Can you run Qwen3.5 35B-A3B Instruct on RTX 4070 Ti SUPER?
Qwen3.5 35B-A3B Instruct Q4_K_M on the NVIDIA GeForce RTX 4070 Ti SUPER: verdict, VRAM math and estimated speed.
Yes, but slowly: Qwen3.5 35B-A3B Instruct spills past the RTX 4070 Ti SUPER. 20 GB weights at Q4_K_M vs 14.4 GB usable VRAM; ~44 tok/s est. (ModelFit, 2026).
VRAM math and speed are ModelFit engine estimates, not measurements. Commands are registry-verified Ollama tags.
Cite this page: ModelFit, Qwen3.5 35B-A3B Instruct on RTX 4070 Ti SUPER, https://modelfit.io/can-i-run/qwen3.5-35b-a3b-q4-on-rtx-4070-ti-super/, updated September 2026, CC BY 4.0.
Last updated: September 18, 2026 · Editor: ModelFit Team
What limits this combo
The four constraints the fit engine checks for Qwen3.5 35B-A3B Instruct on the RTX 4070 Ti SUPER, in order of what usually breaks first.
Quant explorer
Switch between the quality-gated builds tracked for this exact combo. Q4_K_M stays the default recommendation; heavier Q6/Q8 builds only appear when their exact Ollama tags are registry-verified.
Why no 2-bit builds: Q1/Q2-class quants can look attractive in a memory table, but their quality loss is large enough that ModelFit excludes them from rankings instead of inflating the catalog with junk options. Usable VRAM: 14.4 GB.
Workload verdicts
Qwen3.5 35B-A3B Instruct on the RTX 4070 Ti SUPER, graded per use case from the model's registry-verified tuning and the engine's speed estimate for this exact combo.
Grades combine tag-verified tuning (a model not built for the workload caps at C) with the tok/s floor each workload needs to feel usable. A combo that partially offloads caps at C; one that does not fit is D everywhere.
Memory math: weights + context vs budget
Weights take 20 GB. Context costs extra KV-cache on top — this is where long-context sessions break on cards that technically fit the weights.
This configuration exceeds the comfortable VRAM budget by about 5.9 GB. Expect offload pressure or a shorter safe context.
KV-cache figures assume an fp16 cache, the llama.cpp/Ollama default. Standard GQA models use a size-class estimate (8 KV heads x 128 head dim class); hybrid linear-attention models (Qwen3.5/3.6, Qwen3-Next) use the exact per-token cost from their published config, since only their sparse full-attention layers cache KV. A q8_0 KV cache roughly halves either figure. Estimates, not measurements.
See how fast it feels
A deterministic typing simulation for Qwen3.5 35B-A3B Instruct: first token ~1.0s (instant prefill), then ~44 tokens/sec.
ModelFit engine estimate, not a measured benchmark. Real speed varies with prompt length, thermals, runtime, and KV-cache settings.
Upgrade path
The cheapest tracked card that runs Qwen3.5 35B-A3B Instruct comfortably is the AMD Radeon RX 7900 XTX (24 GB VRAM).
See the RX 7900 XTX pageQwen3.5 35B-A3B Instruct on RTX 4070 Ti SUPER: FAQ
Can the NVIDIA GeForce RTX 4070 Ti SUPER run Qwen3.5 35B-A3B Instruct?
Barely. Qwen3.5 35B-A3B Instruct (Q4_K_M) needs about 20 GB but the RTX 4070 Ti SUPER has 14.4 GB usable VRAM, so part of the model spills to system RAM and speed drops to at roughly 44 tokens/sec (est.).
How much VRAM does Qwen3.5 35B-A3B Instruct need?
About 20 GB for the weights at Q4_K_M, plus KV-cache for context: roughly 0.3 GB extra at 16k tokens. The RTX 4070 Ti SUPER budget is 14.4 GB (16 GB x 90%).
What is the best quantization of Qwen3.5 35B-A3B Instruct for the RTX 4070 Ti SUPER?
Stick with the Q4_K_M build at 20 GB — every heavier quant exceeds the 14.4 GB usable VRAM.
What GPU do I need to run Qwen3.5 35B-A3B Instruct comfortably?
The cheapest tracked card that runs Qwen3.5 35B-A3B Instruct (Q4_K_M) fully in VRAM is the AMD Radeon RX 7900 XTX (24 GB).
How much context can Qwen3.5 35B-A3B Instruct use on the RTX 4070 Ti SUPER?
None worth having — the 20 GB of weights alone exceed the 14.4 GB usable VRAM, so the model only runs with system-RAM offload and short prompts.
Is Qwen3.5 35B-A3B Instruct on the RTX 4070 Ti SUPER fast enough for coding agents?
Yes: the engine estimates ~44 tok/s against the ~30 tok/s an agentic loop needs to feel responsive, and Qwen3.5 35B-A3B Instruct is tuned for tool-calling.