Carnice Qwen3.6 MoE 35B

Q3_K_M running on AMD Radeon RX Ellesmere Prototype with macOS 15.7.3 Sequoia

PERFORMANCE / TOKENS PER SECONDUnknown

Prompt processing99.63tok/s

#120 in index

Token generation14.52tok/s

#105 in index

Run fingerprint

Enough context to make the number useful.

ModelCarnice Qwen3.6 MoE 35BMoE architecture

QuantizationQ3_K_MExact submitted variant

GPUAMD Radeon RX Ellesmere Prototype8 GB VRAM

GPU architectureUnknownMetal backend

Test context512prompt tokens

Model familyMoESigned ToshLLM app · ncmoe 30 · amd-gpu · Metal

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.