Qwen · text

Qwen2.5-Math-72B-Instruct

Qwen/Qwen2.5-Math-72B-Instruct

Qwen2.5-Math-72B-Instruct at Q4_K_M is exactly 47,415,715,232 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 1 file(s)From the file· KV per layer
Parameters
72.7B
Architecture
qwen2
80 layers
Context
4,096
native (config.json)
License
other

Shipped quantizations

● exact bytes, summed from published files
QuantSize●Exact bytes●Effective bpw●Tensors●Publisher
IQ1_M22.11 GiB23,740,212,9282.612—bartowski
IQ2_XXS23.74 GiB25,490,024,1282.805—bartowski
IQ2_XS25.20 GiB27,057,645,2482.977—bartowski
IQ2_M27.32 GiB29,338,986,1763.228—bartowski
Q2_K27.76 GiB29,811,762,8803.280—bartowski
Q2_K_L28.90 GiB31,028,274,8803.414—bartowski
IQ3_XXS29.66 GiB31,845,082,8163.504—bartowski
Q3_K_S32.12 GiB34,487,789,2483.795—bartowski
IQ3_M33.07 GiB35,503,597,2483.906—bartowski
Q3_K_M35.11 GiB37,698,725,5684.148—bartowski
Q3_K_L36.79 GiB39,505,225,1204.347—lmstudio-community
Q3_K_L36.79 GiB39,505,225,4084.347—bartowski
IQ4_XS36.98 GiB39,709,075,1364.369—bartowski
Q4_038.54 GiB41,383,126,7204.553—bartowski
Q4_K_M44.16 GiB47,415,715,2325.217—lmstudio-community
Q4_K_M44.16 GiB47,415,715,5205.217—bartowski
Q5_K_M2 shards50.71 GiB54,447,466,3685.991—bartowski
Q6_K2 shards59.93 GiB64,347,629,1527.080—lmstudio-community
Q6_K2 shards59.93 GiB64,347,629,4407.080—bartowski
Q8_02 shards71.96 GiB77,262,612,0968.501—lmstudio-community
Q8_02 shards71.96 GiB77,262,612,3848.501—bartowski

KV cache by context

computed per layer
ContextKV cache (f16)●Flat formulaOverstated byFull / windowed / recurrent
4,0961.25 GiB1.25 GiB—80 / 0 / 0
8,1922.50 GiB2.50 GiB—80 / 0 / 0
16,3845.00 GiB5.00 GiB—80 / 0 / 0
32,76810.00 GiB10.00 GiB—80 / 0 / 0
65,53620.00 GiB20.00 GiB—80 / 0 / 0
131,07240.00 GiB40.00 GiB—80 / 0 / 0

Compare with

same modality, comparable size
vs Qwen3-Coder-30B-A3B-Instructvs Qwen3.6-27Bvs Qwen3.8-27Bvs gemma-4-E4B-itvs Qwen3-30B-A3B-Thinking-2507vs Qwen3-8BAll alternatives →Will it fit on my card? →

Will it run on your card?

full quant x context sweep
By VRAM:8GB12GB16GB24GB32GB48GB
Radeon RX 6500 XT 4GBGeForce RTX 3050 6GBGeForce RTX 5050 8GBGeForce RTX 3080 10GBGeForce RTX 2080 Ti 11GBGeForce RTX 5070 12GBGeForce RTX 5060 Ti 16GBApple M3 Pro 18GBGeForce RTX 3080 Ti 20GBGeForce RTX 5090 D V2 24GBGeForce RTX 5090 D 32GBApple M5 Max 36GBApple M5 Pro 48GBApple M5 Max 64GBApple M3 Ultra 96GBApple M5 Max 128GBApple M2 Ultra 192GBApple M3 Ultra 256GBApple M3 Ultra 512GB

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
80
Attention heads
64
KV heads
8
Head dim
128
Hidden size
8192
Vocab
152,064
Sliding window
4096
SWA period
—
MLA
no
Experts
—
Experts per token
—
use_sliding_window
false

This model declares a sliding window but sets use_sliding_window: false, so the window is not applied. Honouring the field without the flag understates KV for the whole family.

Questions people ask

How much VRAM does Qwen2.5-Math-72B-Instruct need?
Q4_K_M is exactly 47,415,715,232 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 Qwen2.5-Math-72B-Instruct'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 Qwen2.5-Math-72B-Instruct 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.