GeForce RTX 5080
16 GB GDDR7 · 960 GB/s · 360 W
RTX 5080 16 GB · 64 GB RAM → gpt-oss-20b
GPU · NVIDIA
RTX 5080 for local LLMs: which models run?
With 16 GB of VRAM and 960 GB/s of bandwidth, the RTX 5080 runs models up to about gpt-oss-20b entirely on the GPU.
- VRAM16 GB GDDR7
- Bandwidth960 GB/s
- Board power360 W
- ArchitectureBlackwell
Specifications
- VRAM
- 16 GB
- Memory type
- GDDR7
- Memory bus
- 256-bit
- Bandwidth
- 960 GB/s
- Board power
- 360 W
- Backends
- CUDA, Vulkan
- Interface
- PCIe 5.0 x16
- Released
- January 2025
- Segment
- Consumer
- FP16 compute
- Not available
Official specData updated 24 days agoSource: NVIDIA specifications
What the RTX 5080 runs
| gpt-oss-20bMXFP4 · 8K~13 GB · 176–215 tok/s measured | Excellent |
|---|---|
| Gemma 2 9B ITQ8_0 · 8K~12.7 GB · 58–81 tok/s estimate | Excellent |
| Qwen3 8BQ8_0 · 8K~10.5 GB · 68–95 tok/s estimate | Excellent |
| Llama 3.1 8B InstructQ8_0 · 8K~10.2 GB · 71–98 tok/s estimate | Excellent |
| DeepSeek R1 Distill Llama 8BQ8_0 · 8K~10.2 GB · 71–98 tok/s estimate | Excellent |
| Qwen2.5 7B InstructQ8_0 · 8K~9.2 GB · 77–107 tok/s estimate | Excellent |
| Mistral 7B Instruct v0.3Q8_0 · 8K~9.2 GB · 77–107 tok/s estimate | Excellent |
| Gemma 3 4B ITQ8_0 · 8K~5.4 GB · 128–192 tok/s estimate | Excellent |
| Qwen3 4BQ8_0 · 8K~6.2 GB · 114–170 tok/s estimate | Excellent |
| Phi-4 Mini Instruct 3.8BQ8_0 · 8K~6 GB · 123–181 tok/s estimate | Excellent |
| Llama 3.2 3B InstructQ8_0 · 8K~5.1 GB · 144–214 tok/s estimate | Excellent |
| Qwen3 1.7BQ8_0 · 8K~3.7 GB · 209–334 tok/s estimate | Excellent |
| Llama 3.2 1B InstructQ8_0 · 8K~2.5 GB · 342–539 tok/s estimate | Excellent |
| Qwen3 0.6BQ8_0 · 8K~2.5 GB · 315–578 tok/s estimate | Excellent |
| Mistral Small 3.2 24B InstructIQ4_XS · 8K~14.6 GB · 49–67 tok/s estimate | Compatible |
| Qwen3 14BQ6_K · 8K~14 GB · 51–70 tok/s estimate | Compatible |
| DeepSeek R1 Distill Qwen 14BQ6_K · 8K~14.3 GB · 49–69 tok/s estimate | Compatible |
| Qwen2.5 14B InstructQ6_K · 8K~14.3 GB · 49–69 tok/s estimate | Compatible |
| Phi-4 14BQ6_K · 8K~14.2 GB · 51–70 tok/s estimate | Compatible |
| Mistral Nemo 12B InstructQ8_0 · 8K~14.9 GB · 48–66 tok/s estimate | Compatible |
| Gemma 3 12B ITQ8_0 · 8K~14.1 GB · 49–68 tok/s estimate | Compatible |
| Qwen3 30B-A3BQ3_K_M · 8K~15.4 GB · 135–232 tok/s estimate | Compatible with limits |
| Gemma 3 27B ITQ3_K_M · 8K~15.3 GB · 44–63 tok/s estimate | Compatible with limits |
| Mixtral 8x7B InstructQ3_K_M · 8K~21.6 GB · 10–20 tok/s estimate | CPU/GPU offload |
| Qwen3 32BQ3_K_M · 8K~18.6 GB · 6–11 tok/s estimate | CPU/GPU offload |
| DeepSeek R1 Distill Qwen 32BQ3_K_M · 8K~18.5 GB · 6–12 tok/s estimate | CPU/GPU offload |
| Qwen2.5 32B InstructQ3_K_M · 8K~18.5 GB · 6–12 tok/s estimate | CPU/GPU offload |
| Qwen2.5 Coder 32B InstructQ3_K_M · 8K~18.5 GB · 6–12 tok/s estimate | CPU/GPU offload |
| QwQ 32BQ3_K_M · 8K~18.5 GB · 6–12 tok/s estimate | CPU/GPU offload |
| Qwen3 Coder 30B-A3B InstructQ3_K_M · 8K~16 GB · 82–171 tok/s estimate | CPU/GPU offload |
| Gemma 2 27B ITQ3_K_M · 8K~16.5 GB · 15–27 tok/s estimate | CPU/GPU offload |
| gpt-oss-120bMXFP4 · 8K~63.2 GB · 8.5–17 tok/s estimate | Possible but slow |
| Llama 4 Scout 17B-16E InstructQ3_K_M · 8K~55.7 GB · 3–5.5 tok/s estimate | Possible but slow |
| Qwen2.5 72B InstructQ3_K_M · 8K~38.2 GB · 0.9–1.7 tok/s estimate | Not recommended |
| Llama 3.3 70B InstructQ3_K_M · 8K~37 GB · 0.9–1.8 tok/s estimate | Not recommended |
| DeepSeek R1 Distill Llama 70BQ3_K_M · 8K~37 GB · 0.9–1.8 tok/s estimate | Not recommended |
| DeepSeek R1 (671B)Q8_0 · 8K~699 GB · No data | Incompatible |
| Qwen3 235B-A22BQ8_0 · 8K~247 GB · No data | Incompatible |
For each model, the highest-precision quantization that runs entirely in fast memory; otherwise the one with the best result. Speeds are ranges; "estimate" unless a benchmark exists for this exact hardware.
EstimateData updated 24 days agoSource: Run LLM Locally engine
Limits in plain words
16 GB of VRAM holds the weights and KV cache of models up to about gpt-oss-20b at Q4_K_M. Bigger models spill into system RAM and slow down sharply: generation speed is then limited by RAM bandwidth, not by the GPU.
Where to buy a RTX 5080
Prices and links follow the market you choose.
No current offer imported for this market: the link opens a marketplace search.
Frequently asked questions
Which LLMs can the RTX 5080 run?
Entirely on the GPU: Qwen3 30B-A3B (Q3_K_M), Gemma 3 27B IT (Q3_K_M), Mistral Small 3.2 24B Instruct (IQ4_XS), gpt-oss-20b (MXFP4), Qwen3 14B (Q6_K), DeepSeek R1 Distill Qwen 14B (Q6_K), Qwen2.5 14B Instruct (Q6_K), Phi-4 14B (Q6_K). Larger models need CPU/GPU offload.
Can the RTX 5080 run a 70B model?
Not recommended: a 70B model at Q4_K_M needs about 45.1 GB; the RTX 5080 has 16 GB.
How is the speed estimated?
Token generation reads every active weight once per token, so it is limited by memory bandwidth (960 GB/s here). We apply an efficiency range per backend and label the result as an estimate until real benchmarks exist.