Qwen-AgentWorld-35B-A3B

Name: Qwen-AgentWorld-35B-A3B
Author: Qwen

Quantized builds

Benchmark records

Quantized builds

Community and official quantized releases; "linked records" counts only benchmarks tied to that exact release.

No quantized builds cataloged yet.

20 configurations

Hardware	Framework	Quant	Decode	VRAM used	Samples	Evidence
NVIDIA RTX 5080 SUPER	vLLM	Q5_K_M	36.6 tok/s	24 GB	1	L0 Self-reported
NVIDIA RTX 5080 SUPER	vLLM	Q4_K_M	44.7 tok/s	21.8 GB	1	L0 Self-reported
NVIDIA RTX 5080 SUPER	llama.cpp	Q5_K_M	33.6 tok/s	24 GB	1	L0 Self-reported
NVIDIA RTX 5080 SUPER	llama.cpp	Q4_K_M	41 tok/s	21.8 GB	1	L0 Self-reported
NVIDIA RTX 5070 SUPER	vLLM	Q5_K_M	29.3 tok/s	18 GB	1	L0 Self-reported
NVIDIA RTX 5070 SUPER	vLLM	Q4_K_M	35.8 tok/s	18 GB	1	L0 Self-reported
NVIDIA RTX 5070 SUPER	llama.cpp	Q5_K_M	26.9 tok/s	18 GB	1	L0 Self-reported
NVIDIA RTX 5070 SUPER	llama.cpp	Q4_K_M	32.8 tok/s	18 GB	1	L0 Self-reported
NVIDIA RTX 5070 Ti	vLLM	Q5_K_M	29.3 tok/s	16 GB	1	L0 Self-reported
NVIDIA RTX 5070 Ti	vLLM	Q4_K_M	35.8 tok/s	16 GB	1	L0 Self-reported
NVIDIA RTX 5070 Ti	llama.cpp	Q5_K_M	26.9 tok/s	16 GB	1	L0 Self-reported
NVIDIA RTX 5070 Ti	llama.cpp	Q4_K_M	32.8 tok/s	16 GB	1	L0 Self-reported
NVIDIA RTX 5090	vLLM	Q5_K_M	58.6 tok/s	26.5 GB	1	L0 Self-reported
NVIDIA RTX 5090	vLLM	Q4_K_M	71.5 tok/s	21.8 GB	1	L0 Self-reported
NVIDIA RTX 5090	llama.cpp	Q5_K_M	53.8 tok/s	26.5 GB	1	L0 Self-reported
NVIDIA RTX 5090	llama.cpp	Q4_K_M	65.6 tok/s	21.8 GB	1	L0 Self-reported
NVIDIA RTX 4090	vLLM	Q5_K_M	33 tok/s	24 GB	1	L0 Self-reported
NVIDIA RTX 4090	vLLM	Q4_K_M	40.2 tok/s	21.8 GB	1	L0 Self-reported
NVIDIA RTX 4090	llama.cpp	Q5_K_M	30.2 tok/s	24 GB	1	L0 Self-reported
NVIDIA RTX 4090	llama.cpp	Q4_K_M	36.9 tok/s	21.8 GB	1	L0 Self-reported

20 of these records are not linked to a specific quantized build; the full set is on the search page.

No discussions yet — start the first one.