HamsterResearch Enables Full Qwen Model on M4 Max With 37GB RAM via Streaming
EyalToledano · x · 2026-08-30
HamsterResearch has implemented dynamic quantization and expert streaming using pMLX, allowing users to download a full precision model once while the engine adapts to specific tasks on the fly based on context needs and speed limits.
Benchmarks on M4 Max show Qwen3.8-Flash-Next running with full experts (no pruning) using only 37GB of memory at 40 tok/s. This was achieved by storing 60% of experts on disk and streaming them to memory on-demand, eliminating the need to manage multiple quant versions.
Related event: Optimization Lets Qwen3.8-Flash-Next Run on 37GB VRAM(4 posts)→
More from Infra
- Perplexity's new embedding models: index with a 9B model, search with 0.6B — antoine_chaffin · 2026-10-15
- Unsloth ships GGUF quants for Nemotron 3.5: Bolt-74B runs in 24GB RAM — danielhanchen · 2026-10-15
- vLLM-Omni ships Day-0 serving for FLUX 3 Image Klein with BF16, FP8, NVFP4 support — vllm_project · 2026-10-15
- NVIDIA's Nemotron 3.5 Super VL lands training and inference support on Applied Compute — ypatil125 · 2026-10-15
- CoreWeave bond yield tops 16% as loans outlast customer contracts by ~2 years — tengyanAI · 2026-10-15
- AGI isn't real until H100 hourly rates jump 10x, argues compute economics essay — corbtt · 2026-10-15