Mistral AIMistralMistralForCausalLM

Mistral 7B Instruct v0.2 — Hardware Requirements & GPU Compatibility

Chat

Mistral 7B Instruct v0.2 is a 7.2-billion-parameter instruction-tuned language model from Mistral AI, built for general chat, question answering, and instruction following. It refines the original Mistral 7B with better adherence to complex prompts and improved handling of longer inputs. Its compact size suits local deployment on modern consumer GPUs, running comfortably on mainstream hardware once quantized. The model supports a 32,768 token context window, a result of raising the RoPE base frequency used for positional encoding, which improved handling of longer inputs versus the original v0.1. It is released under the Apache 2.0 license, allowing unrestricted commercial and research use. Published in December 2023, it became one of the most widely adopted 7B open-weight chat models, still supported by tools such as llama.cpp, vLLM, and Ollama.

7.2B params · dense33K contextApache 2.0Dec 20231.6M downloads3.3K likes68.3K 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.

S

Runs great on a 24 GB GPU

Runs from 8 GB (Q4_K_M · 16K)Best on 24 GB (Q4_K_M · ~133 tok/s · 32K)Macs from 8 GB (IQ2_XXS · ~28 tok/s)

Apache 2.0

Reference GPU · RTX 4090 24 GB

Estimates, ±20% · how we estimate

Run Mistral 7B Instruct v0.2

One recommended way. Every other method, OS and quant is in the step-by-step guide.

Recommended

Ollama

one command · needs Ollama installed

$ollama run mistral:7b-instruct-v0.2-q4_K_M

Q4_K_M fits fully on the RTX 4090 · 17.2 GB free · 16K context

Download: mistral-7b-instruct-v0.2.Q4_K_M.gguf4.37 GBTheBloke

install, OS, other quants

Other ways

each opens step-by-step

Run in cloud

Fits on RTX 3060 12GB (5 GB headroom) · Q4_K_M

Generation speed: ~48 tok/s; generation speed
Cost per 1M output tokens: $0.55; per 1M output tokens

Deployon Vast.aiBest optionfrom $0.095/hr

Compare GPUs →

or

How Much VRAM Does Mistral 7B Instruct v0.2 Need?

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

Quantization	VRAM	+32K	+128K	File	Quality	On RTX 4090 (reference)
	2.6 GB	6.6 GB	—	2 GB	2-bit · i-quant extreme compression — Importance-weighted 2-bit, extreme compression — significant quality loss	Fits: 32K context · ~256 tok/s
	2.7 GB	6.8 GB	—	2.2 GB	2-bit · i-quant extra small — Importance-weighted 2-bit, extra small	Fits: 32K context · ~239 tok/s
	2.8 GB	6.9 GB	—	2.3 GB	2-bit · i-quant small — Importance-weighted 2-bit, small	Fits: 32K context · ~232 tok/s
	3.0 GB	7 GB	—	2.5 GB	2-bit · i-quant medium — Importance-weighted 2-bit, medium	Fits: 32K context · ~218 tok/s
	3.4 GB	7.4 GB	—	2.8 GB	3-bit · i-quant — Importance-weighted 3-bit	Fits: 32K context · ~194 tok/s
	3.6 GB	7.6 GB	—	3 GB	3-bit · i-quant extra small — Importance-weighted 3-bit, extra small	Fits: 32K context · ~184 tok/s
	3.6 GB	7.7 GB	—	3.2 GB	3-bit · i-quant small — Importance-weighted 3-bit, small	Fits: 32K context · ~180 tok/s
	3.6 GB	7.7 GB	—	3.1 GB	2-bit · K-quant — 2-bit quantization with K-quant improvements	Fits: 32K context · ~180 tok/s
	3.7 GB	7.8 GB	—	3.2 GB	3-bit small — 3-bit small quantization	Fits: 32K context · ~175 tok/s
	3.8 GB	7.9 GB	—	3.3 GB	3-bit · i-quant medium — Importance-weighted 3-bit, medium	Fits: 32K context · ~171 tok/s
	4.1 GB	8.1 GB	—	3.5 GB	3-bit medium — 3-bit medium quantization	Fits: 32K context · ~160 tok/s
	4.2 GB	8.2 GB	—	4.1 GB	4-bit · legacy — 4-bit legacy quantization	Fits: 32K context · ~156 tok/s
	4.3 GB	8.3 GB	—	3.8 GB	3-bit large — 3-bit large quantization	Fits: 32K context · ~153 tok/s
	4.5 GB	8.5 GB	—	3.9 GB	4-bit · i-quant compact — Importance-weighted 4-bit, compact	Fits: 32K context · ~147 tok/s
	4.6 GB	8.7 GB	—	4.1 GB	4-bit small — 4-bit small quantization	Fits: 32K context · ~141 tok/s
	4.6 GB	8.7 GB	—	4.6 GB	4-bit · legacy+ — 4-bit legacy quantization with offset	Fits: 32K context · ~141 tok/s
	4.9 GB	8.9 GB	—	4.4 GB	4-bit medium — 4-bit medium quantization — most popular sweet spot	Fits: 32K context · ~133 tok/s
	5.1 GB	9.1 GB	—	5 GB	5-bit · legacy — 5-bit legacy quantization	Fits: 32K context · ~129 tok/s
	5.5 GB	9.6 GB	—	5.4 GB	5-bit · legacy+ — 5-bit legacy quantization with offset	Fits: 32K context · ~118 tok/s
	5.5 GB	9.6 GB	—	5 GB	5-bit small — 5-bit small quantization	Fits: 32K context · ~118 tok/s
	5.7 GB	9.8 GB	—	5.1 GB	5-bit medium — 5-bit medium quantization — good quality/size tradeoff	Fits: 32K context · ~114 tok/s
	6.5 GB	10.6 GB	—	5.9 GB	6-bit, very good — 6-bit quantization, very good quality	Fits: 32K context · ~100 tok/s
	7.8 GB	11.8 GB	—	7.7 GB	8-bit, near-lossless — 8-bit quantization, near-lossless	Fits: 32K context · ~84 tok/s
	15.1 GB	19.1 GB	—	14.5 GB	16-bit · bfloat — Brain floating point 16 — preferred for training	Fits: 32K context · ~44 tok/s

Selected Q4_K_M

4-bit medium quantization

6.8GBat 16K context

Weights: 4.3 GB
KV cache: 2.2 GB
Overhead: 0.3 GB

Fits RTX 4090 (reference) · 17.2 GB free · ~133 tok/s

≥50 tok/s needs ≥377 GB/s · RTX 5090 ~237, RTX 3090 Ti ~133

Which Hardware Can Run Mistral 7B Instruct v0.2?

Q4_K_M · 4.9 GB

Mistral 7B Instruct v0.2 (Q4_K_M) requires 4.9 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 7+ GB is recommended. Using the full 33K context window can add up to 4.0 GB, bringing total usage to 8.9 GB. 52 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti. 151 devices with unified memory can run Mistral 7B Instruct v0.2, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB).

By VRAM tier · typical GPUs and Macs at Q4_K_M

Typical hardwareQuantVRAMtok/sContext that fits

8 GB · RTX 4060Q4_K_M · 6.8 GB · ~36 tok/s · 16K6.8~3616K8 GB tier →

12 GB · RTX 3060 12GBQ4_K_M · 6.8 GB · ~48 tok/s · 32K6.8~4832K12 GB tier →

16 GB · RTX 5060 Ti 16GBQ4_K_M · 6.8 GB · ~59 tok/s · 32K6.8~5932K16 GB tier →

24 GB · RTX 4090referenceQ4_K_M · 6.8 GB · ~133 tok/s · 32K6.8~13332K24 GB tier →

Mac 32 GB · Mac Mini M4Q4_K_M · 6.8 GB · ~17 tok/s · 32K6.8~1732KMacs →

Mac 64 GB · Mac Studio M4 MaxQ4_K_M · 6.8 GB · ~78 tok/s · 32K6.8~7832KMacs →

How good is Mistral 7B Instruct v0.2?

llmrun Score blends public benchmark boards into one number; 100 = the average open model.

Not enough data yet for an llmrun Score.

A Score needs results on enough independent boards. How the Composite Score is built

Benchmarks

LMArena Text
LMArena · Oct 2026Arena
1149.5
#168/187 open
Arena
MMLU-Pro
TIGER-LabIndependent
30.8%
#119/145 open
Independent
MMLU
Epoch AI · Dec 2023Lab-reported
62.5%
#43/85 open
Lab-reported
GSM8K
Epoch AI · Dec 2023Lab-reported
35.4%
#40/62 open
Lab-reported
BoolQ
Epoch AI · Dec 2023Lab-reported
83.2%
#10/38 open
Lab-reported
PIQA
Epoch AI · Dec 2023Lab-reported
82.2%
#14/40 open
Lab-reported

All 6 Mistral 7B Instruct v0.2 benchmarks

Alternatives to Mistral 7B Instruct v0.2

Mistral family · 34 models →

Similar models

6tok/s on RTX 4090

Model	Score	VRAM	tok/s	Why it is similar
Qwen2.5 7B InstructAlibaba	65.1	5.8 GB	~131	same size
Olmo 3 7B InstructAllen AI	—	8.4 GB	~114	same size
Phi Mini MoE InstructMicrosoft	—	5.4 GB	~239	same size
Falcon H1 7B InstructTII UAE	—	6.3 GB	~130	same size
DeepSeek R1 Distill Qwen 7BDeepSeek	—	5.8 GB	~131	same size
Eurus 2 7B PRIMEPRIME-RL	—	5.1 GB	~131	same size

Fine-tunes & variants(3)community builds of Mistral 7B Instruct v0.2

Specifications

Publisher: Mistral AI
Family: Mistral
Parameters: 7.2B
Architecture: MistralForCausalLM
Context Length: 32,768 tokens
Vocabulary Size: 32,000
Release Date: 2023-12-11
License: Apache 2.0

Resources

Frequently Asked Questions

How much VRAM does Mistral 7B Instruct v0.2 need?

Mistral 7B Instruct v0.2 requires 4.9 GB of VRAM at Q4_K_M, or 15.1 GB at BF16. Full 33K context adds up to 4.0 GB (8.9 GB total).

VRAM = Weights + KV Cache + Overhead

Weights = 7.2B × 4.8 bits ÷ 8 = 4.3 GB

KV Cache + Overhead ≈ 0.6 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 ≈ 4.6 GB (at full 33K context)

VRAM usage by quantization

Q4_K_M

4.9 GB

Q4_K_M + full context

8.9 GB

Learn more about VRAM estimation →

What's the best quantization for Mistral 7B Instruct v0.2?

For Mistral 7B Instruct v0.2, Q4_K_M (4.9 GB) offers the best balance of quality and VRAM usage. Q5_0 (5.1 GB) provides better quality if you have the VRAM. The smallest option is IQ2_XXS at 2.6 GB.

VRAM requirement by quantization

IQ2_XXS

2.6 GB~53%

IQ3_S

3.6 GB~75%

Q3_K_L

4.3 GB~86%

Q4_K_M ★

4.9 GB~89%

Q5_0

5.1 GB~90%

BF16

15.1 GB~100%

★ Recommended — best balance of quality and VRAM usage.

Learn more about quantization →

Can I run Mistral 7B Instruct v0.2 on a Mac?

Yes — MacBook Air 13" M3 (8 GB) and 145 other Macs can run Mistral 7B Instruct v0.2, the smallest at IQ2_XXS. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 4.9 GB of usable unified memory (RAM minus macOS overhead), from Mac Mini M2 Pro (16 GB).

Can I run Mistral 7B Instruct v0.2 locally?

Yes — Mistral 7B Instruct v0.2 can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.

How fast is Mistral 7B Instruct v0.2?

At Q4_K_M, Mistral 7B Instruct v0.2 can reach ~978 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~133 tok/s. 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 ÷ 4.91 × 0.65 = ~1059 tok/s

Estimated speed at Q4_K_M (4.9 GB)

NVIDIA B200

~1059 tok/s

NVIDIA GeForce RTX 4090

~133 tok/s

NVIDIA B300

~1059 tok/s

AMD Instinct MI350X

~978 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 7B Instruct v0.2?

At Q4_K_M, the download is about 4.35 GB. The full-precision BF16 version is 14.48 GB. The smallest option (IQ2_XXS) is 1.99 GB.

Which GPUs can run Mistral 7B Instruct v0.2?

52 consumer GPUs can run Mistral 7B Instruct v0.2 at Q4_K_M. Top options include AMD Radeon RX 6700 XT, AMD Radeon RX 6800, AMD Radeon RX 6800 XT. 52 GPUs have plenty of headroom for comfortable inference.

Which devices can run Mistral 7B Instruct v0.2?

151 devices with unified memory can run Mistral 7B Instruct v0.2 at Q4_K_M (4.9 GB), including AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10, Beelink GTR9 Pro (Ryzen AI Max+ 395, 128 GB), Framework Desktop (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 7B Instruct v0.2

6.8 GB VRAM at 16K context · fits the RTX 4090 (17.2 GB free)

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 mistral:7b-instruct-v0.2-q4_K_M
Official Ollama library build. For the exact Q4_K_M file from TheBloke/Mistral-7B-Instruct-v0.2-GGUF: ollama run hf.co/TheBloke/Mistral-7B-Instruct-v0.2-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/TheBloke/Mistral-7B-Instruct-v0.2-GGUF, then pick Q4_K_M. Or use the CLI (run LM Studio once first):
$lms get https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.2-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 TheBloke/Mistral-7B-Instruct-v0.2-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/TheBloke/Mistral-7B-Instruct-v0.2-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 TheBloke/Mistral-7B-Instruct-v0.2-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-7B-Instruct-v0.2 --max-model-len 16384
Runs the original weights, not the Q4_K_M GGUF; needs ~16 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.
$TheBloke/Mistral-7B-Instruct-v0.2-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 3060 12GBCheapestCheapest5 GB free	~48 tok/s	$0.55	Deploy on Vast.aifrom $0.095/hr (opens in new tab)	5 GB free · ~48 tok/s · $0.55 / 1M tokens
RTX A4000 (16 GB)9 GB free	~59 tok/s	$0.57	Deploy on Vast.aifrom $0.12/hr (opens in new tab)	16 GB · 9 GB free · ~59 tok/s · $0.57 / 1M tokens
Tesla P40 (24 GB)17 GB free	~46 tok/s	$0.74	Deploy on Vast.aifrom $0.12/hr (opens in new tab)	24 GB · 17 GB free · ~46 tok/s · $0.74 / 1M tokens
Tesla V100 PCIe 16GB9 GB free	~119 tok/s	$0.29	Deploy on Vast.aifrom $0.12/hr (opens in new tab)	9 GB free · ~119 tok/s · $0.29 / 1M tokens
RTX A5000 (24 GB)17 GB free	~102 tok/s	$0.44	Deploy on RunPodfrom $0.16/hr (opens in new tab)	24 GB · 17 GB free · ~102 tok/s · $0.44 / 1M tokens
RTX 3080 Ti (12 GB)5 GB free	~121 tok/s	$0.41	Deploy on RunPodfrom $0.18/hr (opens in new tab)	12 GB · 5 GB free · ~121 tok/s · $0.41 / 1M tokens
Tesla V100 PCIe 16GB9 GB free	~119 tok/s	$0.44	Deploy on RunPodfrom $0.19/hr (opens in new tab)	9 GB free · ~119 tok/s · $0.44 / 1M tokens
RTX 3090 (24 GB)17 GB free	~124 tok/s	$0.49	Deploy on RunPodfrom $0.22/hr (opens in new tab)	24 GB · 17 GB free · ~124 tok/s · $0.49 / 1M tokens

Compare GPUs →