How much VRAM does Qwen3-14B-GPT-5.2-High-Reasoning-Distill need?

Q4_K_M is exactly 18,003,508,096 bytes (16.77 GiB) in weights. Add the KV cache, which depends on context length, plus roughly half a gigabyte of runtime overhead.

How large is Qwen3-14B-GPT-5.2-High-Reasoning-Distill's KV cache?

5.00 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.

TeichAI · text

Qwen3-14B-GPT-5.2-High-Reasoning-Distill

TeichAI/Qwen3-14B-GPT-5.2-High-Reasoning-Distill

Qwen3-14B-GPT-5.2-High-Reasoning-Distill at Q4_K_M is exactly 18,003,508,096 bytes (16.77 GiB / 18.00 GB) — an effective 9.752 bits per weight, not the nominal 4. Its KV cache at 32K is 5.00 GiB.

From the file· summed from 2 file(s)From the file· KV per layer

Parameters

14.8B

Architecture

qwen3

40 layers

Context

40,960

native (config.json)

License

—

Shipped quantizations

● exact bytes, summed from published files

Quant	Size●	Exact bytes●	Effective bpw●	Tensors●	Publisher
IQ3_XS	2.82 GiB	3,025,960,960	1.639	—	TeichAI
IQ2_XS	4.37 GiB	4,691,590,016	2.541	—	TeichAI
IQ3_M	6.41 GiB	6,883,410,816	3.729	—	TeichAI
IQ4_XS	7.55 GiB	8,110,731,136	4.394	—	TeichAI
Q3_K_S2 shards	12.40 GiB	13,314,212,736	7.212	—	TeichAI
Q3_K_M2 shards	13.64 GiB	14,642,627,456	7.932	—	TeichAI
IQ4_NL2 shards	15.96 GiB	17,138,433,344	9.284	—	TeichAI
Q4_K_M2 shards	16.77 GiB	18,003,508,096	9.752	—	TeichAI
Q8_03 shards	43.86 GiB	47,095,604,096	25.512	—	TeichAI
F162 shards	55.03 GiB	59,086,848,704	32.007	—	TeichAI
BF162 shards	55.03 GiB	59,086,848,896	32.007	—	TeichAI

KV cache by context

computed per layer

Context	KV cache (f16)●	Flat formula	Overstated by	Full / windowed / recurrent
4,096	0.63 GiB	0.63 GiB	—	40 / 0 / 0
8,192	1.25 GiB	1.25 GiB	—	40 / 0 / 0
16,384	2.50 GiB	2.50 GiB	—	40 / 0 / 0
32,768	5.00 GiB	5.00 GiB	—	40 / 0 / 0
65,536	10.00 GiB	10.00 GiB	—	40 / 0 / 0
131,072	20.00 GiB	20.00 GiB	—	40 / 0 / 0

Compare with

same modality, comparable size

vs gemma-4-12B-it-qat-q4_0-unquantized vs gemma-4-E4B-it vs Qwen3-4B vs Qwen3-8B vs Llama-3.2-1B-Instruct vs llama-3-youko-8b 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 7.74 GiB. The real file is 16.77 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

5120

Vocab

151,936

Sliding window

none

SWA period

—

MLA

Experts

—

Experts per token

—

use_sliding_window

false

Questions people ask

How much VRAM does Qwen3-14B-GPT-5.2-High-Reasoning-Distill need?: Q4_K_M is exactly 18,003,508,096 bytes (16.77 GiB) in weights. Add the KV cache, which depends on your context length, plus roughly half a gigabyte of runtime overhead.
How large is Qwen3-14B-GPT-5.2-High-Reasoning-Distill's KV cache?: 5.00 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 Qwen3-14B-GPT-5.2-High-Reasoning-Distill 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.