⌘K
← All GPUs

RTX A6000

NVIDIA · Pro GPU · 2021

48 GB VRAM
768 GB/s
300W TDP
$4,500 MSRP
Check Latest Price
$4,500 MSRP
Check Price on Amazon →

We earn a commission from qualifying purchases · Prices may vary

Performance Benchmarks

Image Generation all sourced rows →

ModelMetricValueSource
SDXL Turbo FP16 images per minute 35 img/min
ComfyUI · 2025-06-01
Independent benchmark Puget Systems Hardware Testing ↗

LLM Inference all sourced rows →

ModelMetricValueSource
Llama-3-70B Q4
48GB VRAM — editorial estimate pending article-level source verification
tokens per second 22 tok/s est
llama.cpp · 2025-06-01
Estimated Puget Systems Hardware Testing ↗
Llama-3-8B Q4_K_M
Token generation: average speed generating 1024 tokens, batch 1, -ngl 10000 full offload, RunPod; model is Meta-Llama-3-8B (not 3.1); 2024-era build — cross-check: same repo's 4090=127.74 vs myaihardware b3500 125 (+2%); tested_at = repo last push containing Llama-3 results (exact run date unstated)
tokens per second 102.2 tok/s
llama.cpp (CUDA, LLAMA_CUBLAS build) · 2024-05-13
Reproducible community XiongjieDai Multi-GPU llama.cpp Benchmarks ↗
Qwen3-8B Q4_K_XL
Token generation: 16K context, batch 1, Ubuntu 24.04, on-hardware lab measurement
tokens per second 64.3 tok/s
llama.cpp llama-bench, CUDA 12.8 · 2025-12-09
Unverified community Hardware Corner LLM GPU Rankings ↗

Full Specifications

Vram gb
48 GB
Vram type
GDDR6
Memory bus
384 bit
Memory bandwidth gbps
768 GB/s
Tdp watts
300 W
Cuda cores
10752
Pcie interface
PCIe 4.0 x16
Architecture
Ampere

Related GPUs

Guides & Tools

CompareAIHardware.com participates in the Amazon Associates program. As an Amazon Associate, we earn from qualifying purchases.