Can RTX 4070 12GB run Ornith-1.0-9B?

NVIDIA · 12 GB GDDR6X · 504 GB/s bandwidth · DeepReinforce · 9.0B · model ctx up to 256K

Yes — the RTX 4070 12GB (12 GB GDDR6X) can run Ornith-1.0-9B. At Q4 with the default 8K context it needs ≈ 7.75 GB VRAM (weights 4.95 GB + KV cache 1.8 GB + 1 GB runtime overhead), which fits within 12 GB. Decode at Q4/8K: ≈ 35.6 tok/s (estimated, batch 1). FP16 needs ≈ 20.8 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	6.85 GB	Yes	35.6 est.
Q4	8K default	7.75 GB	Yes	35.6 est.
Q4	32K	13.15 GB	No	84.8 est.
FP16	4K	19.9 GB	No	10.2 est.
FP16	8K default	20.8 GB	No	9.3 est.
FP16	32K	26.2 GB	No	5.9 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 12GB VRAM
Q4	4.95 GB	1.8 GB	1 GB	7.75 GB	12 GB
FP16	18.0 GB	1.8 GB	1 GB	20.8 GB	12 GB

Other GPUs that run Ornith-1.0-9B

• B200 192GB SXM — ≈565.7 tok/s Q4 est.
• MI300X 192GB — ≈374.7 tok/s Q4 est.
• H200 141GB SXM5 — ≈339.4 tok/s Q4 est.
• H100 80GB SXM5 — ≈236.9 tok/s Q4 est.
• Gaudi 3 128GB — ≈231.6 tok/s Q4 est.
• A100 80GB SXM4 — ≈144.2 tok/s Q4 est.
• RTX 5090 32GB — ≈126.7 tok/s Q4 est.
• RTX 4090 24GB — ≈71.3 tok/s Q4 est.

All GPUs for Ornith-1.0-9B →

Other models for the RTX 4070 12GB

• MiniCPM5-1B — ≈297.0 tok/s Q4 est.
• Llama-3.2-3B-Instruct — ≈160.7 tok/s Q4 measured
• Qwen3.5-2B — ≈160.4 tok/s Q4 est.
• Qwen3-4B-Instruct-2507 — ≈80.2 tok/s Q4 est.
• Qwen3-4B-Thinking-2507 — ≈80.2 tok/s Q4 est.
• NVIDIA-Nemotron-3-Nano-4B-BF16 — ≈80.2 tok/s Q4 est.
• gemma-4-E2B-it — ≈62.9 tok/s Q4 est.
• Llama-3.1-8B-Instruct — ≈52.1 tok/s Q4 measured

All models on the RTX 4070 12GB →