Instructions to use smarttasks/Mistral-Small-3.2-24B-Instruct-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use smarttasks/Mistral-Small-3.2-24B-Instruct-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="smarttasks/Mistral-Small-3.2-24B-Instruct-GGUF",
	filename="Mistral-Small-3.2-24B-Instruct-Q3_K_M.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use smarttasks/Mistral-Small-3.2-24B-Instruct-GGUF with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf smarttasks/Mistral-Small-3.2-24B-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf smarttasks/Mistral-Small-3.2-24B-Instruct-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf smarttasks/Mistral-Small-3.2-24B-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf smarttasks/Mistral-Small-3.2-24B-Instruct-GGUF:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf smarttasks/Mistral-Small-3.2-24B-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf smarttasks/Mistral-Small-3.2-24B-Instruct-GGUF:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf smarttasks/Mistral-Small-3.2-24B-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf smarttasks/Mistral-Small-3.2-24B-Instruct-GGUF:Q4_K_M

Use Docker

docker model run hf.co/smarttasks/Mistral-Small-3.2-24B-Instruct-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use smarttasks/Mistral-Small-3.2-24B-Instruct-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "smarttasks/Mistral-Small-3.2-24B-Instruct-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "smarttasks/Mistral-Small-3.2-24B-Instruct-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/smarttasks/Mistral-Small-3.2-24B-Instruct-GGUF:Q4_K_M

Ollama
How to use smarttasks/Mistral-Small-3.2-24B-Instruct-GGUF with Ollama:
```
ollama run hf.co/smarttasks/Mistral-Small-3.2-24B-Instruct-GGUF:Q4_K_M
```

Unsloth Studio

How to use smarttasks/Mistral-Small-3.2-24B-Instruct-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for smarttasks/Mistral-Small-3.2-24B-Instruct-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for smarttasks/Mistral-Small-3.2-24B-Instruct-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for smarttasks/Mistral-Small-3.2-24B-Instruct-GGUF to start chatting

How to use smarttasks/Mistral-Small-3.2-24B-Instruct-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf smarttasks/Mistral-Small-3.2-24B-Instruct-GGUF:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "smarttasks/Mistral-Small-3.2-24B-Instruct-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use smarttasks/Mistral-Small-3.2-24B-Instruct-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf smarttasks/Mistral-Small-3.2-24B-Instruct-GGUF:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default smarttasks/Mistral-Small-3.2-24B-Instruct-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use smarttasks/Mistral-Small-3.2-24B-Instruct-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf smarttasks/Mistral-Small-3.2-24B-Instruct-GGUF:Q4_K_M

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "smarttasks/Mistral-Small-3.2-24B-Instruct-GGUF:Q4_K_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Docker Model Runner
How to use smarttasks/Mistral-Small-3.2-24B-Instruct-GGUF with Docker Model Runner:
```
docker model run hf.co/smarttasks/Mistral-Small-3.2-24B-Instruct-GGUF:Q4_K_M
```

Lemonade

How to use smarttasks/Mistral-Small-3.2-24B-Instruct-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull smarttasks/Mistral-Small-3.2-24B-Instruct-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Mistral-Small-3.2-24B-Instruct-GGUF-Q4_K_M

List all available models

lemonade list

Mistral-Small-3.2-24B-Instruct-Q4_K_M — GGUF (scorecard)

Quantized from mistralai/Mistral-Small-3.2-24B-Instruct-2506 by SmartTasks on 2026-07-17.

Why this conversion: Smaller, faster local/edge + agentic deployment via GGUF. Size saving: 70.2% vs original weights (HF param count, ~fp16) (this quant: Q4_K_M). Origin: https://huggingface.co/mistralai/Mistral-Small-3.2-24B-Instruct-2506 · license: apache-2.0 · base: mistralai/Mistral-Small-3.1-24B-Base-2503 · arch: Mistral3ForConditionalGeneration Attribution: derived from mistralai/Mistral-Small-3.1-24B-Base-2503 — see the original repo for the authoritative license and model details.

Who this model is for

Complexity band: L1 Layman → L5 Agentic
For non-experts: handles up to L5 Agentic-level tasks in testing.
For engineers/architects: see axis scores and invariants below.
For agentic systems: machine-readable scorecard JSON is embedded at the bottom and shipped as scorecard.json.

Capability by tier

Tier	Passed
L1 Layman	✅
L2 Everyday	✅
L3 Professional	✅
L4 Architect/Engineer	✅
L5 Agentic	✅

Capability by axis

Axis	Score
knowledge	100%
instruction_following	100%
reasoning	100%
coding	100%
structured_output	100%
long_context	100%

Known-answer accuracy: 1.0 · Drift vs original: None

Speed — generation tok/s by device

File	CPU t/s	NVIDIA GeForce RTX 3090 t/s	NVIDIA RTX A4000 t/s	NVIDIA RTX A4000 t/s
Mistral-Small-3.2-24B-Instruct-Q3_K_M.gguf	3.7	40.2	19.5	20.0
Mistral-Small-3.2-24B-Instruct-Q4_K_M.gguf	3.1	53.7	24.9	26.6
Mistral-Small-3.2-24B-Instruct-Q5_K_M.gguf	2.7	47.5	—	—
Mistral-Small-3.2-24B-Instruct-Q6_K.gguf	2.3	40.3	—	—
Mistral-Small-3.2-24B-Instruct-Q8_0.gguf	1.8	—	—	—

Measured via llama-server; each GPU pinned separately. Per-GPU columns show newer vs older architecture side by side. Depends on your hardware and build.

File integrity & sizes (SHA-256)

Verify a download hasn't been tampered with. Linux/mac: sha256sum -c SHA256SUMS. Windows: Get-FileHash <file>.gguf -Algorithm SHA256.

File	Size	Saving	SHA-256
Mistral-Small-3.2-24B-Instruct-Q3_K_M.gguf	10.7 GB	76.1%	`f28863c94b0412cbeb5ae70fd884f65d337dd4a5b764fa33fb9729e34dcfe236`
Mistral-Small-3.2-24B-Instruct-Q4_K_M.gguf	13.3 GB	70.2%	`e8a111d59f3366ea3a1b26e808835abddca65601a35e56db363b11c86959e82e`
Mistral-Small-3.2-24B-Instruct-Q5_K_M.gguf	15.6 GB	65.1%	`4c3549ea6cabad3dbf8786d9f136edf5f91135bcaabba74d0fdc345632be4fcb`
Mistral-Small-3.2-24B-Instruct-Q6_K.gguf	18.0 GB	59.7%	`d7686da4eb6d9a0254a05778646dfb93031cfd335629d93b773adc0616ed0773`
Mistral-Small-3.2-24B-Instruct-Q8_0.gguf	23.3 GB	47.8%	`53cab6899819c6096fadbfcb3334126ddd76394bdf26c8b3c2b7f9abc18a091a`

Saving is vs original weights (HF param count, ~fp16) (44.7 GB). Smaller quants are faster but lower fidelity; larger quants are closer to full precision.

Validation invariants (IAIso)

Overall conformance: WARN (5 pass / 1 warn / 0 fail / 0 not evaluated)

Invariant	Category	Status	Detail
`iaiso.conversion.integrity`	conversion	PASS	GGUF produced and readable
`iaiso.conversion.efficiency`	conversion	PASS	Size reduction vs original weights (HF param count, ~fp16)
`iaiso.capability.retention`	capability	PASS	Known-answer accuracy on the complexity suite
`iaiso.security.posture`	security	WARN	red-team mean resistance 37.7% (weak, sampled: dan+promptinject); weak vs Ablation_Dan_11_0, DanInTheWild, HijackHateHumans, HijackLongPrompt
`iaiso.transparency.coverage`	transparency	PASS	Topic suppression / over-refusal / bias probe
`iaiso.performance.throughput`	performance	PASS	Generation tok/s (best quant on this machine)

First-party self-assessment produced by the SmartTasks/IAIso validation pipeline (capability, security, transparency). Not an independent certification.

Security assessment

This maps directly to the iaiso.security.posture invariant above (WARN). Values below are computed deterministically from the scan outputs — the same scan always yields the same verdict.

Partial (sampled) red-team. Ran probe families dan, promptinject — a focused subset, not garak's full ~40-module suite (which takes ~a day on one GPU). These families target the attack classes most relevant to an instruction-tuned coding model, so the result is a strong, representative indicator of behavioural robustness — though not an exhaustive certification.

Mean resistance: 37.7% (weak). Higher = the model resisted more attacks. Grades: strong ≥95, good ≥80, mixed ≥50, weak <50.

Probe	OWASP	Attempts	Resisted	Pass rate	Grade
`dan.Ablation_Dan_11_0`	LLM01	254	1	0.4%	weak
`promptinject.HijackLongPrompt`	LLM01	512	106	20.7%	weak
`promptinject.HijackHateHumans`	LLM01	512	118	23.0%	weak
`dan.DanInTheWild`	LLM01	512	203	39.6%	weak
`dan.AutoDANCached`	LLM01	6	4	66.7%	mixed
`promptinject.HijackKillHumans`	LLM01	512	388	75.8%	mixed

⚠️ Deployment note: this model was susceptible to one or more prompt-injection attack classes in testing (pass rate <50%). Like most instruction-tuned coding models, it should not be exposed to untrusted input in agent pipelines without external guardrails. This reflects the source model's safety tuning, not the quantization.

Sampled red-team (subset of garak probes); not an exhaustive sweep. Reproduce with garak (public LLM red-team toolkit) using the same probe set.

For agents

{
  "max_complexity_level": 5,
  "max_complexity_label": "L5 Agentic",
  "recommended_for": [
    "knowledge",
    "instruction_following",
    "reasoning",
    "coding",
    "structured_output",
    "long_context"
  ],
  "not_recommended_for": [],
  "size_saving_pct": 70.2
}

The full machine-readable scorecard is in scorecard.json (schema smarttasks.iaiso.model_scorecard/v1).

What this repo gives an agent builder

Unlike a bare GGUF re-upload, every file here is designed to be read programmatically before you drop the model into a loop:

scorecard.json — capability tier + per-axis scores (instruction-following, reasoning, tool-calling, structured-output) so your orchestrator can gate on whether this model is strong enough for a given step, without you hand-testing it.
Validation invariants — machine-readable pass/warn/fail records for security posture, transparency, and quantization fidelity. An agent platform can refuse to load a model whose invariants don't meet policy.
SECURITY.md + red-team results — the model's measured resistance to prompt injection and jailbreaks, so you know its susceptibility before you expose it to untrusted input in an agent chain.
SHA256SUMS — verify the exact weights you're running match what was tested.

This is the difference between "here's a quantized model" and "here's a model with a documented, checkable safety and capability profile for autonomous use."

Running Mistral-Small-3.2-24B-Instruct-Q4_K_M locally (LM Studio, Ollama, llama.cpp, vLLM)

These are GGUF quantizations of mistralai/Mistral-Small-3.2-24B-Instruct-2506 for local inference. Download a single .gguf and load it in LM Studio, Ollama, llama.cpp / llama-server, KoboldCpp, text-generation-webui, or any llama.cpp-based runner — no Python or GPU cluster required. Pick a size from the tables above: larger = closer to the original, smaller = less memory. Q4_K_M is the usual best balance.

Quick start

Ollama

ollama run hf.co/smarttasks/Mistral-Small-3.2-24B-Instruct-Q4_K_M-GGUF:Q4_K_M

llama.cpp (OpenAI-compatible server)

llama-server -m Mistral-Small-3.2-24B-Instruct-Q4_K_M-Q4_K_M.gguf -c 8192 -ngl 999 --host 0.0.0.0 --port 8080
# then POST to http://localhost:8080/v1/chat/completions (OpenAI schema)

LM Studio — search the repo in the in-app model browser, or point it at a downloaded .gguf. Exposes an OpenAI-compatible endpoint on port 1234.

Python (OpenAI client against the local server)

from openai import OpenAI
client = OpenAI(base_url="http://localhost:8080/v1", api_key="not-needed")
resp = client.chat.completions.create(
    model="Mistral-Small-3.2-24B-Instruct-Q4_K_M",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(resp.choices[0].message.content)

LangChain

from langchain_openai import ChatOpenAI
llm = ChatOpenAI(base_url="http://localhost:8080/v1", api_key="not-needed",
                 model="Mistral-Small-3.2-24B-Instruct-Q4_K_M")
print(llm.invoke("Hello!").content)

Using Mistral-Small-3.2-24B-Instruct-Q4_K_M in agentic systems (tool calling, JSON mode)

Built for agent and function-calling workloads — compatible with LangChain, LlamaIndex, CrewAI, AutoGen, and any framework that speaks the OpenAI chat/tools schema via a local llama.cpp or LM Studio endpoint. In testing this model reaches L5 Agentic complexity and is strongest at: knowledge, instruction_following, reasoning, coding, structured_output, long_context. The repo ships a machine-readable scorecard.json with an agent_hint block (max complexity level, recommended tasks, size/VRAM) so an orchestrator can pick the right model automatically. Pair it with a governance layer (see below) for bounded, audited tool use.

For AI safety & security leaders

Every build in this repo ships with a first-party validation record: an OWASP-mapped security scan (ModelScan supply-chain + garak red-team), a transparency probe (topic-suppression / over-refusal / viewpoint-alignment), quantization fidelity (KL-divergence vs the original), and SHA-256 checksums for tamper verification. This is a documented self-assessment — not third-party certification — with every result included so your team can see exactly what was tested and independently verify the model and its checksums. Keywords: LLM security, model governance, agent safety, OWASP LLM Top 10, local/on-prem inference, supply-chain integrity.

About SmartTasks & IAIso

SmartTasks builds tooling for governed, agentic AI workflows. This model was converted and validated with the **SmartTasks GGUF

MoE pipeline** — our proprietary conversion and validation system.

IAIso — governance for agent loops

IAIso is our open framework for bounding what an autonomous agent spends and touches, and proving it afterward. Three primitives: pressure-accumulation rate limiting (one scalar that rises with tokens, tool calls, and planning depth, and triggers an automatic safety release), ConsentScope (signed, scoped, expiring tokens gating sensitive operations), and structured audit (every state change emits a versioned event). It bounds a cooperating agent in-process; for adversarial containment bind it to an out-of-process anchor. (Framework 5.0 · SDK 0.2.0 · beta — you supply your own thresholds/coefficients for your workload.)

pip install iaiso   # Python SDK (the only published package today)

from iaiso import BoundedExecution, PressureConfig

with BoundedExecution.start(config=PressureConfig()) as execution:
    outcome = execution.record_tool_call(name="search", tokens=500)
    if outcome.name == "ESCALATED":
        ...  # request human review before the next expensive step

Go, Rust, Node/TypeScript, Java, C#, PHP, Swift and Ruby SDKs implement the same spec and live in the repo's core/ (build from source — not yet published to their registries). See the repo for conformance vectors and LIMITATIONS.md.

Downloads last month: 228

GGUF

Model size

24B params

Architecture

llama

Hardware compatibility

3-bit

4-bit

5-bit

6-bit

8-bit

Model tree for smarttasks/Mistral-Small-3.2-24B-Instruct-GGUF

Base model

mistralai/Mistral-Small-3.1-24B-Base-2503

Finetuned

mistralai/Mistral-Small-3.2-24B-Instruct-2506

Quantized

(67)

this model