How much VRAM does Phi-4-mini-instruct-abliterated need?

Q4_K_M is exactly 2,491,875,264 bytes (2.32 GiB) in weights. Add the KV cache, which depends on context length, plus roughly half a gigabyte of runtime overhead.

How large is Phi-4-mini-instruct-abliterated's KV cache?

4.00 GiB at 32K context with an f16 cache, computed per layer from the model's architecture. Quantizing the cache to q8_0 roughly halves it.

huihui-ai · text

Phi-4-mini-instruct-abliterated

huihui-ai/Phi-4-mini-instruct-abliterated

Phi-4-mini-instruct-abliterated at Q4_K_M is exactly 2,491,875,264 bytes (2.32 GiB / 2.49 GB) — an effective 5.197 bits per weight, not the nominal 4. Its KV cache at 32K is 4.00 GiB.

From the file· summed from 1 file(s)From the file· KV per layer

Parameters

3.8B

Architecture

phi3

32 layers

Context

131,072

native (config.json)

License

mit

Shipped quantizations

● exact bytes, summed from published files

Quant	Size●	Exact bytes●	Effective bpw●	Tensors●	Publisher
Q2_K_S	1.48 GiB	1,593,769,920	3.324	—	Melvin56
Q2_K	1.57 GiB	1,682,636,480	3.509	—	tensorblock
Q2_K	1.57 GiB	1,682,636,736	3.509	—	Melvin56
Q3_K_M	1.97 GiB	2,117,533,376	4.416	—	tensorblock
Q3_K_M	1.97 GiB	2,117,533,632	4.416	—	Melvin56
Q3_K_L	2.10 GiB	2,249,654,208	4.692	—	Melvin56
Q4_K_M	2.32 GiB	2,491,875,264	5.197	—	Melvin56
Q5_K_M	2.65 GiB	2,848,128,960	5.940	—	Melvin56
Q6_K	2.94 GiB	3,155,623,872	6.581	—	Melvin56
Q8_0	3.80 GiB	4,084,612,032	8.518	—	Melvin56
F16	7.15 GiB	7,680,695,232	16.018	—	Melvin56

KV cache by context

computed per layer

Context	KV cache (f16)●	Flat formula	Overstated by	Full / windowed / recurrent
4,096	0.50 GiB	0.50 GiB	—	32 / 0 / 0
8,192	1.00 GiB	1.00 GiB	—	32 / 0 / 0
16,384	2.00 GiB	2.00 GiB	—	32 / 0 / 0
32,768	4.00 GiB	4.00 GiB	—	32 / 0 / 0
65,536	8.00 GiB	8.00 GiB	—	32 / 0 / 0
131,072	16.00 GiB	16.00 GiB	—	32 / 0 / 0

Compare with

same modality, comparable size

vs gemma-4-E4B-it vs Qwen3-4B vs Qwen3-8B vs HyperCLOVAX-SEED-Text-Instruct-1.5B vs Llama-3.2-1B-Instruct vs Qwen3-VL-8B-Instruct-abliterated-v1 All alternatives →Will it fit on my card? →

Why other calculators give a different number

A parameters × bits ÷ 8 estimate puts Q4_K_M at roughly 2.01 GiB. The real file is 2.32 GiB, because a quantization is a mixture and some tensors are always kept at higher precision.

Architecture

from config.json

Layers

Attention heads

KV heads

Head dim

128

Hidden size

3072

Vocab

200,064

Sliding window

262144

SWA period

MLA

Experts

—

Experts per token

—

use_sliding_window

—

Questions people ask

How much VRAM does Phi-4-mini-instruct-abliterated need?: Q4_K_M is exactly 2,491,875,264 bytes (2.32 GiB) in weights. Add the KV cache, which depends on your context length, plus roughly half a gigabyte of runtime overhead.
How large is Phi-4-mini-instruct-abliterated's KV cache?: 4.00 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 Phi-4-mini-instruct-abliterated 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.