Home / Models / Hermes 3 Llama 3.1 8B / NVIDIA RTX 5090 32 GB

Calculated memory fit · not a benchmark

Can Hermes 3 Llama 3.1 8B run on NVIDIA RTX 5090 32 GB?

Yes. Calculated memory fit: Hermes 3 Llama 3.1 8B 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
Hermes 3 Llama 3.1 8B · 8.0B
GPU
NVIDIA RTX 5090 32 GB · 32 GB advertised

Memory calculation

Breakdown for Q4 at 8K context, batch size 1. Calculator v1.0.0.

Model weights4.7 GB
KV cache1.0 GB
Runtime reserve0.7 GB
Safety margin0.4 GB
Required (estimated)6.8 GB
GPU usable VRAM28.8 GB

Result: FITS IN VRAM

Quantization table

Quantization2K4K8K16K32K64K128K
BF16FitsFitsFitsFitsFitsFitsLimited context
FP16FitsFitsFitsFitsFitsFitsLimited context
Q3FitsFitsFitsFitsFitsFitsFits
Q4FitsFitsFitsFitsFitsFitsFits
Q5FitsFitsFitsFitsFitsFitsFits
Q6FitsFitsFitsFitsFitsFitsFits
Q8FitsFitsFitsFitsFitsFitsFits

What fits entirely in VRAM?

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.

Check price on Amazon

Sources

Model: official config NousResearch/Hermes-3-Llama-3.1-8B (main). GPU/product specs: Icecat. Compatibility: RigForAI calculator v1.0.0 estimated VRAM · Q8 at 8K: FITS_IN_VRAM. Amazon: affiliate commerce match, not a spec source.