beam
beam
Discover
PulseActivityAnalyticsBest forMapOrgs
Niches
AgentsMCPRAGCoding AssistantsInference & ServingVector DBs
Personal
WatchlistCompareWeekly report
?
Sign in
magic link · no password
LIVE──────── · ──:──:── UTCabout
beam
beam
Discover
PulseActivityAnalyticsBest forMapOrgs
Niches
AgentsMCPRAGCoding AssistantsInference & ServingVector DBs
Personal
WatchlistCompareWeekly report
?
Sign in
magic link · no password
Back to Pulse
Tool profile

carloslfu/slotstream

stable

Run a 105 GB AI model on a Mac that can't hold it. Slotstream streams Qwen3.8-Flash-Next (125B mixture of experts) from your SSD and caches the busiest experts in memory, so it runs on Macs with 16 to 64 GB. One native Swift binary on MLX and Metal, no Python, offline. Works with Claude Code, Codex and Ollama or OpenAI clients.

apple-siliconclaude-codeinference-enginellmllm-inferencelocal-ailocal-llmmacos
Velocity score
0.22/ 10
[STARS]
390
[FORKS]
25
[CONTRIBUTORS]
3
[LAST_COMMIT]
6d ago
OPEN_ON_GITHUB
Velocity class: stable
Is carloslfu/slotstream still actively maintained?
[VR]

This tool is in the Velocity Report when it moves. Get the weekly numbers.

Score breakdown
511/ 1000
coding-assistants · carloslfu/slotstream
Velocity50%
Adoption30%
Maintenance15%
Community5%
[CODE_GROWTH]
518
[INSTALL_VEL]
500
[ACTIVITY]
561
[COMMUNITY_SIGNAL]
353

Terminal score: 0–1000 raw, weighted across 4 dimensions. Public score: 0–10 normalized (shown in the 30-day stars chart above).

LIVE──────── · ──:──:── UTCabout