Q
Manufacturer
Qwen (Alibaba)
Qwen-Modellfamilie von Alibaba.
Best token generation
1.716,6 tok/s
Qwen3-Coder-30B-A3B-Instruct
Best prefill
112.346,4 tok/s
Qwen3-0.6B
∅ Token generation
245,3 tok/s
Average of 1661 runs
∅ Prefill
6.009,7 tok/s
Average of 1654 runs
Best TTFT
121 ms
Qwen3-0.6B
Best harness rate
100%
Qwen3.8-Flash-Next
🏆
Qwen3-Coder-30B-A3B-Instruct · fastest model at 1.716,6 tok/s token generation
Best prefill of this manufacturer: 112.346,4 tok/s (Qwen3-0.6B)
Best prefill of this manufacturer: 112.346,4 tok/s (Qwen3-0.6B)
Top models by token generation
Best measured generation throughput per model (tok/s), published performance benchmarks.
Models
All benchmarks →36 assigned
Huihui-Qwen3-VL-30B-A3B-Instruct-abliterated30B6 runs
158,2tok/s Ø
Min 66,5Max 233,4
Qwen-AgentWorld-35B-A3B35B80 runs
342,1tok/s Ø
Min 21,8Max 1.481,2
Qwen-Image-2.17B6 runs
No performance data yet
Qwen2.5-0.5B-Instruct0.5B5 runs
121,0tok/s Ø
Min 11,7Max 298,1
Qwen2.5-1.5B-Instruct1.5B5 runs
51,6tok/s Ø
Min 4,1Max 126,7
Qwen2.5-32B-Instruct32.8B60 runs
127,7tok/s Ø
Min 4,3Max 510,3
Qwen2.5-32B-Instruct-AWQ32B3 runs
128,8tok/s Ø
Min 40,2Max 222,0
Qwen2.5-3B-Instruct3B23 runs
169,0tok/s Ø
Min 0,1Max 364,1
Qwen2.5-72B-Instruct72B32 runs
43,9tok/s Ø
Min 0,8Max 239,2
Qwen2.5-7B-Instruct7B14 runs
158,3tok/s Ø
Min 28,3Max 442,0
Qwen2.5-Coder-32B-Instruct32B104 runs
95,9tok/s Ø
Min 1,5Max 500,6
Qwen2.5-Coder-7B-Instruct7.6B5 runs
109,2tok/s Ø
Min 28,2Max 256,7
Qwen3-0.6B0.6B22 runs
242,2tok/s Ø
Min 3,2Max 561,4
Qwen3-1.7B1.7B19 runs
208,6tok/s Ø
Min 3,0Max 492,7
Qwen3-14B14B12 runs
104,9tok/s Ø
Min 10,6Max 280,8
Qwen3-30B-A3B30B3 runs
145,1tok/s Ø
Min 75,9Max 227,0
Qwen3-30B-A3B-Instruct-250730B134 runs
313,5tok/s Ø
Min 1,0Max 1.671,0
Qwen3-30B-A3B-Thinking-250730B128 runs
324,2tok/s Ø
Min 0,6Max 1.683,8
Qwen3-32B32B3 runs
70,0tok/s Ø
Min 28,4Max 117,2
Qwen3-4B4B19 runs
141,2tok/s Ø
Min 0,0Max 325,2
Qwen3-8B8.2B14 runs
124,1tok/s Ø
Min 1,6Max 315,2
Qwen3-Coder-30B-A3B-Instruct30B132 runs
324,9tok/s Ø
Min 1,0Max 1.716,6
Qwen3-Coder-Next79.7B57 runs
282,9tok/s Ø
Min 18,1Max 1.253,3
Qwen3-Omni-30B-A3B-Thinking30B77 runs
396,3tok/s Ø
Min 26,2Max 1.673,6
Qwen3-VL-30B-A3B-Instruct30B107 runs
331,5tok/s Ø
Min 16,3Max 1.655,9
Qwen3.5-122B-A10B122B58 runs
86,9tok/s Ø
Min 3,4Max 564,6
Qwen3.5-122B-A10B-Q8122B0 runs
No performance data yet
Qwen3.5-35B-A3B35B113 runs
330,4tok/s Ø
Min 5,6Max 1.520,4
Qwen3.6-27B27B75 runs
130,7tok/s Ø
Min 8,8Max 546,9
Qwen3.6-35B-A3B35B213 runs
239,3tok/s Ø
Min 4,3Max 1.499,4
Qwen3.6-35B-A3B-AWQ35B4 runs
No performance data yet
Qwen3.8-27B27.8B57 runs
101,0tok/s Ø
Min 6,9Max 426,5
Qwen3.8-27B-Uncensored27B6 runs
90,9tok/s Ø
Min 70,6Max 105,3
Qwen3.8-Flash-Next180B88 runs
237,3tok/s Ø
Min 9,0Max 1.564,6
Z-Image6B1 runs
No performance data yet
Z-Image-Turbo6B2 runs
No performance data yet

