llamaperf

DeepSeek V4 Flash 284B (13B active)

on 4× NVIDIA CMP 170HX 64GB (unlocked) · llama.cpp · 1,000,000 ctx

NVIDIA hardware
Sep 7, 2026
Throughput
29.0 t/s gen · 450.0 tokens/s prompt processing (prefill)Prompt processing measures input prefill speed; it does not tell you the time to first token.
Quant
Q4_K_XL
VRAM reported
64 GB

Summary

User reports testing multiple models on 4x CMP 170HX 64GB cards, including DeepSeek V4-Flash 0731 with a Q4_K_XL quant, 13B active MoE, and 1M context, plain no-spec. The cards are cut-down A100 mining cards with 64GB each, PCIe Gen2 x4, and no NVLink. Other models tested include gpt-oss-120B, Qwen3.6-35B-A3B, GLM-4.5-Air, and MiniMax-M2.7.