llamaperf

NVIDIA RTX 4060 Ti 8GB vs NVIDIA RTX 5070 for local LLMs

3 reports on the NVIDIA RTX 4060 Ti 8GB and 8 on the NVIDIA RTX 5070

Which is faster for local LLMs?

Nobody has reported the same model at the same quant on both cards yet, so there's no measured head-to-head. Memory bandwidth, which caps how fast a card can write, is 2.3x higher on the NVIDIA RTX 5070 (288 GB/s on the NVIDIA RTX 4060 Ti 8GB, 672 on the NVIDIA RTX 5070). The estimates below compare them on the models people run most.

NVIDIA RTX 4060 Ti 8GB
Memory
8GB
Memory bandwidth
288 GB/s
FP16 compute
88 TFLOPS
Reports
3
NVIDIA RTX 5070
Memory
12GB
Memory bandwidth
672 GB/s
FP16 compute
124 TFLOPS
Reports
8

Estimated by the calculator

The quant the calculator recommends for each card and its estimated speed at a 32,768-token context with 32 GB of system RAM, from memory bandwidth and the model's shape.

ModelNVIDIA RTX 4060 Ti 8GBNVIDIA RTX 5070
Qwen3.8 27B1.6 t/sQ6_K, layers on CPU1.8 t/sQ8_0, layers on CPU
Qwen3.8 125B · 6B activedoesn't fit at these settingsdoesn't fit at these settings
DeepSeek V4 Flash 284B · 13B activedoesn't fit at these settingsdoesn't fit at these settings
Qwen3.6 35B · 3B active14.7 t/sQ5_K_M, experts in RAM14.5 t/sQ6_K, experts in RAM
Qwen3.6 27B1.6 t/sQ6_K, layers on CPU1.8 t/sQ8_0, layers on CPU
Gemma 4 26B · 4B active9.4 t/sQ6_K, experts in RAM109.7 t/sQ2_K

Change the context, RAM or model in the calculator: NVIDIA RTX 4060 Ti 8GB · NVIDIA RTX 5070

Every report on each card, with its source: NVIDIA RTX 4060 Ti 8GB · NVIDIA RTX 5070

More comparisons