How much VRAM does Mistral-Large-Instruct-2411 need?

Q4_K_M is exactly 73,219,623,136 bytes (68.19 GiB) in weights. Add the KV cache, which depends on context length, plus roughly half a gigabyte of runtime overhead.

How large is Mistral-Large-Instruct-2411's KV cache?

11.00 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.

mistralai · text

Mistral-Large-Instruct-2411

mistralai/Mistral-Large-Instruct-2411

Mistral-Large-Instruct-2411 at Q4_K_M is exactly 73,219,623,136 bytes (68.19 GiB / 73.22 GB) — an effective 4.777 bits per weight, not the nominal 4. Its KV cache at 32K is 11.00 GiB.

From the file· summed from 2 file(s)From the file· KV per layer

Parameters

123B

Architecture

llama

88 layers

Context

131,072

native (config.json)

License

—

Shipped quantizations

● exact bytes, summed from published files

Quant	Size●	Exact bytes●	Effective bpw●	Tensors●	Publisher
IQ1_M	26.44 GiB	28,386,314,528	1.852	—	bartowski
IQ2_XXS	30.20 GiB	32,430,541,088	2.116	—	bartowski
IQ2_XS	33.60 GiB	36,081,158,432	2.354	—	bartowski
IQ2_M	38.76 GiB	41,619,605,792	2.716	—	bartowski
Q2_K	42.09 GiB	45,196,298,272	2.949	—	MaziyarPanahi
Q2_K	42.09 GiB	45,196,298,528	2.949	—	bartowski
Q2_K_L	42.46 GiB	45,589,514,528	2.975	—	bartowski
IQ3_XXS	43.78 GiB	47,009,024,288	3.067	—	bartowski
Q3_K_S2 shards	49.22 GiB	52,849,854,976	3.448	—	bartowski
IQ3_M2 shards	51.48 GiB	55,276,390,880	3.607	—	bartowski
Q3_K_M2 shards	55.04 GiB	59,102,775,808	3.856	—	bartowski
Q3_K_L2 shards	60.12 GiB	64,554,322,144	4.212	—	lmstudio-community
Q3_K_L2 shards	60.12 GiB	64,554,322,432	4.212	—	bartowski
IQ4_XS2 shards	60.94 GiB	65,434,339,840	4.269	—	bartowski
Q4_02 shards	64.56 GiB	69,322,459,648	4.523	—	bartowski
Q4_K_S2 shards	64.79 GiB	69,570,972,160	4.539	—	bartowski
Q4_K_M2 shards	68.19 GiB	73,219,623,136	4.777	—	lmstudio-community
Q4_K_M2 shards	68.19 GiB	73,219,623,424	4.777	—	bartowski
Q5_K_S3 shards	78.56 GiB	84,355,893,856	5.504	—	bartowski
Q5_K_M3 shards	80.55 GiB	86,488,304,224	5.643	—	bartowski
Q6_K3 shards	93.68 GiB	100,586,277,184	6.563	—	lmstudio-community
Q6_K3 shards	93.68 GiB	100,586,277,472	6.563	—	bartowski
Q8_04 shards	121.33 GiB	130,280,376,800	8.501	—	lmstudio-community
Q8_04 shards	121.33 GiB	130,280,376,800	8.501	—	bartowski

KV cache by context

computed per layer

Context	KV cache (f16)●	Flat formula	Overstated by	Full / windowed / recurrent
4,096	1.38 GiB	1.38 GiB	—	88 / 0 / 0
8,192	2.75 GiB	2.75 GiB	—	88 / 0 / 0
16,384	5.50 GiB	5.50 GiB	—	88 / 0 / 0
32,768	11.00 GiB	11.00 GiB	—	88 / 0 / 0
65,536	22.00 GiB	22.00 GiB	—	88 / 0 / 0
131,072	44.00 GiB	44.00 GiB	—	88 / 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 64.23 GiB. The real file is 68.19 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

12288

Vocab

32,768

Sliding window

none

SWA period

—

MLA

Experts

—

Experts per token

—

use_sliding_window

—

Questions people ask

How much VRAM does Mistral-Large-Instruct-2411 need?: Q4_K_M is exactly 73,219,623,136 bytes (68.19 GiB) in weights. Add the KV cache, which depends on your context length, plus roughly half a gigabyte of runtime overhead.
How large is Mistral-Large-Instruct-2411's KV cache?: 11.00 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 Mistral-Large-Instruct-2411 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.