Qwen (Alibaba)
Qwen2.5-32B-Instruct-AWQ32B
Benchmark profile and published results.
Dense32B
Position in the field
Best values compared
Best metrics of this model against the minimum, average and maximum of all published systems.
Generation222,0 tok/s
Min 0,0Ø 265,2Max 2.263,7
Unter dem Durchschnitt · 273 Systeme im Feld
Prefill2.436 tok/s
Min 5Ø 3.549Max 32.005
Unter dem Durchschnitt · 273 Systeme im Feld
Time to First Token1.705 ms
Min 20Ø 78.661Max 459.880
Ueber dem Durchschnitt · 273 Systeme im Feld
Performance profile
Throughput by hardware & engine
Each bubble is a GPU, CPU or engine – position shows prompt processing (X) and output speed (Y), bubble size the number of runs.
Throughput & latency
Performance benchmark
| # | Model / Maker | Metrics | Parallel | GPU / CPU / RAM | Runtime | ||
|---|---|---|---|---|---|---|---|
| 1 | Qwen2.5-32B-Instruct-AWQ32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 222,01 tok/s TG Prefill 2.436 · TTFT 45.755 ms | 10× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketAWQ | Details → | |
| 2 | Qwen2.5-32B-Instruct-AWQ32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 124,33 tok/s TG Prefill 2.267 · TTFT 13.440 ms | 5× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketAWQ | Details → | |
| 3 | Qwen2.5-32B-Instruct-AWQ32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 40,18 tok/s TG Prefill 1.444 · TTFT 1.705 ms | 1× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketAWQ | Details → |
Agent & chat rating
Harness benchmark
Noch keine Harnessbenchmarks fuer dieses Modell.

