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" alt="Full Deployment gemma-4-31B-it-AWQ-4bit Locally via Ollama 2" style="display:block; width:100%; height:auto; border-radius:8px;">
The most rapid route to a local installation of this model is through WSL2.
Proceed by following the technical instructions below.
Everything happens automatically, including the heavy cloud asset download.
To guarantee smooth performance, the process auto-selects the best options.
|
📡 Hash Check: 92dd90b31199459ab00288442daf9c33 | 📅 Last Update: 2026-07-02
|
The Gemma-4-31B-it-AWQ-4bit model is a 31‑billion parameter instruction‑tuned language model optimized for efficient inference. It leverages AWQ quantization to achieve 4‑bit precision while preserving much of the original performance. The model supports a 2048‑token context window, enabling coherent long‑form generation. Benchmarks show it rivals larger models on reasoning, coding, and multilingual tasks despite its reduced memory footprint. Its compact design makes it suitable for deployment on consumer‑grade hardware and edge devices. The following table compares key specifications with related models:
| Model | Parameters | Quantization | Context Length | Avg. Benchmark |
|---|---|---|---|---|
| Gemma-4-31B-it-AWQ-4bit | 31B | 4-bit AWQ | 2048 | 84.3 |
| Llama-2-70B | 70B | 16-bit | 4096 | 86.1 |
| Mistral-7B-v0.1 | 7B | 16-bit | 8192 | 78.5 |
- Installer setting up local Ollama models with custom system prompts
- How to Deploy gemma-4-31B-it-AWQ-4bit Windows FREE
- Downloader pulling specialized offline translation models for LibreTranslate systems
- Setup gemma-4-31B-it-AWQ-4bit PC with NPU No Admin Rights Complete Walkthrough FREE
- Downloader pulling high-fidelity text-to-speech model voices locally
- How to Run gemma-4-31B-it-AWQ-4bit PC with NPU Fully Jailbroken No-Code Guide
- Downloader pulling calibrated EXL2 quantizations of Llama-3.1-70B
- How to Deploy gemma-4-31B-it-AWQ-4bit via WebGPU (Browser) Step-by-Step FREE
- Script downloading optimized tokenizers designed specifically for complex localized text
- Zero-Click Run gemma-4-31B-it-AWQ-4bit Locally (No Cloud) Windows
- Setup tool mapping local CUDA environment variables for native nvcc code compilation
- Zero-Click Run gemma-4-31B-it-AWQ-4bit Zero Config No-Code Guide