baa-ai/Gemma-4-31B-it-RAM-43GB-GGUF overview
Gemma 4 31B it — 43GB GGUF Mixed precision quantized version of google/gemma 4 31B it https://huggingface.co/google/gemma 4 31B it using a proprietary quantiza…
Runs locally from ~39.94 GB disk (32 GB+ VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| Gemma-4-31B-it-RAM-43GB.gguf | GGUF | GGUF | 39.94 GB | Download |
Model Details
| Model ID | baa-ai/Gemma-4-31B-it-RAM-43GB-GGUF |
|---|---|
| Author | baa-ai |
| Pipeline | text-generation |
| License | gemma |
| Base model | google/gemma-4-31B-it |
| Last modified | 2026-10-16T09:40:11.000Z |
Model README
---
library_name: gguf
tags:
- gguf
- quantized
- mixed-precision
license: gemma
base_model: google/gemma-4-31B-it
base_model_relation: quantized
pipeline_tag: text-generation
---
Gemma-4-31B-it — 43GB (GGUF)
Mixed-precision quantized version of google/gemma-4-31B-it using a proprietary quantization method by baa.ai.
Metrics
| Metric | Value |
|--------|-------|
| Size | 42.9 GB |
| Average bits | 11.17 |
| Format | llama.cpp (GGUF) |
Usage
brew install llama.cpp huggingface-cli
hf download baa-ai/Gemma-4-31B-it-RAM-43GB-GGUF --include "*.gguf" --local-dir ./gemma-4-31b-it-ram-43gb
llama-cli -m ./gemma-4-31b-it-ram-43gb/Gemma-4-31B-it-RAM-43GB.gguf -p "Hello!" -n 256 -ngl 99
Or via llama-server for an OpenAI-compatible HTTP API:
llama-server -m ./gemma-4-31b-it-ram-43gb/Gemma-4-31B-it-RAM-43GB.gguf --port 8080 -ngl 99 --ctx-size 8192
Also works with Ollama, LM Studio, and llama-cpp-python.
---
Quantized by baa.ai
---
Black Sheep AI Products
Black Sheep AI builds private AI with the Bounded AI Architecture (BAA): three layers, each bound to something you control, on infrastructure you control. Nothing leaves your boundary.
Ram (Reasoning Layer) — Full-capability frontier models, shrunk to fit smaller GPUs with reasoning kept and certified. They rely strictly on your Data Modules for knowledge, so you swap the model as better ones ship.
Paddock (Knowledge Plane) — Binds your Data Modules directly to the reasoning layer: one per topic, period, person, permission or tenant. Permission, freeze, hand back or delete each one on its own.
Watchman (GRC Layer) — Governance, risk and compliance in a single, complete audit log: every module permission, every bind, every model's provenance. Five certificates before anything goes live.
Shepherd — Takes a frontier model, compresses it into a Ram reasoning model, certifies it with Watchman, binds it to your Paddock, and deploys the Bounded AI Architecture to your infrastructure: your cloud, a Mac Studio, or an air-gapped facility.
Learn more at baa.ai — Private AI for enterprises whose data cannot leave the building.
Run baa-ai/Gemma-4-31B-it-RAM-43GB-GGUF with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models