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
QuantSize●Exact bytes●Effective bpw●Tensors●Publisher
IQ1_M26.44 GiB28,386,314,5281.852—bartowski
IQ2_XXS30.20 GiB32,430,541,0882.116—bartowski
IQ2_XS33.60 GiB36,081,158,4322.354—bartowski
IQ2_M38.76 GiB41,619,605,7922.716—bartowski
Q2_K42.09 GiB45,196,298,2722.949—MaziyarPanahi
Q2_K42.09 GiB45,196,298,5282.949—bartowski
Q2_K_L42.46 GiB45,589,514,5282.975—bartowski
IQ3_XXS43.78 GiB47,009,024,2883.067—bartowski
Q3_K_S2 shards49.22 GiB52,849,854,9763.448—bartowski
IQ3_M2 shards51.48 GiB55,276,390,8803.607—bartowski
Q3_K_M2 shards55.04 GiB59,102,775,8083.856—bartowski
Q3_K_L2 shards60.12 GiB64,554,322,1444.212—lmstudio-community
Q3_K_L2 shards60.12 GiB64,554,322,4324.212—bartowski
IQ4_XS2 shards60.94 GiB65,434,339,8404.269—bartowski
Q4_02 shards64.56 GiB69,322,459,6484.523—bartowski
Q4_K_S2 shards64.79 GiB69,570,972,1604.539—bartowski
Q4_K_M2 shards68.19 GiB73,219,623,1364.777—lmstudio-community
Q4_K_M2 shards68.19 GiB73,219,623,4244.777—bartowski
Q5_K_S3 shards78.56 GiB84,355,893,8565.504—bartowski
Q5_K_M3 shards80.55 GiB86,488,304,2245.643—bartowski
Q6_K3 shards93.68 GiB100,586,277,1846.563—lmstudio-community
Q6_K3 shards93.68 GiB100,586,277,4726.563—bartowski
Q8_04 shards121.33 GiB130,280,376,8008.501—lmstudio-community
Q8_04 shards121.33 GiB130,280,376,8008.501—bartowski

KV cache by context

computed per layer
ContextKV cache (f16)●Flat formulaOverstated byFull / windowed / recurrent
4,0961.38 GiB1.38 GiB—88 / 0 / 0
8,1922.75 GiB2.75 GiB—88 / 0 / 0
16,3845.50 GiB5.50 GiB—88 / 0 / 0
32,76811.00 GiB11.00 GiB—88 / 0 / 0
65,53622.00 GiB22.00 GiB—88 / 0 / 0
131,07244.00 GiB44.00 GiB—88 / 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 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
88
Attention heads
96
KV heads
8
Head dim
128
Hidden size
12288
Vocab
32,768
Sliding window
none
SWA period
—
MLA
no
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.