llamaperf

Qwen3.6 35B (3B active)

on NVIDIA GTX 1080 Ti · llama.cpp

Tone: mixedNVIDIA hardware
Nov 7, 2026
Throughput
7-10 t/s gen
Quant
Q4_K_M (GGUF)
System RAM
32 GB
VRAM reported
11 GB

Use cases

codingagentic

Summary

User asks which model to use as a coding builder agent on a GTX 1080 Ti 11GB with 32GB RAM, running llama.cpp with the Vulkan backend. They report Qwen3.6 35B A3B UD Q4_K_M at about 7 to 10 t/s on a few small tasks, and Qwen3.5-9B UD Q4_K_XL with MTP at about 25 to 30 t/s but not usable as a builder agent. They also tried Sharp Spark X2.5 4B Q6_K_XL, which overthinks, and Sharp Spark X2.6 4B Q6_K_XL, which is fine for simple tasks but not real work. They want 100k to 128k context and note CUDA is unstable on the 1080 Ti.

Compare this run

Medians of plain runs: one device, one request, no speculative decoding, the whole model in the device's memory. The report above is one setup, so read it beside them and not as one of them.

Qwen3.6 35B · 3B active at 4-bit by hardware

Bars are medians on one scale, 0 to 215.1 tokens/s. Each dot is one run and opens its report. Press ▶ to watch text arrive at a row's speed.

Models most run on the NVIDIA GTX 1080 Ti

Bars are medians on one scale, 0 to 62.0 tokens/s. Press ▶ to watch text arrive at a row's speed.

Everything reported on the NVIDIA GTX 1080 Ti →Every Qwen3.6 report →Estimate Qwen3.6 on this card →