← EVENT LIBRARY / Infrastructure

JustFit serves a 200K-token model context on a 24 GiB MacBook

JustFit combines compressed KV execution, component swapping and state-preserving serving transitions in an MLX runtime. On a 24 GiB M4 Pro MacBook, Qwen3.8-27B MXFP4 completes 196K input tokens plus 16K output tokens in three runs. That raises completed single-request context 6.93x over the stated mlx-vlm baseline. Extreme-context runs take about 103 minutes, so the result establishes capacity more than interactive speed.

Imported from the existing research archive. Migration preserves the recorded judgment and is not a fresh verification.

What this means for you

For local-agent teams, memory scheduling can unlock long sessions without changing model-weight quantization. The practical use is asynchronous ingestion with prefix reuse, not repeated cold 200K prompts. Reproduce the branch on your own hardware before treating the reported boundary as a deployment target.

FRONTIER WATCH

Public artifacts and validated results are different.

The recorded fact is the public work and its artifacts. Author-reported outcomes do not establish independent reproduction. Next checks include usable code, task conditions and third-party validation.

Evidence & related material

Background · Historical record, not rechecked

JustFit combines compressed KV execution, component swapping and state-preserving serving transitions in an MLX runtime. On a 24 GiB M4 Pro MacBook, Qwen3.8-27B MXFP4 completes 196K input tokens plus 16K output tokens in three runs. That raises completed single-request context 6.93x over the stated mlx-vlm baseline. Extreme-context runs take about 103 minutes, so the result establishes capacity more than interactive speed.

Technical details & scores
Hardware 24 GiB M4 Pro MacBook
Model Qwen3.8-27B MXFP4
Capacity 196,608 input plus 16,384 output tokens; 212,992 completed positions
Baseline Delta 6.93x completed single-request context over mlx-vlm baseline
Speed about 48 minutes cold prefill; 4.99 tok/s at the limit; about 103 minutes total
Reproducibility public evolving branch; exact historical environments incomplete
Technical impact 4
Engineering value 4
Adoption signal 1
Maturity 2
Verification cost 3
Risk 2