Mistral AIMistralMistralForCausalLM

Mistral Large Instruct 2411 — Hardware Requirements & GPU Compatibility

Chat

Mistral Large Instruct 2411 is a 122.6B-parameter open language model from Mistral AI in the Mistral family. It supports a context window of up to 131,072 tokens. At Q4_K_M it needs about 74.60 GB of VRAM — see which GPUs and Macs can run it below.

122.6B params · dense131K contextOtherNov 202411.3K downloads288 likes36.3K quant downloads

Your hardware

Verdicts below are for the reference RTX 4090. Set yours to personalise the page.

Detection reads your browser's GPU name with no data sent anywhere.

Mistral Large Instruct 2411 runs on a 96 GB+ Mac or a workstation GPU

Best local pick → Mac Studio (M3 Ultra, 96GB) · Q4_K_M · 79.8 GB · ~8 tok/s

Macs from 64 GB (Q3_K_S · ~10 tok/s)

Score 82.5#83 of 106 open#40 of 62 that fit ≤96 GBOther

Not set up for it?

Reference GPU · RTX 4090 24 GB

Estimates, ±20% · how we estimate

llmrun Composite Score →

82.5

90% range 77.9–87.1
#83 of 106 open models
#40 of 62 that fit ≤96 GB

Benchmarks · tier chart ↓

Among 106 open modelsHow the Composite Score is built

CodingNot enough data yet
AgentsNot enough data yet
MathNot enough data yet
ScienceNot enough data yet
Reasoning86.990% range 77–96

Run Mistral Large Instruct 2411

One recommended way. Every other method, OS and quant is in the step-by-step guide.Each way opens a step-by-step guide for your OS and quant.

Recommended

Ollama

one command · needs Ollama installed

$ollama run hf.co/MaziyarPanahi/Mistral-Large-Instruct-2411-GGUF:Q4_K_M

Q4_K_M · needs ~79.8 GB · 16K context

Download: Mistral-Large-Instruct-2411.Q4_K_M.gguf-00001-of-00007.gguf73.22 GB + 6 partsMaziyarPanahi

install, OS, other quants

Ways to runOther ways

each opens step-by-step

Run in cloud

Runs on RTX PRO 6000 (96 GB) (16 GB headroom) · Q4_K_M

Generation speed: ~16 tok/s; generation speed
Cost per 1M output tokens: $23.71; per 1M output tokens

Deployon Vast.aiBest valuefrom $1.33/hr

Compare GPUs →

or

How Much VRAM Does Mistral Large Instruct 2411 Need?

Select a quantization level; the listed hardware adheres to it.

Quantization	VRAM	+32K	+128K	File	Quality	On RTX 4090 (reference)
	53.1 GB	64.2 GB	99.7 GB	45.2 GB	2-bit · K-quant — 2-bit quantization with K-quant improvements	Does not fit: needs 58.3 GB
	54.7 GB	65.8 GB	101.2 GB	52.8 GB	3-bit small — 3-bit small quantization	Does not fit: needs 59.9 GB
	60.8 GB	71.9 GB	107.3 GB	59.1 GB	3-bit medium — 3-bit medium quantization	Does not fit: needs 66 GB
	63.9 GB	75 GB	110.4 GB	64.6 GB	3-bit large — 3-bit large quantization	Does not fit: needs 69.1 GB
	70.0 GB	81.1 GB	116.5 GB	69.6 GB	4-bit small — 4-bit small quantization	Does not fit: needs 75.2 GB
	74.6 GB	85.7 GB	121.1 GB	73.2 GB	4-bit medium — 4-bit medium quantization — most popular sweet spot	Does not fit: needs 79.8 GB
	85.3 GB	96.4 GB	131.8 GB	84.4 GB	5-bit small — 5-bit small quantization	Does not fit: needs 90.5 GB
	88.4 GB	99.5 GB	134.9 GB	86.5 GB	5-bit medium — 5-bit medium quantization — good quality/size tradeoff	Does not fit: needs 93.6 GB
	102.2 GB	113.3 GB	148.7 GB	~101.2 GB	6-bit, very good — 6-bit quantization, very good quality	Does not fit: needs 107.4 GB
	123.7 GB	134.7 GB	170.2 GB	~122.6 GB	8-bit, near-lossless — 8-bit quantization, near-lossless	Does not fit: needs 128.8 GB
	246.3 GB	257.3 GB	292.8 GB	~245.2 GB	16-bit · bfloat — Brain floating point 16 — preferred for training	Does not fit: needs 251.4 GB

est.calculated, no published file yet

Selected Q4_K_M

4-bit medium quantization

79.8GBat 16K context

Weights: 73.6 GB
KV cache: 5.9 GB
Overhead: 0.3 GB

Doesn't fit RTX 4090 (reference) · needs 55.8 GB more

Or .

Which Hardware Can Run Mistral Large Instruct 2411?

Q4_K_M · 74.6 GB

Mistral Large Instruct 2411 (Q4_K_M) requires 74.6 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 97+ GB is recommended. Using the full 131K context window can add up to 46.5 GB, bringing total usage to 121.1 GB. No consumer GPU has enough memory. 30 devices with unified memory can run Mistral Large Instruct 2411, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB), Mac Studio (M3 Ultra, 96GB).

By VRAM tier · typical GPUs and Macs at Q4_K_M

Typical hardwareQuantVRAMtok/sContext that fits

8–16 GB · RTX 4060, RTX 3060 12GB, RTX 5060 Ti 16GBDoesn't fit — smallest quant needs 58.3 GB8 GB tier →12 GB tier →16 GB tier →

24 GB · RTX 4090referenceDoesn't fit — smallest quant needs 58.3 GB24 GB tier →

Mac 32 GB · Mac Mini M4Doesn't fit — smallest quant needs 58.3 GBMacs →

Mac 64 GB · Mac Studio M4 MaxQ3_K_S · 59.9 GB · ~7 tok/s · 16K59.9~716KMacs →

How good is Mistral Large Instruct 2411?

The llmrun Score merges 5 public benchmark boards into a single figure, where 100 represents the average for open models.

Score vs VRAM in the ≤96 GB tier

Mistral Large Instruct 2411
Other models
Best Score for its VRAM
x: VRAM (GB, log scale) · y: llmrun Score

#40 of 62 that fit ≤96 GB

Each dot is a model at the best quant that fits ≤96 GB. The line steps up to the best Score available at each amount of VRAM; a dot below it is beaten by a model that needs no more memory.

Full ≤96 GB ranking →

Benchmarks

GPQA Diamond
Epoch AI · Nov 2024Independent
51.3%
#54/100 open
Independent
LMArena Text
LMArena · Oct 2026Arena
1305.6
#104/188 open
Arena
AIME 2024/2025
Epoch AI · Nov 2024Independent
7.8%
#65/88 open
Independent
MMLU-Pro
TIGER-LabIndependent
67.9%
#42/146 open
Independent
MATH Level 5
Epoch AI · Nov 2024Independent
50.3%
#14/39 open
Independent
DTBench
Epoch AI · Nov 2024Lab-reported
60.8%
#48/70 open
Lab-reported

All 7 Mistral Large Instruct 2411 benchmarks

In the ≤96 GB class

62 models fit ≤96 GB

Same Score, only models that fit ≤96 GB at their best quant: the ranking a ≤96 GB owner actually chooses from.

#1
MiMo V2.6 Flash RLXiaomi
131.9
~153 tok/s · 93.8 GB
#2
DeepSeek V4 Flash 0731DeepSeek
127.6
~103 tok/s · 95.5 GB
#3
Qwen3.8 27BAlibaba
122.0
~67 tok/s · 17.9 GB
#4
Inkling SmallThinking Machines
119.6
~356 tok/s · 92.9 GB
#5
DeepSeek V4 FlashDeepSeek
115.3
~162 tok/s · 91.4 GB
#6
MiniMax M2.5MiniMax
111.8
~139 tok/s · 93.9 GB

Full ≤96 GB ranking →RTX PRO 6000 Blackwell Workstation Edition page →

Alternatives to Mistral Large Instruct 2411

Mistral family · 35 models →

Official models with an llmrun Score, each answering one question; numbers are at the best quant that fits a 24 GB GPU.

Best alternative at this size
Mistral Medium 3.5 128B
Mistral AI
- 19.6 higher Score
- 3.1 GB more VRAM
Score 102.1 · 82.8 GB
Compare with Mistral Large Instruct 2411 Open Mistral Medium 3.5 128B
Other vendor
Qwen3 235B A22B Thinking 2507
Alibaba
- 25.9 higher Score
- 63.2 GB more VRAM
Score 108.4 · 142.9 GB
Compare with Mistral Large Instruct 2411 Open Qwen3 235B A22B Thinking 2507

Similar models

10tok/s on RTX 4090

Model	Score	VRAM	tok/s	Why it is similar
MiniMax M2.5MiniMax	111.8	139.6 GB	—needs > 24 GB	similar score
Qwen3.5 122B A10BAlibaba	109.4	75.5 GB	—needs > 24 GB	similar score
MiniMax M2.7MiniMax	107.4	139.6 GB	—needs > 24 GB	similar score
MiniMax M2.1MiniMax	106.2	139.6 GB	—needs > 24 GB	similar score
MiniMax M2MiniMax	104.0	139.6 GB	—needs > 24 GB	similar score
Qwen3 235B A22BAlibaba	100.0	142.9 GB	—needs > 24 GB	similar score
Phi 4Microsoft	83.9	12.5 GB	~69	similar score
Qwen2.5 72B InstructAlibaba	82.2	49.3 GB	—needs > 24 GB	similar score
Llama 3.3 70B InstructMeta	80.0	51.3 GB	—needs > 24 GB	similar score
Gemma 3 27B ITGoogle	79.4	21.7 GB	~36	similar score

Specifications

Publisher: Mistral AI
Family: Mistral
Parameters: 122.6B
Architecture: MistralForCausalLM
Context Length: 131,072 tokens
Vocabulary Size: 32,768
Release Date: 2024-11-14
License: Other

Resources

Frequently Asked Questions

How much VRAM does Mistral Large Instruct 2411 need?

Mistral Large Instruct 2411 requires 74.6 GB of VRAM at Q4_K_M, or 246.3 GB at BF16. Full 131K context adds up to 46.5 GB (121.1 GB total).

VRAM = Weights + KV Cache + Overhead

Weights = 122.6B × 4.8 bits ÷ 8 = 73.6 GB

KV Cache + Overhead ≈ 1 GB (at 2K context + ~0.3 GB framework)

Fit ratings and hardware model lists check this model with room for a 16K-token context, which needs a little more memory.

KV Cache + Overhead ≈ 47.5 GB (at full 131K context)

VRAM usage by quantization

Q4_K_M

74.6 GB

Q4_K_M + full context

121.1 GB

Learn more about VRAM estimation →

Can NVIDIA GeForce RTX 5090 run Mistral Large Instruct 2411?

No — Mistral Large Instruct 2411 requires at least 53.1 GB at Q2_K, which exceeds the NVIDIA GeForce RTX 5090's 32 GB of VRAM.

What's the best quantization for Mistral Large Instruct 2411?

For Mistral Large Instruct 2411, Q4_K_M (74.6 GB) offers the best balance of quality and VRAM usage. Q5_K_S (85.3 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 53.1 GB.

VRAM requirement by quantization

Q2_K

53.1 GB~75%

Q3_K_L

63.9 GB~86%

Q4_K_M ★

74.6 GB~89%

Q5_K_S

85.3 GB~92%

Q6_K

102.2 GB~95%

BF16

246.3 GB~100%

★ Recommended — best balance of quality and VRAM usage.

Learn more about quantization →

Can I run Mistral Large Instruct 2411 on a Mac?

Yes — Mac Pro M2 Ultra (64 GB) and 41 other Macs can run Mistral Large Instruct 2411, the smallest at Q3_K_S. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 74.6 GB of usable unified memory (RAM minus macOS overhead), from Mac Studio (M3 Ultra, 96GB).

Can I run Mistral Large Instruct 2411 locally?

Yes — Mistral Large Instruct 2411 can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.

How fast is Mistral Large Instruct 2411?

At Q4_K_M, Mistral Large Instruct 2411 can reach ~64 tok/s on AMD Instinct MI350X. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.

tok/s = (bandwidth GB/s ÷ model GB) × efficiency

Example: NVIDIA B200 → 8000 ÷ 74.6 × 0.65 = ~70 tok/s

Estimated speed at Q4_K_M (74.6 GB)

NVIDIA B200

~70 tok/s

NVIDIA B300

~70 tok/s

AMD Instinct MI350X

~64 tok/s

Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.

Learn more about tok/s estimation →

What's the download size of Mistral Large Instruct 2411?

At Q4_K_M, the download is about 73.57 GB. The full-precision BF16 version is 245.22 GB. The smallest option (Q2_K) is 52.11 GB.

Which GPUs can run Mistral Large Instruct 2411?

No single consumer GPU has enough VRAM to run Mistral Large Instruct 2411 at Q4_K_M (74.6 GB). Multi-GPU or professional hardware is required.

Which devices can run Mistral Large Instruct 2411?

30 devices with unified memory can run Mistral Large Instruct 2411 at Q4_K_M (74.6 GB), including ASUS Ascent GX10, Beelink GTR9 Pro (Ryzen AI Max+ 395, 128 GB), Framework Desktop (Ryzen AI Max+ 395, 128 GB), GMKtec EVO-X2 (Ryzen AI Max+ 395, 128 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.

Run Mistral Large Instruct 2411

79.8 GB VRAM at 16K context

Works on macOS, Windows and Linux.

Install Ollama (Linux)
$curl -fsSL https://ollama.com/install.sh | sh
Install Ollama (macOS / Windows)
Download and run the app; it installs the ollama command.
Download Ollama ↗
Run Q4_K_M
$ollama run hf.co/MaziyarPanahi/Mistral-Large-Instruct-2411-GGUF:Q4_K_M
Raise the context window
Type it inside the chat. For the API server instead, start it with OLLAMA_CONTEXT_LENGTH=16384 ollama serve.
$/set parameter num_ctx 16384
A larger context needs more memory than the weights alone.
Use the API
Ollama serves its API on http://localhost:11434.

Works on macOS, Windows and Linux.

Install LM Studio
Desktop app for macOS (Apple silicon), Windows and Linux.
lmstudio.ai ↗
Download the model
In the app press Ctrl/Cmd + Shift + M and paste https://huggingface.co/MaziyarPanahi/Mistral-Large-Instruct-2411-GGUF, then pick Q4_K_M. Or use the CLI (run LM Studio once first):
$lms get https://huggingface.co/MaziyarPanahi/Mistral-Large-Instruct-2411-GGUF@Q4_K_M
Open on Hugging Face ↗
Load and chat
Open the model loader, select the model and set Context Length to 16384. Leave GPU offload at maximum if it fits.
Start the local server (optional)
$lms server start

Works on macOS, Windows and Linux.

Install llama.cpp (macOS)
MacPorts, Nix and conda-forge also work.
$brew install llama.cpp
Install options ↗
Install llama.cpp (Windows)
$winget install llama.cpp
Install llama.cpp (Linux)
Download the prebuilt llama-*-bin-ubuntu-* archive for your GPU backend (CPU, Vulkan) from the releases page, unpack it and run the binaries from that folder. Homebrew (brew install llama.cpp) and conda-forge also work on Linux.
llama.cpp releases ↗
Start the server
Downloads the model on first run. The chat UI and an OpenAI-compatible API are at http://localhost:8080.
$llama-server -hf MaziyarPanahi/Mistral-Large-Instruct-2411-GGUF:Q4_K_M -c 16384 -ngl 99 --port 8080

Works on macOS, Windows and Linux.

Option A: Docker Model Runner
Docker Desktop: Settings > AI > Enable Docker Model Runner. Docker Engine on Linux: install the docker-model-plugin package.
$docker model run hf.co/MaziyarPanahi/Mistral-Large-Instruct-2411-GGUF:Q4_K_M
Model Runner docs ↗
The quant tag after the repo is how Hugging Face cards write it; if your Docker version rejects it, drop the tag and pick the quant by repo.
Option B: llama.cpp server image (NVIDIA)
Needs the NVIDIA Container Toolkit. Models are cached in the llama-cache volume. Open http://localhost:8080.
$docker run --gpus all -p 8080:8080 -v llama-cache:/root/.cache ghcr.io/ggml-org/llama.cpp:server-cuda -hf MaziyarPanahi/Mistral-Large-Instruct-2411-GGUF:Q4_K_M -c 16384 -ngl 99 --host 0.0.0.0 --port 8080
Image tags (cuda13, vulkan, rocm) ↗
Cache path inside the image is not in the docs; remove the -v flag if the volume complains.

Linux only.

Install vLLM
Linux only; on Windows run it inside WSL2. NVIDIA GPU shown; AMD ROCm, Intel and CPU builds have their own install pages.
$uv venv --python 3.12 --seed
$source .venv/bin/activate
$uv pip install vllm --torch-backend=auto
vLLM installation ↗
Serve the model
OpenAI-compatible API at http://localhost:8000/v1.
$vllm serve mistralai/Mistral-Large-Instruct-2411 --max-model-len 16384
Runs the original weights, not the Q4_K_M GGUF; needs ~270 GB of GPU memory.

Works on macOS, Windows and Linux.

Install Jan
jan.ai ↗
Find the model
Open the Hub tab, paste this model ID in Search, and choose Q4_K_M if offered.
$MaziyarPanahi/Mistral-Large-Instruct-2411-GGUF
Use the local API (optional)
Settings > Local API Server > Start Server. It listens on http://127.0.0.1:1337.

Rent GPUs hourly to run Q4_K_M right there. Pricing comes from partner marketplaces and varies.

Available GPU rentals for Q4_K_M, prioritized by value
GPU	Speed	$/1M tokens	Rent
RTX PRO 6000 Max-Q (96 GB)CheapestCheapest16 GB free	~16 tok/s	$23.71	Deploy on Vast.aifrom $1.33/hr (opens in new tab)	96 GB · 16 GB free · ~16 tok/s · $23.71 / 1M tokens
RTX PRO 6000 (96 GB)16 GB free	~16 tok/s	$27.34	Deploy on Vast.aifrom $1.54/hr (opens in new tab)	96 GB · 16 GB free · ~16 tok/s · $27.34 / 1M tokens
RTX PRO 6000 Server (96 GB)16 GB free	~14 tok/s	$33.77	Deploy on RunPodfrom $1.69/hr (opens in new tab)	96 GB · 16 GB free · ~14 tok/s · $33.77 / 1M tokens
RTX PRO 6000 Server (96 GB)16 GB free	~14 tok/s	$34.73	Deploy on Vast.aifrom $1.74/hr (opens in new tab)	96 GB · 16 GB free · ~14 tok/s · $34.73 / 1M tokens
H200 SXM (141 GB)61 GB free	~42 tok/s	$23.86	Deploy on RunPodfrom $3.59/hr (opens in new tab)	141 GB · 61 GB free · ~42 tok/s · $23.86 / 1M tokens
H200 NVL (141 GB)61 GB free	~42 tok/s	$25.06	Deploy on Vast.aifrom $3.77/hr (opens in new tab)	141 GB · 61 GB free · ~42 tok/s · $25.06 / 1M tokens
B200 (192 GB)112 GB free	~70 tok/s	$23.83	Deploy on RunPodfrom $5.98/hr (opens in new tab)	192 GB · 112 GB free · ~70 tok/s · $23.83 / 1M tokens
B300 (288 GB)208 GB free	~70 tok/s	$27.66	Deploy on RunPodfrom $6.94/hr (opens in new tab)	288 GB · 208 GB free · ~70 tok/s · $27.66 / 1M tokens

Compare GPUs →