Can I Run OLMo 2 on NVIDIA GeForce RTX 5080?
Written by Jakub Rusinowski · Last updated September 29, 2026
Yes, but it's tight — OLMo 2 13B Instruct at Q4_K_M needs 15.8 GB at 8K context (8.3 GB weights + 7.5 GB KV cache/overhead), leaving ~0.2 GB of the NVIDIA GeForce RTX 5080's 16 GB, at ~61 tok/s (est.), with room for up to 4K context.
See what else this hardware can run →
or compare on Vast.ai from $0.35/hr (typical low · varies)
As an Amazon Associate we earn from qualifying purchases. Cloud GPU links are referral links — we may earn a commission at no extra cost to you.
NVIDIA GeForce RTX 5080 Specs
| VRAM | 16 GB |
| Memory Bandwidth | 960 GB/s |
OLMo 2 13B Instruct on the NVIDIA GeForce RTX 5080: VRAM by quantization
| Quant | VRAM needed | Fits 16 GB? | Max context | Whole PC |
|---|---|---|---|---|
| F16 | 34.9 GB | ✗ No | — | — |
| Q8_0 | 22.1 GB | ✗ No | — | — |
| Q6_K | 18.7 GB | ✗ No | — | — |
| Q5_K_M | 17.2 GB | ✗ No | — | — |
| Q4_K_M | 15.8 GB | ✓ Yes | 4K | — |
| Q3_K_M | 13.4 GB | ✓ Yes | 4K | — |
| Q2_K | 12 GB | ✓ Yes | 4K | — |
Assumes an 8K-token context with an f16 KV cache. A longer window needs more; a quantized KV cache needs less. “Max context” is the largest window that still fits in 16 GB. Figures are estimates from parameter count, quantization and memory bandwidth — the analyzer lets you tune KV-cache quant and context.
No compatible GPU? OLMo 2 13B Instruct on 24 GB of system RAM, CPU only: runs.
OLMo 2 Sizes That Fit the NVIDIA GeForce RTX 5080 (at 8K context)
| OLMo 2 13B Instruct | Q4_K_M · 15.8 GB at 8K context · ~61 tok/s (est.) |
| OLMo 2 7B Instruct | Q4_K_M · 9.5 GB at 8K context · ~97 tok/s (est.) |
At 2 hrs/day, buying (~$999) beats renting at $0.34/hr after about 4.1 years.
Affiliate links — we may earn a commission if you sign up, at no extra cost to you.
Cloud rates verified 2026-07 — estimates, and marketplace prices vary. Buying price is GPU MSRP only, not a full PC.
FAQ
Is the NVIDIA GeForce RTX 5080 enough to run OLMo 2 locally?
Yes, but it's tight — OLMo 2 13B Instruct at Q4_K_M needs 15.8 GB at 8K context (8.3 GB weights + 7.5 GB KV cache/overhead), leaving ~0.2 GB of the NVIDIA GeForce RTX 5080's 16 GB, at ~61 tok/s (est.), with room for up to 4K context.
What's the best OLMo 2 size for the NVIDIA GeForce RTX 5080?
OLMo 2 13B Instruct at Q4_K_M quantization needs 15.8 GB at 8K context (8.3 GB weights + 7.5 GB KV cache/overhead), estimated ~61 tokens/sec, up to 4K context.
Every OLMo 2 size on the NVIDIA GeForce RTX 5080
| Size | VRAM at 8K | Verdict | Speed |
|---|---|---|---|
| OLMo 2 13B Instruct | 15.8 GB | Runs | ~61 tok/s |
| OLMo 2 7B Instruct | 9.5 GB | Runs | ~97 tok/s |
OLMo 2 on Other GPUs
- OLMo 2 on NVIDIA GeForce RTX 5070 Ti
- OLMo 2 on NVIDIA GeForce RTX 5060 Ti 16GB
- OLMo 2 on NVIDIA GeForce RTX 4080 Super
- OLMo 2 on NVIDIA GeForce RTX 4080
- OLMo 2 on NVIDIA GeForce RTX 4070 Ti Super
Popular Models on the NVIDIA GeForce RTX 5080
- DeepSeek R1 on NVIDIA GeForce RTX 5080
- Qwen 3 on NVIDIA GeForce RTX 5080
- Qwen 2.5 Family on NVIDIA GeForce RTX 5080
VRAM Tier
Troubleshooting
- CUDA out of memory — why it happens and how to fix it
- Which GGUF quant should I download? (Q4 vs Q5 vs Q8)
Buying Guide
← Can I Run It? | OLMo 2 Model Page | NVIDIA GeForce RTX 5080 GPU Page | VRAM calculator | Check Your Hardware