basecompute/gemma-4-E4B-it-BaseQuant-V1
Updated • 2
Prabod
prabodbc
AI & ML interests
None yet
Recent Activity
updated a model about 15 hours ago
basecompute/gemma-4-E4B-it-BaseQuant-V1 liked a model about 15 hours ago
basecompute/Qwen3.8-27B-BaseQuant-V1 upvoted an article about 24 hours ago
15% More Accurate Than Unsloth: Qwen-3.8-27B Quants for Local AgentsOrganizations
updated a
model about 15 hours ago
liked a
model about 15 hours ago
upvoted an article about 24 hours ago
Article
15% More Accurate Than Unsloth: Qwen-3.8-27B Quants for Local Agents
basecompute
• • 3 updated a
model about 24 hours ago
published an article 1 day ago
Article
15% More Accurate Than Unsloth: Qwen-3.8-27B Quants for Local Agents
basecompute
• • 3 published a
dataset 1 day ago
updated a
dataset 1 day ago
published 2
models 1 day ago
Q4: add the MTP drafting-vocabulary ranking (mtp.draft_rank), weights unchanged
#3 opened 3 days ago
by 
prabodbc
Q4: add the MTP drafting-vocabulary ranking (mtp.draft_rank), weights unchanged
#2 opened 3 days ago
by prabodbc
Re-convert with the Qwen MTP head (header.speculator): basertd --speculate mtp-head
#2 opened about 1 month ago
by prabodbc
Re-convert with the Qwen MTP head (header.speculator): basertd --speculate mtp-head
#1 opened about 1 month ago
by prabodbc
Re-convert with the Qwen MTP head (header.speculator): basertd --speculate mtp-head
#1 opened about 1 month ago
by prabodbc
Re-convert with the Qwen MTP head (header.speculator): basertd --speculate mtp-head
#1 opened about 1 month ago
by prabodbc
Re-convert with the Qwen MTP head (header.speculator): basertd --speculate mtp-head
#1 opened about 1 month ago
by prabodbc
Re-convert with the Qwen MTP head (header.speculator): basertd --speculate mtp-head
#1 opened about 1 month ago
by prabodbc
published an article 14 days ago
Article
Introducing Superfluid: the local-AI native LLM server for multi-agent inference
basecompute
• • 3 updated a
model 22 days ago