Models › Qwen3.6 35B A3B (MoE) › RTX 4060 Ti 16GB
Can I run Qwen3.6 35B A3B (MoE) on RTX 4060 Ti 16GB?
With offload
Only with RAM offload. At Q4_K_M it needs about 23.7 GB, more than the 16 GB usable on the RTX 4060 Ti 16GB; with 32 GB system RAM, llama.cpp can split layers (MoE experts to RAM), at a speed cost. ESTIMATE
Verdict by quantization (8k context, f16 KV, 32 GB RAM for offload)
| Quant | Needs | RTX 4060 Ti 16GB (16 GB) |
|---|---|---|
| Q3_K_M | 19.6 GB | 🐢 Needs RAM offload |
| IQ4_XS | 20.8 GB | 🐢 Needs RAM offload |
| Q4_K_M | 23.7 GB | 🐢 Needs RAM offload |
| MXFP4 | 22.6 GB | 🐢 Needs RAM offload |
| Q5_K_M | 27.6 GB | 🐢 Needs RAM offload |
| Q6_K | 31.7 GB | 🐢 Needs RAM offload |
| Q8_0 | 40.9 GB | 🐢 Needs RAM offload |
| F16 | 75.1 GB | ❌ Doesn't fit |
Speed
No measured run for this pair yet, and we don't estimate MoE speeds. Submit a llama-bench run.
Memory figures are estimates from the model's parameter count and config.json (Hugging Face). How we calculate. Last verified with data from 2026-10-20.
FAQ
Can I run Qwen3.6 35B A3B (MoE) on the RTX 4060 Ti 16GB?
Only with RAM offload. At Q4_K_M it needs about 23.7 GB, more than the 16 GB usable on the RTX 4060 Ti 16GB; with 32 GB system RAM, llama.cpp can split layers (MoE experts to RAM), at a speed cost.
How much VRAM does Qwen3.6 35B A3B (MoE) need?
About 23.7 GB at Q4_K_M and 40.9 GB at Q8_0 with 8k context (estimate).
Qwen3.6 35B A3B (MoE) on other hardware: RTX 3060 12GB · RTX 3090 · RTX 5090 · Apple M4 Pro (48 GB) · Apple M4 Max (128 GB)
Other models on RTX 4060 Ti 16GB: gpt-oss 20B (MoE) · Qwen3.6 27B · Qwen3.8 27B · Gemma 4 26B A4B (MoE) · Gemma 4 12B · Qwen3.5 9B · Llama 3.1 8B Instruct
See all models for 16 GB VRAM.
Won't fit? Free hosted options: FreeAISwap.