Can RTX 6000 Ada 48GB run Mistral-Medium-3.5-128B?

NVIDIA · 48 GB GDDR6 · 960 GB/s bandwidth · Mistral · 128.0B · model ctx up to 256K

No — Mistral-Medium-3.5-128B at Q4 needs ≈ 84.2 GB even at 4K context, beyond the RTX 6000 Ada 48GB's 48 GB GDDR6. It would only run with heavy CPU/disk offload. Decode at Q4/8K: ≈ 3.3 tok/s (estimated, batch 1). FP16 needs ≈ 282.6 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	84.2 GB	No	4.4 est.
Q4	8K default	97.0 GB	No	3.3 est.
Q4	32K	173.8 GB	No	1.0 est.
FP16	4K	269.8 GB	No	—
FP16	8K default	282.6 GB	No	—
FP16	32K	359.4 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 6000 Ada 48GB VRAM
Q4	70.4 GB	25.6 GB	1 GB	97.0 GB	48 GB
FP16	256.0 GB	25.6 GB	1 GB	282.6 GB	48 GB

Other GPUs that run Mistral-Medium-3.5-128B

• B200 192GB SXM — ≈39.8 tok/s Q4 est.
• MI300X 192GB — ≈26.3 tok/s Q4 est.
• H200 141GB SXM5 — ≈23.9 tok/s Q4 est.
• Gaudi 3 128GB — ≈16.3 tok/s Q4 est.
• Mac Studio M2 Ultra 192GB — ≈4.0 tok/s Q4 est.
• MacBook Pro M4 Max 128GB — ≈2.7 tok/s Q4 est.
• MacBook Pro M3 Max 128GB — ≈2.0 tok/s Q4 est.

All GPUs for Mistral-Medium-3.5-128B →

Other models for the RTX 6000 Ada 48GB

• MiniCPM5-1B — ≈565.7 tok/s Q4 est.
• Qwen3.5-2B — ≈305.5 tok/s Q4 est.
• GLM-4.7-Flash — ≈203.6 tok/s Q4 est.
• Qwen3-30B-A3B-Instruct-2507 — ≈203.6 tok/s Q4 est.
• Qwen3-Coder-Next — ≈203.6 tok/s Q4 est.
• Qwen3.5-35B-A3B — ≈203.6 tok/s Q4 est.
• Qwen3.6-35B-A3B — ≈203.6 tok/s Q4 est.
• Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16 — ≈203.6 tok/s Q4 est.

All models on the RTX 6000 Ada 48GB →