Qwen3 VL 2B

Q8_0 running on AMD Radeon Pro WX 9100 with macOS 26.7.3 Tahoe

PERFORMANCE / TOKENS PER SECONDUnknown

Prompt processing875.8tok/s

#94 in index

Token generation102.08tok/s

#31 in index

Run fingerprint

Enough context to make the number useful.

ModelQwen3 VL 2BDense architecture

QuantizationQ8_0Exact submitted variant

GPUAMD Radeon Pro WX 910015.98 GB VRAM

GPU architectureUnknownMetal backend

Test context512prompt tokens

Model familyDenseSigned ToshLLM app · amd-gpu · Metal

ToshLLM versionv0.87.33App version used to capture and sign this run

Prompt processing and generation are reported separately so memory bandwidth and decode behavior stay visible.

Quantization, GPU family, VRAM and context travel with the result instead of being hidden behind one score.

This result remains explicitly labeled as a community submission.