Yes — the Arc Pro B70 32GB (32 GB GDDR6) can run gemma-4-E4B-it. At Q4 with the default 8K context it needs ≈ 7.0 GB VRAM (weights 4.4 GB + KV cache 1.6 GB + 1 GB runtime overhead), which fits within 32 GB. Decode at Q4/8K: ≈ 48.4 tok/s (estimated, batch 1). FP16 (≈ 18.6 GB) also fits, at ≈ 13.3 tok/s (estimated). 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
6.2 GB
Yes
48.4est.
Q4
8K default
7.0 GB
Yes
48.4est.
Q4
32K
11.8 GB
Yes
48.4est.
FP16
4K
17.8 GB
Yes
13.3est.
FP16
8K default
18.6 GB
Yes
13.3est.
FP16
32K
23.4 GB
Yes
13.3est.
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).