Qwen2.5-1.5B-heretic

A parameters × bits ÷ 8 estimate puts Q4_K_M at roughly 0.81 GiB. The real file is 0.92 GiB, because a quantization is a mixture and some tensors are always kept at higher precision.

How much VRAM does Qwen2.5-1.5B-heretic need?

Q4_K_M is exactly 986,048,672 bytes (0.92 GiB) in weights. Add the KV cache, which depends on your context length, plus roughly half a gigabyte of runtime overhead.

How large is Qwen2.5-1.5B-heretic's KV cache?

0.88 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 Qwen2.5-1.5B-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.