Can RTX 3070 8GB run DeepSeek-V3.2?

NVIDIA · 8 GB GDDR6 · 448 GB/s bandwidth · DeepSeek · 685.4B (active 37B) · MoE · model ctx up to 128K

No — DeepSeek-V3.2 at Q4 needs ≈ 381.67 GB even at 4K context, beyond the RTX 3070 8GB's 8 GB GDDR6. It would only run with heavy CPU/disk offload. FP16 needs ≈ 1379.2 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.

Fit & speed by quant and context

Quant	Context	VRAM needed	Fits?	tok/s (decode)
Q4	4K	381.67 GB	No	—
Q4	8K default	385.37 GB	No	—
Q4	32K	407.57 GB	No	—
FP16	4K	1375.5 GB	No	—
FP16	8K default	1379.2 GB	No	—
FP16	32K	1401.4 GB	No	—

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 3070 8GB VRAM
Q4	376.97 GB	7.4 GB	1 GB	385.37 GB	8 GB
FP16	1370.8 GB	7.4 GB	1 GB	1379.2 GB	8 GB

Other GPUs that run DeepSeek-V3.2

No catalog GPU fully fits DeepSeek-V3.2 at Q4/8K — see the model page for offload estimates.

All GPUs for DeepSeek-V3.2 →

Other models for the RTX 3070 8GB

• Qwen3-0.6B — ≈356.4 tok/s Q4 est.
• gemma-3-1b-it — ≈285.1 tok/s Q4 est.
• Llama-3.2-1B-Instruct — ≈237.6 tok/s Q4 est.
• Qwen3-1.7B — ≈142.5 tok/s Q4 est.
• Llama-3.2-3B-Instruct — ≈89.1 tok/s Q4 est.
• Phi-4-mini-instruct — ≈75.0 tok/s Q4 est.
• Phi-4-mini-reasoning — ≈75.0 tok/s Q4 est.
• gemma-3-4b-it — ≈73.1 tok/s Q4 est.

All models on the RTX 3070 8GB →