llamaperf

Qwen3.6 35B (3B active) Opus distill, abliterated

on 2× NVIDIA RTX 3080 10GB · llama.cpp · 124,000 ctx

Tone: mixedNVIDIA hardware
Nov 19, 2026
Throughput
85.0 t/s gen · 2900.0 tokens/s prompt processing (prefill)Prompt processing is how fast the input is read, not how long you wait for the first word. How to measure time to first token.
Quant
i1-IQ3_XXS (GGUF)
System RAM
32 GB
VRAM reported
18 GB

Use cases

codingagentictool-use

Summary

User reports Qwen3.6 35B-A3B (Opus distill, abliterated, i1-IQ3_XXS) at about 85 t/s generation and about 2900 t/s prompt processing on an RTX 3080 10GB plus RTX 2070 Super 8GB, with 124k context. Setup is llama.cpp (CUDA) with opencode; the model fits fully in VRAM. Generation drops to about 68 t/s at 30k context. User finds the speed fine but the output quality poor and suspects the 3-bit quant. A Qwen3-Coder 30B-A3B abliterated at i1-IQ4_XS ran about 33 t/s at 64k, but at 128k the KV cache pushed experts to CPU and it fell to about 17 t/s. Qwen3.5 35B abliterated on Ollama was fast but the code quality was not great. User asks for a middle ground with at least 90k context for agentic coding in C++ and Python.

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.

Everything reported on the NVIDIA RTX 3080 10GB →Every Qwen3.6 report →Estimate Qwen3.6 on this card →