Qwen3.6 35B (3B active)
on NVIDIA RTX 3060 12GB · Strata
Summary
User reports Qwen3.6-35B-A3B at 106 tok/s for a single user on one 12 GB RTX 3060, served by Strata.
Setup is Strata with a Q2_K_XL GGUF and --parallel 4; the 35B MoE is quantized to fit the 12 GB card.
Aggregate throughput rises to 139 tok/s with 2 users (69 tok/s each) and 164 tok/s with 4 users (41 tok/s each). The server exposes OpenAI and Anthropic APIs, per-key usage logs and a fair queue.
Compare this run
Medians of plain runs: one device, one request, no speculative decoding, the whole model in the device's memory. The report above is one setup, so read it beside them and not as one of them.
Qwen3.6 35B · 3B active at 4-bit by hardware
- NVIDIA RTX 509032 GB215.1 t/s · one run
- 178.0 t/s · one run
- 137.7 t/s · 2 runs
- AMD RX 7900 XTX24 GB125.5 t/s · one run
- NVIDIA RTX 309024 GB101.7 t/s · one run
- 81.1 t/s · one run
Bars are medians on one scale, 0 to 215.1 tokens/s. Each dot is one run and opens its report. Press ▶ to watch text arrive at a row's speed.
Models most run on the NVIDIA RTX 3060 12GB
- Gemma 4 8B4-bit59.5 t/s · 2 runs
- Gemma 4 5.1B4-bit60.0 t/s · one run
- Qwen2.5 7B4-bit49.0 t/s · one run
- 113.6 t/s · one run
Bars are medians on one scale, 0 to 113.6 tokens/s. Each dot is one run and opens its report. Press ▶ to watch text arrive at a row's speed.
Everything reported on the NVIDIA RTX 3060 12GB →Every Qwen3.6 report →Estimate Qwen3.6 on this card →