Can Gaudi 3 128GB run gemma-4-26B-A4B-it?

Intel · 128 GB HBM2e · 3276 GB/s bandwidth · Google · 25.2B (active 3.8B) · MoE · model ctx up to 256K

Fit & speed by quant and context

Fits = weights + KV(ctx) + 1.5 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 gemma-4-26B-A4B-it

• B200 192GB SXM — ≈1978.2 tok/s Q4 est.
• MI300X 192GB — ≈1293.4 tok/s Q4 est.
• H200 141GB SXM5 — ≈1186.9 tok/s Q4 est.
• H100 80GB SXM5 — ≈828.4 tok/s Q4 est.
• A100 80GB SXM4 — ≈504.2 tok/s Q4 est.
• RTX 5090 32GB — ≈443.1 tok/s Q4 est.
• RTX 4090 24GB — ≈226.6 tok/s Q4 est.
• RTX 4090D 24GB (China) — ≈226.6 tok/s Q4 est.

All GPUs for gemma-4-26B-A4B-it →

Other models for the Gaudi 3 128GB

• MiniCPM5-1B — ≈2812.9 tok/s Q4 est.
• Qwen3.5-2B — ≈1519.0 tok/s Q4 est.
• Qwen3.6-35B-A3B — ≈1012.6 tok/s Q4 est.
• Qwen3.5-35B-A3B — ≈1012.6 tok/s Q4 est.
• GLM-4.7-Flash — ≈1012.6 tok/s Q4 est.
• Qwen3-30B-A3B-Instruct-2507 — ≈1012.6 tok/s Q4 est.
• Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16 — ≈1012.6 tok/s Q4 est.
• Qwen3-Coder-Next — ≈1012.6 tok/s Q4 est.

All models on the Gaudi 3 128GB →