gemma-4-E2B-it-qat-q4_0-unquantized-heretic

28 of 35 layers cache only a 512-token window rather than the full context, on a period of . Figures assume the default configuration; --swa-full disables the saving entirely.

A parameters × bits ÷ 8 estimate puts Q4_K_M at roughly 2.67 GiB. The real file is 3.18 GiB, because a quantization is a mixture and some tensors are always kept at higher precision. The larger discrepancy is the cache: a flat formula gives 1.09 GiB at 32K context where the real figure is 0.25 GiB, because most of this model's layers cache a fixed window rather than the whole context.

How much VRAM does gemma-4-E2B-it-qat-q4_0-unquantized-heretic need?

Q4_K_M is exactly 3,416,119,296 bytes (3.18 GiB) in weights. Add the KV cache, which depends on your context length, plus roughly half a gigabyte of runtime overhead.

How large is gemma-4-E2B-it-qat-q4_0-unquantized-heretic's KV cache?

0.25 GiB at 32K context with an f16 cache, computed per layer. Quantizing the cache to q8_0 roughly halves it, which is often the difference between a context length fitting and not.

Which quantization of gemma-4-E2B-it-qat-q4_0-unquantized-heretic should I use?

Q4_K_M is the usual default. Pick the largest quantization that fits your card at the context you actually need — the table above gives exact sizes for every one published.