Qwen3-VL-8B-Instruct on AMD GPUs

8 results · 3 sources · 17 measurements

Grouped by reported model identity. Exact weights, quantizations and software can differ. How results are reviewed

Documented results

8 selected tests


View ReportLocalMaxxing	Qwen3-VL-8B-InstructQ8_0Model ref. ↗	Token speed	—	2,633.03 tok/sPrefill · unknown	89.84 tok/sGeneration · unknown	1 × RX 7900 XTXSingle GPU · 24 GB VRAM/GPU Configuration Memory 24 GB VRAM/GPU OS Arch Linux Engine llama.cpp Backend Not reported Harness LocalMaxxing community speed test; exact client where reported Prompt / output 530 / 256 tokens Context 8192 Concurrency Not reported Date 2026-09-15 Full record →
View ReportLocalMaxxing	Qwen3-VL-8B-InstructQ8_0Model ref. ↗	Token speed	—	3,037.91 tok/sPrefill · unknown	58.81 tok/sGeneration · peak · unknown	3 × R9700Multi-GPU · split unknown · 32 GB VRAM/GPU Configuration Memory 32 GB VRAM/GPU OS Arch Linux Engine llama.cpp Backend vulkan Harness LocalMaxxing community speed test; exact client where reported Prompt / output 530 / 256 tokens Context 786 Concurrency Not reported Date 2026-08-04 Full record →
View ReportGeneric LLM	Qwen3-VL-8B-InstructQuant not reportedModel ref. ↗	Relative performanceVery light pages (exact task set not supplied)	1.02 xReported speedup · Whole system	—	—	GPU count unknownUnknown Configuration Memory Not reported OS Ubuntu 24.04.2 LTS Engine AMD PACE Backend Not reported Harness AMD PACE / LangGraph Prompt / output ? / ? tokens Context Not reported Concurrency Not reported Date 2026-08-21 Full record →
View ReportLocalMaxxing	Qwen3-VL-8B-InstructQ4_K_MModel ref. ↗	Token speed	—	—	95.91 tok/sGeneration · peak · unknown	3 × R9700Multi-GPU · split unknown · 32 GB VRAM/GPU Configuration Memory 32 GB VRAM/GPU OS Arch Linux Engine llama.cpp Backend vulkan Harness LocalMaxxing community speed test; exact client where reported Prompt / output 530 / 256 tokens Context 786 Concurrency Not reported Date 2026-05-07 Full record →
View ReportGeneric LLM	Qwen3-VL-8B-InstructQuant not reportedModel ref. ↗	Relative performanceLight pages (exact task set not supplied)	1.04 xReported speedup · Whole system	—	—	GPU count unknownUnknown Configuration Memory Not reported OS Ubuntu 24.04.2 LTS Engine AMD PACE Backend Not reported Harness AMD PACE / LangGraph Prompt / output ? / ? tokens Context Not reported Concurrency Not reported Date 2026-08-21 Full record →
View ReportGeneric LLM	Qwen3-VL-8B-InstructQuant not reportedModel ref. ↗	Relative performanceMedium pages (exact task set not supplied)	1.08 xReported speedup · Whole system	—	—	GPU count unknownUnknown Configuration Memory Not reported OS Ubuntu 24.04.2 LTS Engine AMD PACE Backend Not reported Harness AMD PACE / LangGraph Prompt / output ? / ? tokens Context Not reported Concurrency Not reported Date 2026-08-21 Full record →
View ReportGeneric LLM	Qwen3-VL-8B-InstructQuant not reportedModel ref. ↗	Relative performanceHeavy pages (exact task set not supplied)	1.21 xReported speedup · Whole system	—	—	GPU count unknownUnknown Configuration Memory Not reported OS Ubuntu 24.04.2 LTS Engine AMD PACE Backend Not reported Harness AMD PACE / LangGraph Prompt / output ? / ? tokens Context Not reported Concurrency Not reported Date 2026-08-21 Full record →
View ReportGeneric LLM	Qwen3-VL-8B-InstructQuant not reportedModel ref. ↗	Relative performanceVery heavy pages (exact task set not supplied)	2.2 xReported speedup · Whole system	—	—	GPU count unknownUnknown Configuration Memory Not reported OS Ubuntu 24.04.2 LTS Engine AMD PACE Backend Not reported Harness AMD PACE / LangGraph Prompt / output ? / ? tokens Context Not reported Concurrency Not reported Date 2026-08-21 Full record →

Quantizations and software

Quantizations: Q4_K_M, Q8_0
Engines: AMD PACE, llama.cpp

Explore all 8 results →

This is a selection across sources, not a ranking or a matched experiment. Reading benchmark reports

GPU benchmark pages: R9700 · R9700S · RX 7900 XTX