How much VRAM does Qwen2.5-Coder-7B-Instruct-Uncensored need?

Q4_K_M is exactly 4,683,073,536 bytes (4.36 GiB) in weights. Add the KV cache, which depends on context length, plus roughly half a gigabyte of runtime overhead.

How large is Qwen2.5-Coder-7B-Instruct-Uncensored's KV cache?

1.75 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.

BlossomsAI · text

Qwen2.5-Coder-7B-Instruct-Uncensored

BlossomsAI/Qwen2.5-Coder-7B-Instruct-Uncensored

Qwen2.5-Coder-7B-Instruct-Uncensored at Q4_K_M is exactly 4,683,073,536 bytes (4.36 GiB / 4.68 GB) — an effective 4.919 bits per weight, not the nominal 4. Its KV cache at 32K is 1.75 GiB.

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

Parameters

7.6B

Architecture

qwen2

28 layers

Context

32,768

native (config.json)

License

mit

Shipped quantizations

● exact bytes, summed from published files

Quant	Size●	Exact bytes●	Effective bpw●	Tensors●	Publisher
Q2_K	2.81 GiB	3,015,940,096	3.168	—	BlossomsAI
Q3_K_M	3.55 GiB	3,808,391,168	4.001	—	BlossomsAI
Q4_K_S	4.15 GiB	4,457,768,960	4.683	—	BlossomsAI
Q4_K_M	4.36 GiB	4,683,073,536	4.919	—	BlossomsAI
Q5_K_S	4.95 GiB	5,315,176,448	5.583	—	BlossomsAI
Q5_K_M	5.07 GiB	5,444,831,232	5.720	—	BlossomsAI
Q6_K	5.82 GiB	6,254,198,784	6.570	—	BlossomsAI
Q8_0	7.54 GiB	8,098,525,184	8.507	—	BlossomsAI

KV cache by context

computed per layer

Context	KV cache (f16)●	Flat formula	Overstated by	Full / windowed / recurrent
4,096	0.22 GiB	0.22 GiB	—	28 / 0 / 0
8,192	0.44 GiB	0.44 GiB	—	28 / 0 / 0
16,384	0.88 GiB	0.88 GiB	—	28 / 0 / 0
32,768	1.75 GiB	1.75 GiB	—	28 / 0 / 0
65,536	3.50 GiB	3.50 GiB	—	28 / 0 / 0
131,072	7.00 GiB	7.00 GiB	—	28 / 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 3.99 GiB. The real file is 4.36 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

3584

Vocab

152,064

Sliding window

none

SWA period

—

MLA

Experts

—

Experts per token

—

use_sliding_window

false

Questions people ask

How much VRAM does Qwen2.5-Coder-7B-Instruct-Uncensored need?: Q4_K_M is exactly 4,683,073,536 bytes (4.36 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-Coder-7B-Instruct-Uncensored's KV cache?: 1.75 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-Coder-7B-Instruct-Uncensored 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.