Yes — the RTX 4070 Ti Super 16GB (16 GB GDDR6X) can run Qwen3.5-122B-A10B-Heretic-v2-MLX-mixed-3.8bit. At Q4 with the default 8K context it needs ≈ 15.85 GB VRAM (weights 10.89 GB + KV cache 3.96 GB + 1 GB runtime overhead), which fits within 16 GB. Decode at Q4/8K: ≈ 21.6 tok/s (estimated, batch 1). FP16 needs ≈ 44.56 GB — does not fit on this card. Estimates come from memory-bandwidth math; rows tagged measured override estimates. Relative ranking is more reliable than absolute tok/s. Methodology. Buy RTX 4070 Ti Super 16GB on Amazon →
Fit & speed by quant and context
Quant
Context
VRAM needed
Fits?
tok/s (decode)
Q4
4K
13.87 GB
Yes
21.6±est.
Q4
8K default
15.85 GB
Yes
21.6±est.
Q4
32K
27.73 GB
No
20.5±est.
FP16
4K
42.58 GB
No
2.4±est.
FP16
8K default
44.56 GB
No
2.2±est.
FP16
32K
56.44 GB
No
1.4±est.
Fits = weights + KV(ctx) + 1 GB overhead ≤ 95% of VRAM. Measured anchors are context-agnostic; the fit verdict is recomputed per context. A missing tok/s means the model is far beyond this card (offload-only territory).
VRAM breakdown at 8K context
Quant
Weights
KV cache
Overhead
Total needed
RTX 4070 Ti Super 16GB VRAM
Q4
10.89 GB
3.96 GB
1 GB
15.85 GB
16 GB
FP16
39.6 GB
3.96 GB
1 GB
44.56 GB
16 GB
Other GPUs that run Qwen3.5-122B-A10B-Heretic-v2-MLX-mixed-3.8bit