A static guide to local AI models that fit in a 8GB RAM budget. Built from the LocalClaw model database and ranked by hardware fit, use case, quality and speed.
With 8GB RAM, prioritize models with minimum RAM at or below 8GB and avoid filling memory completely. For most users, start with MiniCPM5 2B, then test a faster smaller model if latency matters.
Why it fits: Comfortable memory headroom. General match. Catalogue summary: Official OpenBMB compact on-device LLM with Apache 2.0 licensing, 131K context, tool-calling and coding focus, plus official Q4_K_M GGUF, Ollama, llama.cpp, Docker and OpenClaw run paths.
Why it fits: Comfortable memory headroom. General match. Catalogue summary: IBM Granite 4.2 3B is the compact Apache 2.0 Granite reasoning model with 128K native context, thinking-mode chat, tool calling and official GGUF artifacts for laptop-class local inference.
Why it fits: Comfortable memory headroom. General match. Catalogue summary: Liquid AI edge vision-language model with LFM2.5-2.6B backbone, SigLIP2 NaFlex vision encoder, 32K context, LFM 1.0 open weights and official GGUF plus llama.cpp and MLX runtime paths for local image chat and OCR.
Why it fits: Comfortable memory headroom. General match. Catalogue summary: Liquid AI compact hybrid model with 128K context, LFM 1.0 open weights, official GGUF, ONNX and MLX artifacts, and practical llama.cpp / LM Studio paths for 8GB-class local machines.
Why it fits: Comfortable memory headroom. General match. Catalogue summary: DFM-Mimir is a Danish and English 1B-class HRM language model trained from scratch by Danish Foundation Models, with Apache 2.0 weights, permissible-data positioning and GGUF artifacts for lightweight local inference.
Why it fits: Comfortable memory headroom. General match. Catalogue summary: InternScience compact dense agent model with Apache 2.0 licensing, 262K context and official Q4_K_M GGUF artifacts for 8GB-class local assistants.
Why it fits: Comfortable memory headroom. General match. Catalogue summary: IBM Granite 4.1 compact long-context instruct model. Apache 2.0, 131K context, tool calling, RAG and code tasks, with an official Q4_K_M GGUF for practical 4-8 GB local machines.
Why it fits: Comfortable memory headroom. General match. Catalogue summary: NVIDIA fine-tune of Llama 3.1 with hybrid /think and /no_think modes, 128K context and Apache 2.0 licensing. A compact local option for reasoning and chat.
Why it fits: Comfortable memory headroom. General match. Catalogue summary: NVIDIA compact hybrid model distilled from a 9B teacher, with hybrid attention and SSM layers. A lightweight option for local chat and reasoning under the NVIDIA Open Model License.
Why it fits: Comfortable memory headroom. General match. Catalogue summary: OpenBMB compact on-device LLM with Apache 2.0 licensing, 128K context, tool-calling focus and official GGUF plus MLX artifacts for laptops and edge devices.
Why it fits: Comfortable memory headroom. General match. Catalogue summary: IbnSina-1.5B is a Persian-first 1.48B Llama-compatible language model trained from scratch on a Persian-heavy corpus, with Apache 2.0 weights and GGUF artifacts for laptop, phone, Ollama, LM Studio and llama.cpp use.
Why it fits: Comfortable memory headroom. General match. Catalogue summary: IBM ultra-efficient 2B. Best-in-class among small models for tool calling & structured output. Perfect for on-device RAG and agents. 128K context. Apache 2.0.
Why it fits: Comfortable memory headroom. General match. Catalogue summary: Compact Qwen 3.5 model with hybrid thinking, 256K context and multilingual support. Runs in an 8GB-class local setup with the listed quantization. Apache 2.0.
Why it fits: Comfortable memory headroom. General match. Catalogue summary: Mistral AI compact multimodal instruct model. Apache 2.0, strong local app support through official GGUF, LM Studio, Ollama and llama.cpp artifacts. Practical on normal laptops.
Why it fits: Comfortable memory headroom. General match. Catalogue summary: Google Gemma for phones/tablets/laptops. Optimized for mobile and edge. 552K downloads.
Why it fits: Comfortable memory headroom. General match. Catalogue summary: Alibaba's think-then-answer model. Built-in chain-of-thought reasoning at just 4B params.
Why it fits: Comfortable memory headroom. General match. Catalogue summary: Google's multimodal gem. Understands text AND images natively. Great quality-to-size ratio.
Why it fits: Comfortable memory headroom. General match. Catalogue summary: Microsoft's latest small miracle. Punches way above its weight in reasoning & code.
This contextual order uses LocalClaw catalogue quality, reasoning, coding and speed fields plus freshness and RAM fit. It is not the homepage LocalClaw score, not a standardized third-party benchmark and never includes community stars. Catalogue summaries may repeat upstream claims; verify them at the linked model repository.