How much VRAM does Chuluun-Qwen2.5-72B-v0.01 need?

Q4_K_M is exactly 47,415,714,592 bytes (44.16 GiB) in weights. Add the KV cache, which depends on context length, plus roughly half a gigabyte of runtime overhead.

How large is Chuluun-Qwen2.5-72B-v0.01's KV cache?

10.00 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.

DatToad · text

Chuluun-Qwen2.5-72B-v0.01

DatToad/Chuluun-Qwen2.5-72B-v0.01

Chuluun-Qwen2.5-72B-v0.01 at Q4_K_M is exactly 47,415,714,592 bytes (44.16 GiB / 47.42 GB) — an effective 5.217 bits per weight, not the nominal 4. Its KV cache at 32K is 10.00 GiB.

From the file· summed from 10 file(s)From the file· KV per layer

Parameters

72.7B

Architecture

qwen2

80 layers

Context

131,072

native (config.json)

License

—

Shipped quantizations

● exact bytes, summed from published files

Quant	Size●	Exact bytes●	Effective bpw●	Tensors●	Publisher
Q2_K6 shards	27.76 GiB	29,811,761,536	3.280	—	featherless-ai-quants
Q3_K_S7 shards	32.12 GiB	34,487,788,000	3.795	—	featherless-ai-quants
Q3_K_M8 shards	35.11 GiB	37,698,724,480	4.148	—	featherless-ai-quants
Q3_K_L9 shards	36.79 GiB	39,505,224,384	4.347	—	featherless-ai-quants
IQ4_XS9 shards	37.40 GiB	40,163,238,624	4.419	—	featherless-ai-quants
Q4_K_S9 shards	40.88 GiB	43,889,222,400	4.829	—	featherless-ai-quants
Q4_K_M10 shards	44.16 GiB	47,415,714,592	5.217	—	featherless-ai-quants
Q5_K_S11 shards	47.85 GiB	51,375,137,696	5.653	—	featherless-ai-quants
Q5_K_M12 shards	50.71 GiB	54,447,465,664	5.991	—	featherless-ai-quants
Q6_K14 shards	59.93 GiB	64,347,628,832	7.080	—	featherless-ai-quants
Q8_016 shards	71.96 GiB	77,262,612,064	8.501	—	featherless-ai-quants

KV cache by context

computed per layer

Context	KV cache (f16)●	Flat formula	Overstated by	Full / windowed / recurrent
4,096	1.25 GiB	1.25 GiB	—	80 / 0 / 0
8,192	2.50 GiB	2.50 GiB	—	80 / 0 / 0
16,384	5.00 GiB	5.00 GiB	—	80 / 0 / 0
32,768	10.00 GiB	10.00 GiB	—	80 / 0 / 0
65,536	20.00 GiB	20.00 GiB	—	80 / 0 / 0
131,072	40.00 GiB	40.00 GiB	—	80 / 0 / 0

Compare with

same modality, comparable size

vs Qwen3-Coder-30B-A3B-Instruct vs Qwen3.6-27B vs Qwen3.8-27B vs gemma-4-E4B-it vs Qwen3-30B-A3B-Thinking-2507 vs Qwen3-8B 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 38.09 GiB. The real file is 44.16 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

8192

Vocab

152,064

Sliding window

none

SWA period

—

MLA

Experts

—

Experts per token

—

use_sliding_window

false

Questions people ask

How much VRAM does Chuluun-Qwen2.5-72B-v0.01 need?: Q4_K_M is exactly 47,415,714,592 bytes (44.16 GiB) in weights. Add the KV cache, which depends on your context length, plus roughly half a gigabyte of runtime overhead.
How large is Chuluun-Qwen2.5-72B-v0.01's KV cache?: 10.00 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 Chuluun-Qwen2.5-72B-v0.01 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.