Mistral Small 24B Instruct 2501 (Q2_K) — 15.8 GBon NVIDIA H100 640GB

Code Multilingual Tool Calls

Q2_K NVIDIA H100 640GB

Overview

Mistral Small 24B Instruct 2501 is a 23.57B parameter dense language model by Mistral AI, with code, multilingual, tool-calls capabilities. It supports a context window of up to 32,768 tokens.

Mistral Small 24B Instruct 2501 is a 23.57-billion-parameter dense transformer from Mistral AI, optimized for instruction following, code generation, and multilingual conversation. It occupies a mid-range parameter class that offers strong performance relative to its size, competing with larger 30B models on many benchmarks. The model supports tool calling and 10 languages including English, French, Chinese, and Japanese. With a 32K context window and flash attention, it fits on a single consumer GPU at Q4 quantization for efficient self-hosted inference.

At Q2_K quantization (low quality tier), the model weighs 8.28 GB. This fits within the 640 GB of VRAM on NVIDIA H100 640GB, enabling full GPU inference.

Hardware Requirements

Model size	8.28 GB
VRAM available	640 GB
VRAM used	15.8 GB
System RAM
Min RAM required	0 GB
GPU layers	40 / 40
Context size	32,768
Backend	cuda13
Flash attention	Yes
Reading from disk	Yes

Deploy

Prerequisites

Ensure your GPU nodes are prepared with the NVIDIA container toolkit:

ansible-playbook prositronic.infra.nvidia_container_toolkit

Command

helmfile --state-values-file <(curl -s https://www.prositronic.eu/values/mistral-small-24b-instruct-2501/q2_k/nvidia-h100-640gb.yaml) apply

Generated `values.yaml`

/values/mistral-small-24b-instruct-2501/q2_k/nvidia-h100-640gb.yaml

Loading values…

Install llama.cpp

Install llama.cpp from the official build instructions for your platform and backend.

Download Model

curl -L -o mistral-small-24b-instruct-2501.gguf "https://huggingface.co/bartowski/Mistral-Small-24B-Instruct-2501-GGUF/resolve/main/Mistral-Small-24B-Instruct-2501-Q2_K.gguf"

Start Server

llama-server \
  -m mistral-small-24b-instruct-2501.gguf \
  --n-gpu-layers 40 \
  --ctx-size 32768 \
  --flash-attn

Verify

curl http://localhost:8080/health

Frequently Asked Questions

How much VRAM does Mistral Small 24B Instruct 2501 (Q2_K) need?

The Q2_K quantization of Mistral Small 24B Instruct 2501 requires 8.28 GB. All 40 layers fit in the 640 GB of VRAM available on NVIDIA H100 640GB, enabling full GPU acceleration.

Can I run Mistral Small 24B Instruct 2501 on NVIDIA H100 640GB?

Yes. NVIDIA H100 640GB provides 640 GB of VRAM, which is enough to run Mistral Small 24B Instruct 2501 (Q2_K) with all layers on the GPU for optimal performance.

What is quantization?

Quantization reduces a model's numerical precision from its original floating-point format to a more compact representation. This shrinks the file size and VRAM footprint, making it possible to run large models on consumer hardware. The trade-off is a small reduction in output quality. Q2_K compresses Mistral Small 24B Instruct 2501 from its original size down to 8.28 GB.

What quantization should I choose for Mistral Small 24B Instruct 2501?

Q2_K is a low-quality quantization. Higher-quality quants (Q8, Q6) preserve more model accuracy but need more VRAM. Lower quants (Q4, Q3, Q2) reduce VRAM usage at the cost of some quality. Choose based on your available hardware and quality requirements.

What is flash attention and why is it enabled?

Flash attention is a memory-efficient algorithm that speeds up the attention mechanism in transformer models. It reduces VRAM usage during inference by avoiding the materialisation of the full attention matrix. For Mistral Small 24B Instruct 2501 on NVIDIA H100 640GB, flash attention is enabled to maximise context length and throughput within the available 640 GB of VRAM.

How do I run Mistral Small 24B Instruct 2501 (Q2_K) with Ollama?

Run ollama run mistral-small:24b-instruct-2501-q2_k to start Mistral Small 24B Instruct 2501 (Q2_K). Ollama handles downloading the model weights automatically on first run.

Last updated: March 12, 2026