Mistral Small 24B Instruct 2501 (Q5_K_L) — 15.4 GBon Apple M2 Pro 16GB
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 Q5_K_L quantization (low quality tier), the model weighs 16 GB. This fits within the 16 GB of VRAM on Apple M2 Pro 16GB, enabling full GPU inference.
Hardware Requirements
| Model size | 16 GB |
| VRAM available | 16 GB |
| VRAM used | 15.4 GB |
| System RAM | |
| Min RAM required | 2 GB |
| GPU layers | 35 / 40 |
| Context size | 814 |
| Backend | metal |
| Flash attention | Yes |
| Reading from disk | Yes |
Performance Notes
Deploy
Install llama.cpp
brew install llama.cppDownload 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-Q5_K_L.gguf"Start Server
llama-server \
-m mistral-small-24b-instruct-2501.gguf \
--n-gpu-layers 35 \
--ctx-size 814 \
--flash-attnVerify
curl http://localhost:8080/healthFrequently Asked Questions
How much VRAM does Mistral Small 24B Instruct 2501 (Q5_K_L) need?
The Q5_K_L quantization of Mistral Small 24B Instruct 2501 requires 16 GB. 35 of 40 layers fit in the 16 GB of VRAM on Apple M2 Pro 16GB; remaining layers are offloaded to CPU.
Can I run Mistral Small 24B Instruct 2501 on Apple M2 Pro 16GB?
Yes, with reduced performance. Apple M2 Pro 16GB can run Mistral Small 24B Instruct 2501 (Q5_K_L), but only 35 of 40 layers fit in VRAM. The rest are offloaded to CPU.
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. Q5_K_L compresses Mistral Small 24B Instruct 2501 from its original size down to 16 GB.
What quantization should I choose for Mistral Small 24B Instruct 2501?
Q5_K_L 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 Apple M2 Pro 16GB, flash attention is enabled to maximise context length and throughput within the available 16 GB of VRAM.
Why are some layers offloaded to CPU?
Apple M2 Pro 16GB has 16 GB of VRAM, but Mistral Small 24B Instruct 2501 (Q5_K_L) requires approximately 16 GB. Only 35 of 40 layers fit in VRAM; the remaining layers run on CPU, which is slower but still functional.
How do I run Mistral Small 24B Instruct 2501 (Q5_K_L) with Ollama?
Run ollama run mistral-small:24b-instruct-2501-q5_k_l to start Mistral Small 24B Instruct 2501 (Q5_K_L). Ollama handles downloading the model weights automatically on first run.