Llama-3.1-8B-Instruct
7 workload results across 3 hardware configurations.
Fastest community-submitted config (not measured by llm-speed)
232.2 decode tok/s
on RTX 5090 (32GB) via llama.cpp. see full run
For a standard 4-bit quantization using MLX, here are measured results for short-chat generation.
On MLX 4-bit, Llama-3.1-8B-Instruct is fastest on the M3 Ultra (60-core GPU) at 130.2 tok/s, 346% faster than the M3 Pro (18-core GPU) (29.20 tok/s).
| Card | Decode tok/s | TTFT (136-token prompt) | Run | Source |
|---|---|---|---|---|
| M3 Ultra (60-core GPU) | 130.2 (single run) | 340 ms | r_v2pbc0rq2l4 | community-submitted |
| M3 Pro (18-core GPU) | 29.20 (single run) | 669 ms | r_h0-use1ypnb | community-submitted |
Llama-3.1-8B-Instruct, 4-bit, MLX, chat-short, batch 1. Only cards with their standard memory are listed; CPU-only hosts are excluded. Community-submitted runs are signed on the submitter's own machine and are not measured by llm-speed; llm-speed verdicts use only its own runs.
Signed runs (7 workload results)
All 4 runs are community-submitted (signed on the submitter's own machine, not measured by llm-speed, and not used for llm-speed verdicts).
RTX 5090 (32GB)
| Workload | Backend | Quant | decode tok/s | prefill tok/s | TTFT | Run | Source |
|---|---|---|---|---|---|---|---|
| chat-short | llama.cpp | - | 229.4tok/s | no data | 35.6ms | r_qr4srge34da | Community-submitted |
| chat-long | llama.cpp | - | 211.4tok/s | no data | 266ms | r_qr4srge34da | Community-submitted |
| concurrent-decode | llama.cpp | - | 223.0tok/s | no data | no data | r_qr4srge34da | Community-submitted |
| agent-trace | llama.cpp | - | 210.3tok/s | 36,720.3tok/s | 60.8ms | r_qr4srge34da | Community-submitted |
| chat-short | llama.cpp | - | 232.2tok/s | no data | 33.8ms | r_kfrkg-vn376 | Community-submitted |
M3 Pro (18-core GPU) + 36GB unified
| Workload | Backend | Quant | decode tok/s | prefill tok/s | TTFT | Run | Source |
|---|---|---|---|---|---|---|---|
| chat-short | mlx@0.31.3 | 4BIT | 29.20tok/s | 203.3tok/s | 669ms | r_h0-use1ypnb | Community-submitted |
M3 Ultra (60-core GPU) + 96GB unified
| Workload | Backend | Quant | decode tok/s | prefill tok/s | TTFT | Run | Source |
|---|---|---|---|---|---|---|---|
| chat-short | mlx@0.31.3 | 4BIT | 130.2tok/s | 400.3tok/s | 340ms | r_v2pbc0rq2l4 | Community-submitted |
Can Llama-3.1-8B-Instruct run on your hardware?
Fastest decode speed on each GPU or Mac, from llm-speed's own runs and community-submitted runs. Each page lists every quant and runtime and labels which runs llm-speed measured.
Llama-3.1-8B-Instruct on hardware
Request a Llama-3.1-8B-Instruct run
No measured run yet for these pairs. Vote for the one you want; the most-requested runs go first. See all requests.
We never sell or share your email. Privacy
Compare Llama-3.1-8B-Instruct head-to-head
Check it for your setup
- Predict your exact setup: estimate whether Llama-3.1-8B-Instruct fits your GPU or Mac at your quant and context, next to measured speeds where we have them.
- Request this pair: ask for a measured Llama-3.1-8B-Instruct run on hardware we have not measured. Requests are ranked by votes.
- Full run table (4 runs): every Llama-3.1-8B-Instruct result we have, with links to each source run.