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

DominikBucko/qwen38-flash-next-2x3090

new

Qwen3.8-Flash-Next on 2× RTX 3090: with 128 GB RAM up to 4,191 tok/s prefill · 111.5 tok/s decode (131K prompt), full 256K window at 2,865 tok/s; with 64 GB RAM 3,410 tok/s prefill · 84 tok/s decode. New: opt-in uncensored mode (runtime abliteration, no new weights).

256k-contextcpu-offloadingdual-gpufp8int4llm-inferencelocal-llmmoe
Velocity score
0.00/ 10
[STARS]
69
[FORKS]
8
[CONTRIBUTORS]
2
[LAST_COMMIT]
1mo ago
OPEN_ON_GITHUB
Velocity class: new
Is DominikBucko/qwen38-flash-next-2x3090 still actively maintained?
[VR]

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

Score breakdown
363/ 1000
inference · DominikBucko/qwen38-flash-next-2x3090
Velocity50%
Adoption30%
Maintenance15%
Community5%
[CODE_GROWTH]
224
[INSTALL_VEL]
499
[ACTIVITY]
585
[COMMUNITY_SIGNAL]
279

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

LIVE──────── · ──:──:── UTCabout