Can Arc A770 16GB run NVIDIA-Nemotron-3-Super-120B-A12B-BF16?

Intel · 16 GB GDDR6 · 560 GB/s bandwidth · NVIDIA · 120.0B (active 12.0B) · MoE · model ctx up to 256K

No — NVIDIA-Nemotron-3-Super-120B-A12B-BF16 at Q4 needs ≈ 68.2 GB even at 4K context, beyond the Arc A770 16GB's 16 GB GDDR6. It would only run with heavy CPU/disk offload. FP16 needs ≈ 243.4 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	68.2 GB	No	—
Q4	8K default	69.4 GB	No	—
Q4	32K	76.6 GB	No	—
FP16	4K	242.2 GB	No	—
FP16	8K default	243.4 GB	No	—
FP16	32K	250.6 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	Arc A770 16GB VRAM
Q4	66.0 GB	2.4 GB	1 GB	69.4 GB	16 GB
FP16	240.0 GB	2.4 GB	1 GB	243.4 GB	16 GB

Other GPUs that run NVIDIA-Nemotron-3-Super-120B-A12B-BF16

• B200 192GB SXM — ≈424.2 tok/s Q4 est.
• MI300X 192GB — ≈281.1 tok/s Q4 est.
• H200 141GB SXM5 — ≈254.5 tok/s Q4 est.
• H100 80GB SXM5 — ≈177.7 tok/s Q4 est.
• Gaudi 3 128GB — ≈173.7 tok/s Q4 est.
• A100 80GB SXM4 — ≈108.1 tok/s Q4 est.
• Mac Studio M3 Ultra 96GB — ≈43.4 tok/s Q4 est.
• Mac Studio M2 Ultra 192GB — ≈42.4 tok/s Q4 est.

All GPUs for NVIDIA-Nemotron-3-Super-120B-A12B-BF16 →

Other models for the Arc A770 16GB

• MiniCPM5-1B — ≈330.0 tok/s Q4 est.
• Qwen3.5-2B — ≈178.2 tok/s Q4 est.
• Llama-3.2-3B-Instruct — ≈111.4 tok/s Q4 est.
• gpt-oss-20b — ≈99.0 tok/s Q4 est.
• Qwen3-4B-Instruct-2507 — ≈89.1 tok/s Q4 est.
• Qwen3-4B-Thinking-2507 — ≈89.1 tok/s Q4 est.
• NVIDIA-Nemotron-3-Nano-4B-BF16 — ≈89.1 tok/s Q4 est.
• gemma-4-E2B-it — ≈69.9 tok/s Q4 est.

All models on the Arc A770 16GB →