GPU Util — % utilisation
GPU Temp — °C die
Unified — GB of 128 · 8 GB guard
Throughput — tok / second
TTFT — ms · first token
throughput & first-token from the active lane
Active Lane idle no warm brain
OpenRouter $0.00 spend · session

← Models

quant · finance

finance-chat-gguf

base AdaptLLM/finance-chat · license llama2 ·recommended F16

▶ Try in chat ＋ Send to compare
Quant economics quality × speed per build
Variant Perplexity tok/s FinanceBench (n=50, numeric_match)
Q4_K_M 6.221 31.1 0.14
Q5_K_M 6.164 26.9 0.16
Q6_K 6.147 23.9 0.16
Q8_0 6.137 8.9 0.18
F16 sweet spot 6.137 11.5 0.18

Perplexity lower = better; tok/s measured on the DGX Spark (GB10, 128 GB unified).

Efficiency curve quality index × tok/s