50-90 t/s gen · 1500-2200 tokens/s prompt processing (prefill)Prompt processing measures input prefill speed; it does not tell you the time to first token.
Quant
Q6_K_XL (GGUF)
VRAM reported
48 GB
Use cases
coding
Summary
User reports reliable code generation and codebase ingestion with multi-token prediction enabled.
Setup uses 96 GB of total VRAM.