Mistral Small 24B Instruct 2501 (FP16)on CPU Only
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 FP16 quantization (full-precision quality tier), the model weighs 43.92 GB. This exceeds the 0 GB of VRAM on CPU Only. Inference is still possible via CPU offload or memory-mapped loading from disk, but expect significantly reduced performance.
A CPU-only configuration with no GPU acceleration. Inference runs entirely on the CPU, which is significantly slower than GPU-accelerated setups but requires no special hardware. Performance and maximum model size depend on available system RAM. Suitable for testing, development, or deployments where no GPU is available.
Hardware Requirements
| Model size | 43.92 GB |
| VRAM available | 0 GB |
| VRAM used | 0 GB |
| System RAM | |
| Min RAM required | 43.9 GB |
| GPU layers | 0 / 40 |
| Context size | 32,768 |
| Backend | cpu |
| Flash attention | No |
| Reading from disk | Yes |
Performance Notes
Deploy
Command
helmfile --state-values-file <(curl -s https://www.prositronic.eu/values/mistral-small-24b-instruct-2501/fp16/cpu.yaml) applyGenerated values.yaml
/values/mistral-small-24b-instruct-2501/fp16/cpu.yaml
Loading values…Frequently Asked Questions
How much VRAM does Mistral Small 24B Instruct 2501 (FP16) need?
The FP16 quantization of Mistral Small 24B Instruct 2501 requires 43.92 GB. The 0 GB of VRAM on CPU Only is insufficient for GPU layers, so inference runs on CPU.
Can I run Mistral Small 24B Instruct 2501 on CPU Only?
It is possible but not recommended. CPU Only does not have enough VRAM to accelerate Mistral Small 24B Instruct 2501 (FP16), so inference will rely on CPU and system RAM.
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. FP16 compresses Mistral Small 24B Instruct 2501 from its original size down to 43.92 GB.
What quantization should I choose for Mistral Small 24B Instruct 2501?
FP16 is a full-precision 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.
Why are some layers offloaded to CPU?
CPU Only has 0 GB of VRAM, but Mistral Small 24B Instruct 2501 (FP16) requires approximately 43.92 GB. Only 0 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 (FP16) with Ollama?
Run ollama run mistral-small:24b-instruct-2501-fp16 to start Mistral Small 24B Instruct 2501 (FP16). Ollama handles downloading the model weights automatically on first run.