vram.wiki
My space Add your setup
Full directory
DISCOVER BY GPU

Setups running on
RTX 2080 Ti.

Every published setup that reports this GPU, with its models, quantization, runtime and reported results. Use the directory filters below to narrow by capacity, model or runtime.

1documented use
on this GPU
Sort by
Compare
Capacity range
Exact reported VRAM
Practice
Model
Quantization
Context length
Reported speed
Runtime
Tools / workflow (harness)
Record origin
EXPLORE BY CAPACITY

Start with your machine.

Capacity is the reported total for this setup. Multi-GPU and unified-memory layouts can behave differently.

8 GB or lessLaptops, iGPUs and modest cards9–12 GBEntry-level local inference13–16 GBCurrent mid-range cards17–20 GBRX 7900 XT and compact pro cards21–24 GB3090, 4090 and 7900 XTX class25–32 GB5090 and workstation cards33–48 GBWorkstation and multi-GPU setups49–96 GBLarge multi-GPU and datacenter setups97 GB+Unified memory, servers and clusters
1 resultsEvery record keeps its origin visible.
Hybrid orchestrationCommunity snapshot2026-09
27B reasoning model on 2x RTX 2080 Ti (NVFP4, vLLM) for agentic orchestration

Qwen3.8-27B (NVFP4 W4A16 + FP8 KV) served on 2x RTX 2080 Ti 22GB over NVLink via a vLLM TP2 fork. 196K context cap, MTP K=3, prefix caching on. Feeds a 1-orchestrator + 7-worker harness: ~1227 tok/s prefill and ~29 tok/s decode solo at 65K, ~192 tok/s aggregate at 8-way. Rejected AWQ/FP8 weights (72% EOS failure), ExLlamaV3 (3-6x slower), and PP=2 (infeasible on 2 GPUs).

33–48 GBunsloth_Qwen3.8-27B-NVFP4vLLMRTX 2080 Ti
Hybrid↑ 0