Qwen3 4B

65 records across 9 hardware.

hardwaremodelquantbackendtok/spp tok/sWttft sctx/tgdateclassflagssource
B300Qwen3 4B BF16vLLM10543–––tg2562026-10-02community–source
B300Qwen3 4B BF16vLLM10495–––tg2562026-10-02community–source
B300Qwen3 4B BF16vLLM3032–––tg2562026-10-02community–source
B300Qwen3 4B BF16vLLM3012–––tg2562026-10-02community–source
A10Qwen3 4B AWQvLLM656.60–––tg5122025-05community–source
A10Qwen3 4B AWQvLLM607.98–––tg10242025-05community–source
A10Qwen3 4B AWQvLLM469.62–––tg5122025-05community–source
B300Qwen3 4B BF16vLLM464.7–––tg2562026-10-02community–source
B300Qwen3 4B BF16vLLM462.3–––tg2562026-10-02community–source
A10Qwen3 4B AWQvLLM433.77–––tg5122025-05community–source
A10Qwen3 4B AWQSGLang424.58–––tg5122025-05community–source
A10Qwen3 4B AWQSGLang423.26–––tg10242025-05community–source
A10Qwen3 4B AWQSGLang413.54–––tg5122025-05community–source
A10Qwen3 4B AWQSGLang401.26–––tg5122025-05community–source
A10Qwen3 4B AWQvLLM395.12–––tg30962025-05community–source
A10Qwen3 4B AWQvLLM377.98–––tg30962025-05community–source
A10Qwen3 4B AWQSGLang369.19–––tg30962025-05community–source
A10Qwen3 4B AWQSGLang337.17–––tg30962025-05community–source
A10Qwen3 4B AWQvLLM278.73–––tg30962025-05community–source
A10Qwen3 4B AWQvLLM249.99–––tg30962025-05community–source
A10Qwen3 4B AWQSGLang239.82–––tg30962025-05community–source
A10Qwen3 4B AWQSGLang238.21–––tg30962025-05community–source
A10Qwen3 4B BF16vLLM138.3––––2026-10-01community–source
A10Qwen3 4B BF16vLLM132.6––––2026-10-01community–source
M5 MaxQwen3 4B 8bitoMLX90.04528.0––81922026-10-11community–source
L4Qwen3 4B BF16vLLM82.8––––2026-10-01community–source
L4Qwen3 4B BF16vLLM81.6––––2026-10-01community–source
L4Qwen3 4B BF16vLLM80.5––––2026-10-01community–source
L4Qwen3 4B BF16vLLM79.7––––2026-10-01community–source
L4Qwen3 4B BF16vLLM78.2––––2026-10-01community–source
L4Qwen3 4B BF16vLLM77.0––––2026-10-01community–source
M5 MaxQwen3 4B 8bitoMLX74.53844.0––163842026-10-11community–source
L4Qwen3 4B BF16vLLM61.2––––2026-10-01community–source
M5 MaxQwen3 4B 8bitoMLX52.02643.0––327682026-10-11community–source
M5 MaxQwen3 4B 8bitoMLX52.02643.0––327682026-10-11community–source
L4Qwen3 4B BF16vLLM39.2––––2026-10-01communitycontradictionsource
M5 MaxQwen3 4B 8bitoMLX35.21352.0––655362026-10-11community–source
M5 MaxQwen3 4B 8bitoMLX35.21352.0––655362026-10-11community–source
M4Qwen3 4B 4bitoMLX29.4305.8––40962026-10-08community–source
K12-1 Ryzen H255 64gbQwen3 4B Q8_0Vulkan18.040894393.674985–––2026-09community–source
M4Qwen3 4B 4bitoMLX16.2211.8––163842026-10-08community–source
2 GMKtec K12Qwen3 4B Q8_0llama.cpp (RPC)13.21155766.181528–––2026-09community–source
AMD Ryzen 9 9950XQwen3 4B Q8_0llama.cpp (CPU)11.48–––1282026-10community–source
AMD Ryzen 9 9950XQwen3 4B Q8_0llama.cpp (CPU)11.48–––1282026-10community–source
AMD Ryzen 9 9950XQwen3 4B Q8_0llama.cpp (CPU)11.32–––1282026-10community–source
AMD Ryzen 9 9950XQwen3 4B Q8_0llama.cpp (CPU)11.22–––1282026-10community–source
AMD Ryzen 9 9950XQwen3 4B Q8_0llama.cpp (CPU)10.92–––1282026-10community–source
AMD Ryzen 9 9950XQwen3 4B Q8_0llama.cpp (CPU)10.78–––1282026-10community–source
2 GMKtec K12Qwen3 4B Q8_0llama.cpp (RPC)5.41156863.902555–––2026-09community–source
AMD Ryzen 9 9950XQwen3 4B Q8_0llama.cpp (CPU)–95.95––20482026-10community–source
AMD Ryzen 9 9950XQwen3 4B Q8_0llama.cpp (CPU)–310.88––20482026-10community–source
AMD Ryzen 9 9950XQwen3 4B Q8_0llama.cpp (CPU)–176.81––20482026-10community–source
AMD Ryzen 9 9950XQwen3 4B Q8_0llama.cpp (CPU)–552.12––20482026-10community–source
AMD Ryzen 9 9950XQwen3 4B Q8_0llama.cpp (CPU)–307.15––20482026-10community–source
AMD Ryzen 9 9950XQwen3 4B Q8_0llama.cpp (CPU)–810.96––20482026-10community–source
AMD Ryzen 9 9950XQwen3 4B Q8_0llama.cpp (CPU)–87.88––40962026-10community–source
AMD Ryzen 9 9950XQwen3 4B Q8_0llama.cpp (CPU)–237.88––40962026-10community–source
AMD Ryzen 9 9950XQwen3 4B Q8_0llama.cpp (CPU)–162.5––40962026-10community–source
AMD Ryzen 9 9950XQwen3 4B Q8_0llama.cpp (CPU)–430.49––40962026-10community–source
AMD Ryzen 9 9950XQwen3 4B Q8_0llama.cpp (CPU)–284.02––40962026-10community–source
AMD Ryzen 9 9950XQwen3 4B Q8_0llama.cpp (CPU)–657.98––40962026-10community–source
Arc Pro B70Qwen3 4B Q8_0llama.cpp–2985.5––5122026-10-17sourced–source
Arc Pro B70Qwen3 4B Q8_0llama.cpp–4831.58––5122026-10-17sourced–source
Arc Pro B70Qwen3 4B Q8_0llama.cpp–5489.1––5122026-10-18sourced–source
Arc Pro B70Qwen3 4B Q8_0llama.cpp–5652.1––5122026-10-18sourced–source

← all models