llama-3.3-70b-Instruct-4bit
9 workload results across 3 hardware configurations.
Fastest local config
19.1 decode tok/s
on 2x RTX 3090 (24GB) + AMD EPYC 7H12 64-Core Processor (128c) + 1008GB via llama.cpp (Q4_K_M). see full run
Local runs (9 workload results)
Runs from contributors' own machines via MLX, llama.cpp, vLLM, exllamav2, or ollama. Signed on the submitter's hardware.
2x RTX 3090 (24GB) + AMD EPYC 7H12 64-Core Processor (128c) + 1008GB
| Workload | Backend | Quant | decode tok/s | prefill tok/s | TTFT | Run |
|---|---|---|---|---|---|---|
| chat-short | llama.cpp@0.7.0-dev (build 1, commit f74e2fa) | Q4_K_M | 19.14tok/s | 415.4tok/s | 325ms | r_n93ukk0mkmm |
| chat-long | llama.cpp@0.7.0-dev (build 1, commit f74e2fa) | Q4_K_M | 18.69tok/s | 939.3tok/s | 3,366ms | r_n93ukk0mkmm |
| concurrent-decode | llama.cpp@0.7.0-dev (build 1, commit f74e2fa) | Q4_K_M | 19.00tok/s | no data | no data | r_n93ukk0mkmm |
| agent-trace | llama.cpp@0.7.0-dev (build 1, commit f74e2fa) | Q4_K_M | 18.85tok/s | 2,028.8tok/s | 1,037ms | r_n93ukk0mkmm |
A40 (45GB) + Intel(R) Xeon(R) Gold 6342 CPU @ 2.80GHz (48c) + 504GB
| Workload | Backend | Quant | decode tok/s | prefill tok/s | TTFT | Run |
|---|---|---|---|---|---|---|
| chat-short | llama.cpp@0.7.0-dev (build 1, commit ceefd16) | Q4_K_M | 12.99tok/s | 401.0tok/s | 337ms | r_19f64yux97o |
| chat-long | llama.cpp@0.7.0-dev (build 1, commit ceefd16) | Q4_K_M | 12.67tok/s | 551.4tok/s | 5,735ms | r_19f64yux97o |
| concurrent-decode | llama.cpp@0.7.0-dev (build 1, commit ceefd16) | Q4_K_M | 12.85tok/s | no data | no data | r_19f64yux97o |
| agent-trace | llama.cpp@0.7.0-dev (build 1, commit ceefd16) | Q4_K_M | 12.72tok/s | 1,574.5tok/s | 1,344ms | r_19f64yux97o |
M3 Ultra (60-core GPU) + 96GB unified
| Workload | Backend | Quant | decode tok/s | prefill tok/s | TTFT | Run |
|---|---|---|---|---|---|---|
| chat-short | mlx@0.31.3 | - | 16.78tok/s | 25.09tok/s | 5,420ms | r_sx3a4y9n-m4 |
llama-3.3-70b-Instruct-4bit on hardware
Request a llama-3.3-70b-Instruct-4bit run
No measured run yet for these pairs. Vote for the one you want; the most-requested runs go first. See all requests.
0 votes
We never sell or share your email. Privacy
We can rent this card · Submit your own