Home / Models / Vicuna 13B v1.5 / NVIDIA RTX 2070 SUPER 8 GB

Calculated memory fit · not a benchmark

Can Vicuna 13B v1.5 run on NVIDIA RTX 2070 SUPER 8 GB?

Can it run? Yes, with CPU/RAM offload. Full GPU fit? No.

Can it run?

Can it run?
Yes, with CPU/RAM offload. This is not equivalent to full-GPU inference.
Full GPU fit?
No
Model
Vicuna 13B v1.5 · 13B
GPU
NVIDIA RTX 2070 SUPER 8 GB · 8 GB advertised

Memory calculation

Breakdown for Q4 at 4K context, batch size 1. Calculator v1.0.0.

Model weights7.6 GB
KV cache3.1 GB
Runtime reserve0.9 GB
Safety margin0.5 GB
Required (estimated)12.1 GB
GPU usable VRAM7.2 GB

Result: CPU RAM OFFLOAD REQUIRED

Quantization table

Quantization2K4K
BF16NoNo
FP16NoNo
Q3OffloadOffload
Q4OffloadOffload
Q5OffloadOffload
Q6OffloadOffload
Q8OffloadOffload

What fits entirely in VRAM?

No calculated full-VRAM fit at the evaluated quantizations and context lengths.

What requires RAM offload?

Weights may run with CPU/RAM offload. That is not equivalent to full-GPU inference. RigForAI does not estimate tokens/sec in this release.

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 lmsys/vicuna-13b-v1.5 (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.