Home / Models / OLMo 2 13B Instruct / NVIDIA RTX 5000 16 GB
Can OLMo 2 13B Instruct run on NVIDIA RTX 5000 16 GB?
Yes. Calculated memory fit: OLMo 2 13B Instruct can run entirely in this GPU’s usable VRAM at one or more supported quantizations.
Can it run?
- Can it run?
- Yes, full GPU fit (calculated estimate).
- Full GPU fit?
- Yes
- Model
- OLMo 2 13B Instruct · 14B
- GPU
- NVIDIA RTX 5000 16 GB · 16 GB advertised
Memory calculation
Breakdown for Q4 at 4K context, batch size 1. Calculator v1.0.0.
| Model weights | 8.0 GB |
|---|---|
| KV cache | 3.1 GB |
| Runtime reserve | 0.9 GB |
| Safety margin | 0.5 GB |
| Required (estimated) | 12.6 GB |
| GPU usable VRAM | 14.4 GB |
Result: FITS IN VRAM
Quantization table
| Quantization | 2K | 4K |
|---|---|---|
| BF16 | Offload | Offload |
| FP16 | Offload | Offload |
| Q3 | Fits | Fits |
| Q4 | Fits | Fits |
| Q5 | Fits | Fits |
| Q6 | Offload | Offload |
| Q8 | Offload | Offload |
What fits entirely in VRAM?
- Q3 at 2K context
- Q3 at 4K context
- Q4 at 2K context
- Q4 at 4K context
- Q5 at 2K context
- Q5 at 4K context
What requires RAM offload?
Offload is shown only when the model does not fully fit in usable VRAM but stays within the modeled offload allowance.
Available graphics cards
These SKUs use this GPU chip. Amazon CTAs appear only for EXACT/HIGH matches. Absence of a price does not change the compatibility result above.
HP 5JH81AA graphics card NVIDIA Quadro RTX 5000 16 GB GDDR6
16 GB · Amazon EXACT
$602.99
Check price on Amazon
Fujitsu S26361-F2222-L505 graphics card NVIDIA Quadro RTX 5000 16 GB GDDR6
16 GB · Amazon unmatched
Sources
Model: official config allenai/OLMo-2-1124-13B-Instruct (main). GPU/product specs: Icecat. Compatibility: RigForAI calculator v1.0.0 estimated VRAM · Q8 at 4K: CPU_RAM_OFFLOAD_REQUIRED. Amazon: affiliate commerce match, not a spec source.