Qwen on NVIDIA Ada

Can I run Qwen3 235B-A22B on an RTX 4060 Ti 16GB?

Not at Q4_K_M — it needs 135.1 GB against 14.2 GB available. No quantisation of this model fits on one card.

Won't fit

135.1 GB of 14.2 GB · 949%
0141 GB
Weights 132.8 GB
KV cache 1.5 GB
Runtime overhead 0.8 GB
Over the limit 120.9 GB

Short by 120.9 GB. You can run it with 8 of 94 layers on the RTX 4060 Ti 16GB and the rest in system RAM, at roughly 3.01 tok/s — usable for batch work, painful for chat. A smaller quantisation or a shorter context is usually the better trade.

Generation3.01tok/s
Prompt processing417tok/s
Max context0tokens
KV per 1K tokens0GB

Every quantisation of Qwen3 235B-A22B on a RTX 4060 Ti 16GB

Highlighted row is the highest quality that still fits at 8K context.

QuantisationbpwWeights TotalVerdictMax ctxtok/s
FP16 / BF16 16.00 437.9 GB 440.2 GB Won't fit 0.92
INT8 / W8A8 8.50 232.3 GB 234.6 GB Won't fit 1.72
Q8_0 (GGUF) 8.50 232.3 GB 234.6 GB Won't fit 1.72
FP8 (E4M3) 8.00 218.9 GB 221.2 GB Won't fit 1.84
Q6_K 6.56 179.5 GB 181.8 GB Won't fit 2.24
Q5_K_M 5.67 155.2 GB 157.5 GB Won't fit 2.59
Q5_K_S 5.52 151.1 GB 153.4 GB Won't fit 2.65
Q4_K_M 4.85 132.8 GB 135.1 GB Won't fit 3.01
Q4_K_S 4.58 125.5 GB 127.8 GB Won't fit 3.17
Q4_0 4.55 124.7 GB 127.0 GB Won't fit 3.22
AWQ 4-bit 4.25 118.0 GB 120.3 GB Won't fit 3.38
GPTQ 4-bit 4.25 118.0 GB 120.3 GB Won't fit 3.38
MXFP4 4.25 118.0 GB 120.3 GB Won't fit 3.38
IQ4_XS 4.25 116.5 GB 118.8 GB Won't fit 3.42
Q3_K_M 3.91 107.2 GB 109.5 GB Won't fit 3.72
IQ3_M 3.70 101.5 GB 103.8 GB Won't fit 3.94
IQ3_XXS 3.06 84.1 GB 86.4 GB Won't fit 4.74
Q2_K 2.63 72.4 GB 74.7 GB Won't fit 5.50
IQ2_XXS 2.06 56.9 GB 59.2 GB Won't fit 6.98
IQ1_M 1.75 48.4 GB 50.7 GB Won't fit 8.25

Also worth checking