Can RTX 4080 Super 16GB run MiniMax-M2.7?

NVIDIA · 16 GB GDDR6X · 736 GB/s bandwidth · MiniMax · 228.7B (active 10B) · MoE · model ctx up to 200K

No — MiniMax-M2.7 at Q4 needs ≈ 127.79 GB even at 4K context, beyond the RTX 4080 Super 16GB's 16 GB GDDR6X. It would only run with heavy CPU/disk offload. FP16 needs ≈ 460.4 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	127.79 GB	No	—
Q4	8K default	128.79 GB	No	—
Q4	32K	134.79 GB	No	—
FP16	4K	459.4 GB	No	—
FP16	8K default	460.4 GB	No	—
FP16	32K	466.4 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 4080 Super 16GB VRAM
Q4	125.79 GB	2.0 GB	1 GB	128.79 GB	16 GB
FP16	457.4 GB	2.0 GB	1 GB	460.4 GB	16 GB

Other GPUs that run MiniMax-M2.7

• B200 192GB SXM — ≈509.1 tok/s Q4 est.
• MI300X 192GB — ≈337.3 tok/s Q4 est.
• H200 141GB SXM5 — ≈305.5 tok/s Q4 est.
• Mac Studio M2 Ultra 192GB — ≈50.9 tok/s Q4 est.

All GPUs for MiniMax-M2.7 →

Other models for the RTX 4080 Super 16GB

• Qwen3-0.6B — ≈585.5 tok/s Q4 est.
• gemma-3-1b-it — ≈468.4 tok/s Q4 est.
• Llama-3.2-1B-Instruct — ≈390.3 tok/s Q4 est.
• Qwen3-1.7B — ≈234.2 tok/s Q4 est.
• gpt-oss-20b — ≈186.5 tok/s Q4 measured
• Llama-3.2-3B-Instruct — ≈146.4 tok/s Q4 est.
• Phi-4-mini-instruct — ≈123.3 tok/s Q4 est.
• Phi-4-mini-reasoning — ≈123.3 tok/s Q4 est.

All models on the RTX 4080 Super 16GB →