MODEL COMPARISON

Tradeoffs, side by side.

Select up to four models. These signals narrow the shortlist; benchmark on your own workload before deploying.

Signalmradermacher/Llama-3.3-8B-Thinking-Gemini-Flash-11000x-128k-i1-GGUF
TaskUnknown
Parameters8.0B
Minimum VRAM8 GB
Recommended VRAM12 GB
Licenseapache-2.0
Commercial signalLIKELY_ALLOWED
Downloads2,491
Likes3
SourceHugging Face ↗