AMD Radeon RX 6950 XT
GPU
16
GB
PERFORMANCE OVERVIEW
Model
Meta Llama 3.1 8B Instruct
Q4_K - Medium8.0B
DeepSeek R1 0528 Qwen3 8B
Q8_08.2B
Qwen2.5 14B Instruct
Q4_K - Medium14.8B
Prompt Speed
1024tokens/s
1122tokens/s
549tokens/s
Generation Speed
6.1tokens/s
5.2tokens/s
3.3tokens/s
Time to First Token
1.52sec
1.47sec
2.85sec
LocalScore
161
158
86
COMPARE MODELS
3 models tested
Select Models
Meta Llama 3.1 8B Instruct
Q4_K - Medium
Qwen2.5 14B Instruct
Q4_K - Medium
DeepSeek R1 0528 Qwen3 8B
Q8_0
