Qwen2.5-32B-Instruct
7 workload results across 3 hardware configurations.
Fastest community-submitted config (not measured by llm-speed)
71.9 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, Qwen2.5-32B-Instruct is fastest on the M3 Ultra (60-core GPU) at 34.60 tok/s, 390% faster than the M3 Pro (18-core GPU) (7.05 tok/s).
| Card | Decode tok/s | TTFT (131-token prompt) | Run | Source |
|---|---|---|---|---|
| M3 Ultra (60-core GPU) | 34.60 (single run) | 923 ms | r_njgxtgyym1e | community-submitted |
| M3 Pro (18-core GPU) | 7.05 (single run) | 3921 ms | r_f4x3xaan2ay | community-submitted |
Qwen2.5-32B-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 | - | 68.71tok/s | no data | 77.0ms | r_bjy5a5izxjc | Community-submitted |
| chat-long | llama.cpp | - | 65.36tok/s | no data | 968ms | r_bjy5a5izxjc | Community-submitted |
| concurrent-decode | llama.cpp | - | 68.60tok/s | no data | no data | r_bjy5a5izxjc | Community-submitted |
| agent-trace | llama.cpp | - | 66.45tok/s | 10,407.9tok/s | 214ms | r_bjy5a5izxjc | Community-submitted |
| chat-short | llama.cpp | - | 71.90tok/s | no data | 115ms | r_twfs86tf_xf | 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 | 7.05tok/s | 33.41tok/s | 3,921ms | r_f4x3xaan2ay | 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 | 34.60tok/s | 141.9tok/s | 923ms | r_njgxtgyym1e | Community-submitted |
Can Qwen2.5-32B-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.
Qwen2.5-32B-Instruct on hardware
Request a Qwen2.5-32B-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
Check it for your setup
- Predict your exact setup: estimate whether Qwen2.5-32B-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 Qwen2.5-32B-Instruct run on hardware we have not measured. Requests are ranked by votes.
- Full run table (4 runs): every Qwen2.5-32B-Instruct result we have, with links to each source run.