anywhere. Every rung is the same weights, sized to a different RAM budget by the measured allocation. Pick the largest one that fits your machine with room for context: - ~5.6 GB RAM / VRAM -> Q6K (3.56 GB). - ~4.5 GB RAM / VRAM -> IQ4XS (2.48 GB). - ~4.1 GB RAM / VRAM -> IQ3S (2.06 GB). - ~3.4 GB RAM / VRAM -> IQ2KT (1.42…

Open weights mit trellis

View model

Model · Text generation

gemma-4-12B-it-Pollard

Pollard Weights

Pollard builds of google/gemma-4-12B-it made with Pollard Weights -- a ladder of measured-allocation quants (bits placed by per-layer sensitivity, not a uniform crush). Standard GGUF -- every file here runs in stock llama.cpp / ikllama.cpp, Ollama, LM Studio. Every rung is the same weights, sized to a different RAM budget by the measured allocation. Pick the largest one that fits your machine with room for context: - ~12 GB RAM / VRAM -> Q6K (9.65 GB). - ~9 GB RAM / VRAM -> IQ4XS (6.78 GB). - ~7 GB RAM / VRAM -> IQ2XXS (4.64 GB). f16 reference PPL 23.041768. These are standard GGUF and run with llama.cpp: They also work in anything built on llama.cpp -- LM Studio, koboldcpp, Jan, ramalama…

Open weights apache-2.0 trellis

View model