How much VRAM does Qwen3-32B-qweh2 need?

Q5_K_M is exactly 23,214,827,360 bytes (21.62 GiB) in weights. Add the KV cache, which depends on context length, plus roughly half a gigabyte of runtime overhead.

How large is Qwen3-32B-qweh2's KV cache?

8.00 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.

BusRune · text

Qwen3-32B-qweh2

BusRune/Qwen3-32B-qweh2

Qwen3-32B-qweh2 at Q5_K_M is exactly 23,214,827,360 bytes (21.62 GiB / 23.21 GB) — an effective 5.669 bits per weight, not the nominal 5. Its KV cache at 32K is 8.00 GiB.

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

Parameters

32.8B

Architecture

qwen3

64 layers

Context

40,960

native (config.json)

License

wtfpl

Shipped quantizations

● exact bytes, summed from published files

Quant	Size●	Exact bytes●	Effective bpw●	Tensors●	Publisher
Q5_K_M	21.62 GiB	23,214,827,360	5.669	—	BusRune

KV cache by context

computed per layer

Context	KV cache (f16)●	Flat formula	Overstated by	Full / windowed / recurrent
4,096	1.00 GiB	1.00 GiB	—	64 / 0 / 0
8,192	2.00 GiB	2.00 GiB	—	64 / 0 / 0
16,384	4.00 GiB	4.00 GiB	—	64 / 0 / 0
32,768	8.00 GiB	8.00 GiB	—	64 / 0 / 0
65,536	16.00 GiB	16.00 GiB	—	64 / 0 / 0
131,072	32.00 GiB	32.00 GiB	—	64 / 0 / 0

Compare with

same modality, comparable size

vs Qwen3-Coder-30B-A3B-Instruct vs Qwen-AgentWorld-35B-A3B vs gpt-oss-20b vs Qwen3-8B vs Qwen3-VL-8B-Instruct-abliterated-v1 vs UI-TARS-1.5-7B All alternatives →Will it fit on my card? →

Why other calculators give a different number

A parameters × bits ÷ 8 estimate puts Q5_K_M at roughly 17.16 GiB. The real file is 21.62 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 Qwen3-32B-qweh2 need?: Q5_K_M is exactly 23,214,827,360 bytes (21.62 GiB) in weights. Add the KV cache, which depends on your context length, plus roughly half a gigabyte of runtime overhead.
How large is Qwen3-32B-qweh2's KV cache?: 8.00 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 Qwen3-32B-qweh2 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.