LocalMaxxing
Models
Leaderboard
Evals
Rentals
API
Submit
Models
Leaderboard
Evals
Rentals
API Docs
Models
meta-llama
Llama-3.1-70B
Total runs
Highest
Median
Lowest
Benchmarks
Evals
Benchmark Results
Submit benchmark
Any size
< 3B
3B
7B
13B
30B
70B
110B+
Advanced filters
1
#
Hardware
Engine · Quant
Ctx
tok/s out
prefill
tok/s total
TTFT ms
VRAM GB
Llama-3.1-70B (71B) — LocalMaxxing