Gemma 3 1B IT
Small text-only assistant for constrained devices.
License
Gemma license
GPU estimate (4-bit)
3 GB+
The N44 Model Library
Discover open AI models, compare capabilities, and find a starting point for your hardware.
Guided Model Finder
Choose your device and what you want to do. We’ll check a small, source-traceable set of runtime variants.
Your main task
Explore models
Curated entries · Publisher sync not yet run · Benchmarks require sourced results
25 models found
Small text-only assistant for constrained devices.
License
Gemma license
GPU estimate (4-bit)
3 GB+
Hugging Face
Lightweight text assistant for experimenting on modest hardware.
License
Apache 2.0
GPU estimate (4-bit)
3 GB+
Qwen
Compact text model for everyday questions and lightweight reasoning.
License
Apache 2.0
GPU estimate (4-bit)
5 GB+
Microsoft
Small instruction model for constrained local setups.
License
MIT
GPU estimate (4-bit)
5 GB+
Meta
Compact instruction model suitable for smaller local machines.
License
Llama 3.2 Community License
GPU estimate (4-bit)
5 GB+
Compact instruction-tuned model with image-and-text capabilities.
License
Gemma license
GPU estimate (4-bit)
6 GB+
Review the Gemma terms before use.
Qwen
A versatile instruction model with thinking and non-thinking modes.
License
Apache 2.0
GPU estimate (4-bit)
8 GB+
Meta
Widely supported instruction model with a custom community license.
License
Llama 3.1 Community License
GPU estimate (4-bit)
8 GB+
Access may require acceptance of license terms.
Qwen
Focused coding assistant for code generation and explanation.
License
Apache 2.0
GPU estimate (4-bit)
8 GB+
DeepSeek
Distilled reasoning model using a Qwen base.
License
MIT
GPU estimate (4-bit)
8 GB+
DeepSeek
Distilled reasoning model built from a Llama-family base.
License
Llama license terms apply
GPU estimate (4-bit)
8 GB+
Mistral AI
Popular compact instruction model with broad tooling support.
License
Apache 2.0
GPU estimate (4-bit)
8 GB+
Mistral AI
Smaller Mistral-family assistant; check terms for commercial deployment.
License
Mistral Research License
GPU estimate (4-bit)
8 GB+
IBM
Business-oriented instruction model for text and tool workflows.
License
Apache 2.0
GPU estimate (4-bit)
8 GB+
Mistral AI
Multilingual assistant model built for everyday text and code tasks.
License
Apache 2.0
GPU estimate (4-bit)
10 GB+
Qwen
Mid-size reasoning and instruction model for capable local hardware.
License
Apache 2.0
GPU estimate (4-bit)
12 GB+
Qwen
A more capable coding model for local development workflows.
License
Apache 2.0
GPU estimate (4-bit)
12 GB+
Multimodal assistant with image-and-text support.
License
Gemma license
GPU estimate (4-bit)
12 GB+
Microsoft
Compact reasoning-focused text model.
License
MIT
GPU estimate (4-bit)
12 GB+
DeepSeek
Mid-size distilled reasoning model.
License
MIT
GPU estimate (4-bit)
12 GB+
OpenAI
An open-weight reasoning model designed to run locally with supported runtimes.
License
Apache 2.0
GPU estimate (4-bit)
16 GB+
Check runtime support for its native quantization.
Qwen
Larger dense model for advanced local reasoning workloads.
License
Apache 2.0
GPU estimate (4-bit)
24 GB+
Qwen
Large coding-oriented model for supported local inference hardware.
License
Apache 2.0
GPU estimate (4-bit)
24 GB+
Larger multimodal model for capable local servers.
License
Gemma license
GPU estimate (4-bit)
24 GB+
Meta
Large text instruction model best suited to high-memory systems.
License
Llama 3.3 Community License
GPU estimate (4-bit)
48 GB+
Hugging Face downloads are usage/popularity signals, not quality benchmarks. Publisher snapshots are refreshed manually and may become outdated. Memory values are illustrative estimates for selected quantized GPU inference configurations, not minimum requirements or performance scores. CPU offloading, format, context length, and runtime can change fit substantially. Always check the publisher's model card and license.
Benchmarks & rankings
Explore documented benchmark results. Scores are only ranked when they share a benchmark version, evaluation setup and score unit. Missing results stay missing—not zero.
Coding problem success under a defined benchmark and evaluation window.
Verified results coming soon
No source-audited, protocol-matched results are published for this benchmark yet. N44 won't generate a leaderboard from estimates or unrelated benchmark scores.
Select up to three entries above. This comparison uses the same evaluation cohort, not an invented aggregate score.
No comparable results selected.
Benchmark scores alone do not describe local inference speed, memory use, safety or real-world suitability. N44 does not currently publish first-party standardized performance measurements.
Select up to three models in the library to compare their basic specs.
Start with a smaller model, check your available memory, and choose a compatible runtime such as Ollama. Download only from trusted publisher or runtime sources and review licenses before commercial use.
Model formats and runtime compatibility vary. These are external resources; N44 does not host or verify every downloadable file.