Article
15% More Accurate Than Unsloth: Qwen-3.8-27B Quants for Local Agents
basecompute
• • 5
Fabian Waschkowski
fabian-basecompute
AI & ML interests
None yet
Recent Activity
upvoted an article 2 days ago
15% More Accurate Than Unsloth: Qwen-3.8-27B Quants for Local Agents published an article 3 days ago
15% More Accurate Than Unsloth: Qwen-3.8-27B Quants for Local Agents upvoted an article 16 days ago
Introducing Superfluid: the local-AI native LLM server for multi-agent inferenceOrganizations
upvoted an article 2 days ago
published an article 3 days ago
Article
15% More Accurate Than Unsloth: Qwen-3.8-27B Quants for Local Agents
basecompute
• • 5 upvoted an article 16 days ago
Article
Introducing Superfluid: the local-AI native LLM server for multi-agent inference
basecompute
• • 3 published an article 16 days ago
Article
Introducing Superfluid: the local-AI native LLM server for multi-agent inference
basecompute
• • 3 upvoted an article about 1 month ago
Article
Compute:Arena / Measuring Local Inference Across Models, Quants, Chips, and Runtimes
basecompute
• • 6 updated a
model about 2 months ago
updated a
model 2 months ago
upvoted an article 2 months ago
Article
Base Optimization Stack: From Open Weights to Frontier On-Device Inference Speed
basecompute
• • 5 published an article 2 months ago
Article
Base Optimization Stack: From Open Weights to Frontier On-Device Inference Speed
basecompute
• • 5 What profile did these models use?
1
#1 opened 2 months ago
by 
bangbangkido
published a
model 2 months ago
upvoted an article 4 months ago
Article
BaseRT: Best-in-Class LLM Inference on Apple Silicon via Native Metal
basecompute
• • 5 published an article 4 months ago
Article
BaseRT: Best-in-Class LLM Inference on Apple Silicon via Native Metal
basecompute
• • 5