← All GPUs
RTX 6000 Ada
NVIDIA · Pro GPU · 2023
Check Latest Price
$6,800 MSRP
Check Price on Amazon →
We earn a commission from qualifying purchases · Prices may vary
Performance Benchmarks
Image Generation all sourced rows →
| Model | Metric | Value | Source |
|---|---|---|---|
| SDXL Turbo FP16 | images per minute |
75
img/min
ComfyUI · 2025-06-01
|
Independent benchmark Puget Systems Hardware Testing ↗ |
|
Stable Diffusion 1.5
FP16 Standardized UL Procyon suite; same lab platform (ThreadRipper 7980X, driver 571.86); 1.477 s/image |
procyon image overall score |
4,230
score
UL Procyon AI Image Generation · 2025-01-29
|
Independent benchmark StorageReview GPU Reviews ↗ |
|
Stable Diffusion 1.5 INT8
INT8 Standardized UL Procyon suite; same lab platform (ThreadRipper 7980X, driver 571.86); 0.559 s/image |
procyon image overall score |
55,901
score
UL Procyon AI Image Generation · 2025-01-29
|
Independent benchmark StorageReview GPU Reviews ↗ |
|
Stable Diffusion XL
FP16 Standardized UL Procyon suite; same lab platform (ThreadRipper 7980X, driver 571.86); 12.323 s/image |
procyon image overall score |
3,043
score
UL Procyon AI Image Generation · 2025-01-29
|
Independent benchmark StorageReview GPU Reviews ↗ |
LLM Inference all sourced rows →
| Model | Metric | Value | Source |
|---|---|---|---|
|
Llama-2-13B
Standardized UL Procyon suite; same lab platform (ThreadRipper 7980X, driver 571.86); output rate 78.532 tok/s |
procyon text overall score |
3,957
score
UL Procyon AI Text Generation (TensorRT) · 2025-01-29
|
Independent benchmark StorageReview GPU Reviews ↗ |
|
Llama-3-70B
Q4 48GB VRAM — editorial estimate pending article-level source verification |
tokens per second |
35
tok/s
est llama.cpp · 2025-06-01
|
Estimated Puget Systems Hardware Testing ↗ |
|
Llama-3-8B
Standardized UL Procyon suite; same lab platform (ThreadRipper 7980X, driver 571.86); output rate 138.62 tok/s |
procyon text overall score |
4,026
score
UL Procyon AI Text Generation (TensorRT) · 2025-01-29
|
Independent benchmark StorageReview GPU Reviews ↗ |
|
Llama-3.1-8B
Q4_K_M Token generation: single user, batch 1, 4k context, mean of 3 runs |
tokens per second |
110
tok/s
llama.cpp b3500 (CUDA) · 2026-05-22
|
Unverified community MyAIHardware llama.cpp Benchmarks ↗ |
|
Llama-3.1-8B
Q4_K_M Prompt processing: 512-token prompt, batch 1, mean of 3 runs |
prompt tokens per second |
3,200
tok/s
llama.cpp b3500 (CUDA) · 2026-05-22
|
Unverified community MyAIHardware llama.cpp Benchmarks ↗ |
|
Mistral-7B
Standardized UL Procyon suite; same lab platform (ThreadRipper 7980X, driver 571.86); output rate 166.633 tok/s |
procyon text overall score |
4,255
score
UL Procyon AI Text Generation (TensorRT) · 2025-01-29
|
Independent benchmark StorageReview GPU Reviews ↗ |
|
Phi-3.5-mini
Standardized UL Procyon suite; same lab platform (ThreadRipper 7980X, driver 571.86); output rate 228.359 tok/s |
procyon text overall score |
4,508
score
UL Procyon AI Text Generation (TensorRT) · 2025-01-29
|
Independent benchmark StorageReview GPU Reviews ↗ |
|
Qwen3-8B
Q4_K_XL Token generation: 16K context, batch 1, Ubuntu 24.04, on-hardware lab measurement |
tokens per second |
98.7
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
960 GB/s
Tdp watts
300 W
Cuda cores
18176
Pcie interface
PCIe 4.0 x16
Architecture
Ada Lovelace
Related GPUs
Guides & Tools
CompareAIHardware.com participates in the Amazon Associates program. As an Amazon Associate, we earn from qualifying purchases.