Apple silicon · 64 GB
32B models with long context or 70B Q4 with conservative headroom.
Qwen3.8 Flash Next REAP-288
The highest listed result may be a tight or offloaded fit. For daily use, prefer the first result marked Bequem and keep context modest.
MLX LM
Native Apple silicon inference, experimentation and fine-tuning. Only for Apple silicon. Use an MLX-converted model and tune KV cache size for long contexts. The bundled mlx_lm.server is an OpenAI-compatible HTTP endpoint (default 127.0.0.1:8080), but upstream warns it implements only basic security checks and is not recommended for production.
Leitfaden öffnenRepräsentative Open-Weight-Modelle
Qwen3.8 Flash Next REAP-288
- Geschätzter Speicher
- ~40.57 GB
- Kontext
- 7.6K recommended on measured 48 GB Mac
Llama 3.1 70B
- Geschätzter Speicher
- ~46 GB
- Kontext
- 128K
Qwen3.6 35B-A3B
- Geschätzter Speicher
- ~25 GB
- Kontext
- 262K native
Qwen3 32B
- Geschätzter Speicher
- ~24.5 GB
- Kontext
- 32K+
Qwen3 30B-A3B
- Geschätzter Speicher
- ~22.5 GB
- Kontext
- 32K+
Qwen3.6 27B
- Geschätzter Speicher
- ~18.5 GB
- Kontext
- 262K native
Fit is based on estimated total model memory. Driver support, KV cache, multimodal projectors, concurrency, and desktop applications can all reduce available headroom. Current fit: Qwen3.8 Flash Next REAP-288 (Knapp), Llama 3.1 70B (Knapp), Qwen3.6 35B-A3B (Bequem), Qwen3 32B (Bequem), Qwen3 30B-A3B (Bequem), Qwen3.6 27B (Bequem).