Measured on the RTX 4080 SUPER
| Model · quant | Median tok/s | Context | Measured during | Sample |
|---|---|---|---|---|
| Dolphin3.0 R1 Mistral 24B Q3_K_S |
41 t/s | 18K | real use | n=4 · 1 machine |
| Qwen3.8-27B IQ3_XXS |
12 t/s | 50K | real use | n=3 · 1 machine |
| Qwen3 VL 8B Instruct Abliterated Q8_0 |
63 t/s | 25K | real use | n=2 · 1 machine |
Medians of real, opt-in benchmark telemetry from TurboLLM installs on this GPU — not a spec sheet, not an estimate. Every row shows its own sample size; small samples are labeled rather than hidden. Auto-tune sweep rows are measured on an idle machine with a cold cache; real use rows are measured during actual chat, gateway and coding traffic. The two are never averaged together. Context is the largest window that configuration was actually run at, not a theoretical maximum.
How TurboLLM fits a model to this card
Load any model and TurboLLM benchmarks it on your own RTX 4080 SUPER, storing the measured tokens/sec in the model list — the same measurements that, with your consent, become rows in the table above. Before you download, every quant gets a VRAM-fit verdict against your real free VRAM, including KV-cache growth at your chosen context. Flip the auto-fit toggle and it picks the GPU-layer count and, for Mixture-of-Experts models, the expert-offload split — and it decides fit by measuring host-memory spill directly, because used-VRAM alone silently reads as a clean fit while gigabytes run from system RAM. Details in the auto-tune docs.
This page exists because TurboLLM users opted into anonymous benchmark sharing. Turn it on in Settings and your measurements join the dataset — no account, no identity, no prompt content, just the model, the quant, the hardware and the speed. The more people share, the better every one of these pages gets.
FAQ
What LLMs can you actually run on the RTX 4080 SUPER?
TurboLLM users on the RTX 4080 SUPER have benchmarked 3 model/quant configurations across 2 machines, on 16 GB of VRAM. The fastest measured so far is Qwen3 VL 8B Instruct Abliterated at Q8_0, with a median of 63 tokens/sec. Every figure on this page comes from real runs on this card, with its sample size shown — nothing is extrapolated from a different GPU.
How fast is Qwen3 VL 8B Instruct Abliterated on the RTX 4080 SUPER?
Median 63 tokens/sec at Q8_0, from 2 runs across 1 machine running TurboLLM. Your own figure depends on context length, quant and settings, which is why TurboLLM re-measures on your machine every time you load a model instead of quoting someone else's number.
Where do these numbers come from?
Opt-in, anonymous benchmark telemetry from TurboLLM installs — the same measurements the app shows you locally after a load. They are aggregated over a 90-day window and published with per-row sample sizes. Auto-tune sweeps (idle machine, cold cache) are kept separate from measurements taken during real chat, gateway and coding traffic, so a best-case number is never mixed into a real-world one.
Do I need to install CUDA, ROCm or Python to use the RTX 4080 SUPER?
No. npx turbollm detects your GPU and auto-provisions a matching prebuilt llama-server — no toolkit, no Python environment, no compiler. Community forks are available too, from the engines catalog.
Run it on your RTX 4080 SUPER
One command: it detects your GPU, provisions a matching engine, and opens the UI. Already have GGUF files in an LM Studio folder? TurboLLM indexes them in place — no re-download. New here? Start with Install & first run and Quantization explained, or browse the full model hub.