# GeForce RTX 4080 SUPER

> OnPrem World · https://onpremworld.com/en/hardware/rtx-4080-super · Last updated: 2026-10-14 · CC BY 4.0

16 GB of GDDR6X at 736 GB/s: quick with models up to about 24B at 4-bit, but the 16 GB capacity caps what you can load.

## Specifications

|  |  |
|---|---|
| Memory | 16 GB GDDR6X |
| Memory bandwidth | 736 GB/s |
| Power | 320 W |
| Launch | 2024-01 |
| Launch price | US$999 |
| Architecture | Ada Lovelace |
| Software | CUDA |

## What it can run (16 GB, 8K)

Estimates, not benchmarks. See the methodology.

| Model | Parameters | Best quant | Total | tok/s (est.) |
|---|---|---|---|---|
| Gemma 4 26B A4B IT | 25.2B | Q4_K_M | 15.7 GiB | 224 |
| Mistral Small 3.2 24B Instruct (2506) | 24B | Q4_K_M | 16.0 GiB | 35 |
| Magistral Small 1.2 (2509) | 24B | Q4_K_M | 16.0 GiB | 35 |
| Devstral Small 2 24B Instruct (2512) | 24B | Q4_K_M | 16.0 GiB | 35 |
| gpt-oss-20b | 21B | Q5_K_M | 15.3 GiB | 201 |
| Phi-4 (14B) | 14B | Q6_K | 13.3 GiB | 45 |
| Gemma 3 12B IT | 12B | Q8_0 | 13.8 GiB | 40 |
| Gemma 4 12B Unified IT | 11.95B | Q8_0 | 13.3 GiB | 41 |
| Qwen3.5-9B | 9B | Q8_0 | 10.1 GiB | 54 |
| Qwen3-8B | 8.2B | Q8_0 | 10.1 GiB | 59 |
| DeepSeek-R1-0528-Qwen3-8B | 8.19B | Q8_0 | 10.1 GiB | 59 |
| Llama 3.1 8B Instruct | 8B | Q8_0 | 9.8 GiB | 61 |
| Gemma 4 E4B IT | 8B | Q8_0 | 9.1 GiB | 61 |
| Llama 3.2 3B Instruct | 3.21B | FP16 | 7.7 GiB | 80 |
| Kimi K2.6 | 1000B | Doesn't fit | – | – |
| DeepSeek-R1-0528 (671B) | 671B | Doesn't fit | – | – |
| DeepSeek-V4-Flash | 284B | Doesn't fit | – | – |
| Qwen3.8-Flash-Next | 180B | Doesn't fit | – | – |
| Qwen3.5-122B-A10B | 122B | Doesn't fit | – | – |
| Mistral Small 4 119B (2603) | 119B | Doesn't fit | – | – |
| gpt-oss-120b | 117B | Doesn't fit | – | – |
| Llama 4 Scout 17B-16E Instruct | 109B | Doesn't fit | – | – |
| GLM-4.5-Air | 106B | Doesn't fit | – | – |
| Qwen3-Coder-Next (80B-A3B) | 80B | Doesn't fit | – | – |
| Llama 3.3 70B Instruct | 70B | Doesn't fit | – | – |
| Qwen3.5-35B-A3B | 35B | Doesn't fit | – | – |
| Qwen3.6-35B-A3B | 35B | Doesn't fit | – | – |
| Qwen3-32B | 32.8B | Doesn't fit | – | – |
| DeepSeek-R1-Distill-Qwen-32B | 32.76B | Doesn't fit | – | – |
| Gemma 4 31B IT | 30.7B | Doesn't fit | – | – |
| Qwen3-30B-A3B (2507) | 30.5B | Doesn't fit | – | – |
| Qwen3-Coder-30B-A3B-Instruct | 30.5B | Doesn't fit | – | – |
| GLM-4.7-Flash (30B-A3B) | 30B | Doesn't fit | – | – |
| Qwen3.5-27B | 27B | Doesn't fit | – | – |
| Qwen3.6-27B | 27B | Doesn't fit | – | – |
| Qwen3.8-27B | 27B | Doesn't fit | – | – |
| Gemma 3 27B IT | 27B | Doesn't fit | – | – |

## Prices

No prices recorded for this device yet.

## Frequently asked questions

### Which LLMs can the GeForce RTX 4080 SUPER run?

With 16 GB and an 8K context, the largest models that fit include: Gemma 4 26B A4B IT, Mistral Small 3.2 24B Instruct (2506), Magistral Small 1.2 (2509), Devstral Small 2 24B Instruct (2512), gpt-oss-20b. See the full table below.

### How fast is the GeForce RTX 4080 SUPER for local LLMs?

Generation speed is mostly set by memory bandwidth (736 GB/s). For Llama 3.1 8B Instruct at Q8_0, expect roughly 61 tokens/s; bigger models are slower.

### Can the GeForce RTX 4080 SUPER run 70B models?

Llama 3.3 70B Instruct does not fit on the GeForce RTX 4080 SUPER (16 GB), even at Q4_K_M with an 8K context.

## Sources

- https://www.nvidia.com/en-us/geforce/graphics-cards/40-series/rtx-4080-family/
- https://www.nvidia.com/en-us/geforce/news/geforce-rtx-4080-4070-ti-4070-super-gpu/
- https://nvidianews.nvidia.com/news/geforce-rtx-40-super-series
- https://en.wikipedia.org/wiki/List_of_Nvidia_graphics_processing_units