How much VRAM does mistral-7b-uncensored need?

Q4_K_M is exactly 4,368,440,640 bytes (4.07 GiB) in weights. Add the KV cache, which depends on context length, plus roughly half a gigabyte of runtime overhead.

luvGPT · text

mistral-7b-uncensored

luvGPT/mistral-7b-uncensored

mistral-7b-uncensored at Q4_K_M is exactly 4,368,440,640 bytes (4.07 GiB / 4.37 GB) — an effective 4.826 bits per weight, not the nominal 4.

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

Parameters

7.2B

Architecture

llama

32 layers

Context

32,768

native (config.json)

License

apache-2.0

Shipped quantizations

● exact bytes, summed from published files

Quant	Size●	Exact bytes●	Effective bpw●	Tensors●	Publisher
Q2_K	2.53 GiB	2,719,243,584	3.004	—	mradermacher
IQ3_XS	2.81 GiB	3,018,816,832	3.335	—	mradermacher
Q3_K_S	2.95 GiB	3,164,568,896	3.496	—	mradermacher
IQ3_S	2.96 GiB	3,182,394,688	3.516	—	mradermacher
IQ3_M	3.06 GiB	3,284,892,992	3.629	—	mradermacher
Q3_K_M	3.28 GiB	3,518,987,584	3.888	—	mradermacher
Q3_K_L	3.56 GiB	3,822,026,048	4.222	—	mradermacher
IQ4_XS	3.67 GiB	3,944,389,952	4.357	—	mradermacher
Q4_K_S	3.86 GiB	4,140,375,360	4.574	—	mradermacher
Q4_K_M	4.07 GiB	4,368,440,640	4.826	—	mradermacher
Q5_K_S	4.65 GiB	4,997,717,312	5.521	—	mradermacher
Q5_K_M	4.78 GiB	5,131,410,752	5.669	—	mradermacher
Q6_K	5.53 GiB	5,942,066,496	6.564	—	mradermacher
Q8_0	7.17 GiB	7,695,859,008	8.502	—	mradermacher
F16	13.49 GiB	14,484,733,248	16.001	—	mradermacher

KV cache by context

unresolved

This model declares a 4,096-token sliding window, but we could not establish which layers use it. Its architecture publishes the layout as a per-layer array inside the model file rather than as a period in config.json, and we have not yet ingested that array.

A flat context × layers × heads figure would be substantially too high, so we are not showing one. This is tracked as a known gap rather than filled with a guess.

Compare with

same modality, comparable size

vs gemma-4-E4B-it vs Qwen3-4B vs Qwen3-8B vs HyperCLOVAX-SEED-Text-Instruct-1.5B 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 3.79 GiB. The real file is 4.07 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

4096

Vocab

32,000

Sliding window

4096

SWA period

—

MLA

Experts

—

Experts per token

—

use_sliding_window

—

Questions people ask

How much VRAM does mistral-7b-uncensored need?: Q4_K_M is exactly 4,368,440,640 bytes (4.07 GiB) in weights. Add the KV cache, which depends on your context length, plus roughly half a gigabyte of runtime overhead.
Which quantization of mistral-7b-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.