How much VRAM does llama2_70b_chat_uncensored need?

Q4_K_M is exactly 41,422,910,400 bytes (38.58 GiB) in weights. Add the KV cache, which depends on context length, plus roughly half a gigabyte of runtime overhead.

How large is llama2_70b_chat_uncensored'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.

jarradh · text

llama2_70b_chat_uncensored

jarradh/llama2_70b_chat_uncensored

llama2_70b_chat_uncensored at Q4_K_M is exactly 41,422,910,400 bytes (38.58 GiB / 41.42 GB) — an effective 4.804 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

69.0B

Architecture

llama

80 layers

Context

2,048

native (config.json)

License

llama2

Shipped quantizations

● exact bytes, summed from published files

Quant	Size●	Exact bytes●	Effective bpw●	Tensors●	Publisher
Q2_K	27.27 GiB	29,279,253,440	3.396	—	TheBloke
Q3_K_S	27.86 GiB	29,919,294,400	3.470	—	TheBloke
Q3_K_M	30.91 GiB	33,186,657,216	3.849	—	TheBloke
Q3_K_L	33.67 GiB	36,147,835,840	4.192	—	TheBloke
Q4_0	36.20 GiB	38,872,249,280	4.508	—	TheBloke
Q4_K_S	36.39 GiB	39,073,575,872	4.532	—	TheBloke
Q4_K_M	38.58 GiB	41,422,910,400	4.804	—	TheBloke
Q5_K_S	44.20 GiB	47,461,397,440	5.505	—	TheBloke
Q5_0	44.20 GiB	47,461,397,440	5.505	—	TheBloke
Q5_K_M	45.41 GiB	48,753,767,360	5.654	—	TheBloke

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 36.13 GiB. The real file is 38.58 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

32,000

Sliding window

none

SWA period

—

MLA

Experts

—

Experts per token

—

use_sliding_window

—

Questions people ask

How much VRAM does llama2_70b_chat_uncensored need?: Q4_K_M is exactly 41,422,910,400 bytes (38.58 GiB) in weights. Add the KV cache, which depends on your context length, plus roughly half a gigabyte of runtime overhead.
How large is llama2_70b_chat_uncensored'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 llama2_70b_chat_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.