Home / Models / Phi-3 Medium 128K Instruct / NVIDIA RTX A2000 12 GB

Calculated memory fit · not a benchmark

Can Phi-3 Medium 128K Instruct run on NVIDIA RTX A2000 12 GB?

Yes. Calculated memory fit: Phi-3 Medium 128K 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
Phi-3 Medium 128K Instruct · 14B
GPU
NVIDIA RTX A2000 12 GB · 12 GB advertised

Memory calculation

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

Model weights8.2 GB
KV cache1.6 GB
Runtime reserve0.9 GB
Safety margin0.5 GB
Required (estimated)11.2 GB
GPU usable VRAM10.8 GB

Result: FITS WITH LIMITED CONTEXT

Quantization table

Quantization2K4K8K16K32K64K128K
BF16OffloadOffloadOffloadOffloadOffloadOffloadOffload
FP16OffloadOffloadOffloadOffloadOffloadOffloadOffload
Q3FitsFitsFitsLimited contextLimited contextLimited contextLimited context
Q4FitsFitsLimited contextLimited contextLimited contextLimited contextLimited context
Q5OffloadOffloadOffloadOffloadOffloadOffloadOffload
Q6OffloadOffloadOffloadOffloadOffloadOffloadOffload
Q8OffloadOffloadOffloadOffloadOffloadOffloadOffload

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

DELL

DELL NVIDIA A2000 RTX A2000 12 GB GDDR6

12 GB · Amazon unmatched

Check availability
DELL

DELL NVIDIA RTX A2000 12GB GDDR6

12 GB · Amazon unmatched

Check availability

Sources

Model: official config microsoft/Phi-3-medium-128k-instruct (main). GPU/product specs: Icecat. Compatibility: RigForAI calculator v1.0.0 estimated VRAM · Q8 at 8K: CPU_RAM_OFFLOAD_REQUIRED. Amazon: affiliate commerce match, not a spec source.