Can RX 7900 XTX 24GB run Laguna S 2.1?

AMD · 24 GB GDDR6 · 960 GB/s bandwidth · Poolside · 118.0B (active 8.0B) · MoE · model ctx up to 1024K

Fit & speed by quant and context

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

Other GPUs that run Laguna S 2.1

• B200 192GB SXM — ≈956.7 tok/s Q4 est.
• MI300X 192GB — ≈625.5 tok/s Q4 est.
• H200 141GB SXM5 — ≈574.0 tok/s Q4 est.
• H100 80GB SXM5 — ≈400.6 tok/s Q4 est.
• Gaudi 3 128GB — ≈386.6 tok/s Q4 est.
• A100 80GB SXM4 — ≈243.8 tok/s Q4 est.
• MacBook Pro M4 Max 128GB — ≈96.2 tok/s Q4 est.
• MacBook Pro M3 Max 128GB — ≈70.5 tok/s Q4 est.

All GPUs for Laguna S 2.1 →

Other models for the RX 7900 XTX 24GB

• MiniCPM5-1B — ≈653.7 tok/s Q4 est.
• Qwen3.5-2B — ≈353.0 tok/s Q4 est.
• Qwen3.6-35B-A3B — ≈235.3 tok/s Q4 est.
• Qwen3.5-35B-A3B — ≈235.3 tok/s Q4 est.
• GLM-4.7-Flash — ≈235.3 tok/s Q4 est.
• Qwen3-30B-A3B-Instruct-2507 — ≈235.3 tok/s Q4 est.
• Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16 — ≈235.3 tok/s Q4 est.
• Ornith-1.0-35B — ≈235.3 tok/s Q4 est.

All models on the RX 7900 XTX 24GB →