Mac Studio M5 Max 36GB has 36GB of unified memory and is a strong fit for sustained local AI and creative workloads. These recommendations are generated from the current LocalClaw catalogue and filtered for realistic memory headroom.
Amazon.fr listing checked October 5, 2026. Confirm current stock and delivery for your address.
Yes. With 36GB of unified memory, Mac Studio M5 Max 36GB fits 183 current LocalClaw catalogue models under the conservative 8k-context memory filter. Start with LFM2.5-24B-A2B. This desktop generation launched September 22, 2026. Amazon.fr listing checked October 5, 2026. Confirm current stock and delivery for your address. This is memory-fit guidance, not a hands-on speed benchmark.
Hardware facts come from Apple. LocalClaw separately calculates catalogue compatibility from unified memory and model requirements. No unreleased Mac performance result is inferred from chip specifications.
Yes. With 36GB of unified memory, Mac Studio M5 Max 36GB fits 183 current LocalClaw catalogue models under the conservative 8k-context memory filter. Start with LFM2.5-24B-A2B. This desktop generation launched September 22, 2026. Amazon.fr listing checked October 5, 2026. Confirm current stock and delivery for your address. This is memory-fit guidance, not a hands-on speed benchmark.
This configuration has 36GB of unified memory. Apple lists up to 128GB for the M5 Max family represented here. LocalClaw reserves memory for macOS, the runtime and an 8k context before marking a model compatible.
The generation launched September 22, 2026. Amazon.fr listing checked October 5, 2026. Confirm current stock and delivery for your address.
No. The compatibility count and ranking are calculated from 36GB of unified memory and the current LocalClaw catalogue. They are not measured tokens-per-second results or hands-on benchmarks.
Start with LFM2.5-24B-A2B on this Mac. LocalClaw has not hands-on validated runtime speed. Model fit is calculated conservatively from Apple-confirmed unified memory. A tight fit can still work, but close other apps, reduce context length when needed, and prefer the listed quantization.
Liquid AI LFM2.5 reasoning MoE built for private on-device agents. The official LFM 1.0 release has 24B total / 2.45B active parameters, 131K context, official GGUF and MLX artifacts, and a 14.5GB Q4_K_M GGUF for laptop/workstation local use.
Meta Superintelligence Lab local agent model with text+image input, 131K context, Apache 2.0 weights and official GGUF/ExecuTorch artifacts. The K-Quant 17GB build targets 24GB machines; 32GB is safer for vision and long-context sessions.
Official Qwen dense 27B vision-language release with Apache 2.0 weights, 262K native context, thinking controls and strong agentic coding benchmarks. Practical local path through Unsloth and LM Studio-compatible GGUF artifacts.
Gemma 4 MoE flagship-for-workstations: 26B total with ~4B active parameters. 256K context and excellent quality-per-watt for local inference. Apache 2.0.
PrismML Apache 2.0 ternary Qwen3.8-27B derivative with official GGUF and MLX paths. The PQ2_0 pack is 7.21GB, PTQ1_0 is 5.95GB, and custom llama.cpp/MLX kernels target laptop-class local inference.
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.
Liquid AI hybrid model built for on-device assistants. 8.3B total / 1.5B active, 128K context, tool use, GGUF, ONNX, MLX, llama.cpp and LM Studio support. Open-weight under LFM 1.0.
Established 14B Qwen 3 model for reasoning, coding and chat. Its Q4 build is a tight fit on many 16GB machines, so context length and system headroom matter.
IBM Granite 4.2 8B instruct model with Apache 2.0 weights, 128K context, thinking-mode chat template, tool calling and practical GGUF plus MLX paths for everyday local machines.
The shared LocalClaw engine first rejects hosted-only, excluded and oversized records. It reserves system and 8k-context headroom, labels comfortable, good and tight fits, then ranks the remaining models by hardware fit, use case, catalogue capability ratings, runtime and freshness. Community stars are never included. This is practical guidance, not a standardized third-party benchmark.
This guide is about local AI fit, not live pricing. Prices and availability change. An Amazon link may be an affiliate link that supports LocalClaw at no extra cost. Confirm the exact memory and storage on Amazon before ordering.