What GPU do I need to run mistralai/Mistral-Small-24B-Instruct-2501?
A 23.6B language model for chat and instruction-following. 23.6B parameters, published in BF16. View on Hugging Face
Mistral-Small-24B-Instruct-2501 is published by mistralai on Hugging Face, with 50,489 downloads and 970 likes to date. It's a MistralForCausalLM model built for text-generation, published natively in BF16.
What Mistral-Small-24B-Instruct-2501 is
Mistral-Small-24B-Instruct-2501 is a 23.6B-parameter language model published by Mistral AI on Hugging Face. It is released under Apache 2.0.
License note: fully permissive, no gating and no usage restrictions. Facts in this section are sourced from Mistral-Small-24B-Instruct-2501's Hugging Face model card, not benchmarked by Aquanode.
What it's used for
- Chat assistants
- Instruction following
- Synthetic data generation
VRAM required & cheapest live GPU fit
Required VRAM = weight size at each precision times a flat 1.2 overhead for activations and fragmentation. The KV-cache grows with context and is not in that factor; it is listed per model below where the architecture is published. Full formula and assumptions: methodology.
| Precision | Weight size | Required VRAM | Cheapest live fit | GPUs needed | Est. $/hr (full fit) |
|---|---|---|---|---|---|
| BF16 | 43.9 GB | 52.7 GB | A100 | 1 | $1.21/hr |
| cheaper alt. | RTX A5000 | 3 | $0.528/hr | ||
| FP8 (quantized) | 22.0 GB | 26.3 GB | RTX 4090 | 1 | $0.510/hr |
| cheaper alt. | RTX 4000 SFF Ada | 2 | $0.396/hr | ||
| INT4 (quantized) | 11.0 GB | 13.2 GB | RTX A4000 | 1 | $0.167/hr |
A GPU is only matched to a row if its hardware supports that precision, and the primary recommendation is always a single-GPU fit when one exists.
INT4 requires a quantized checkpoint actually published for this model, check its Hugging Face page before relying on this row.
Cheapest way to run Mistral-Small-24B-Instruct-2501 at its published (BF16) precision: 1× A100, at $1.21/hr per GPU ($1.21/hr total). Quantizing to FP8 or INT4 (rows above) can cost less, but requires a compatible quantized checkpoint to exist for this model.
Mistral-Small-24B-Instruct-2501: KV cache by context length
The KV cache is the memory the attention layers hold for every token of context, on top of the weights. It is not part of the flat 1.2x overhead in the table above, grows with context length and with every concurrent request, and is why a long-context deployment needs more VRAM than the table shows.
Grouped-query attention: every layer caches keys and values for a few shared KV heads. Cached per token: 163,840 bytes at 16-bit.
| Context | KV cache, one sequence |
|---|---|
| 4K | 0.63 GB |
| 32K | 5.0 GB |
Computed from the layer, head and window counts in the model's own configuration (mistralai/Mistral-Small-24B-Instruct-2501), at 16 bits per cached value. Each concurrent sequence needs its own cache, on top of the weights.
Mistral-Small-24B-Instruct-2501: common questions
Can Mistral-Small-24B-Instruct-2501 run on a single GPU?
Yes, but not on a desktop card. At BF16 it needs 52.7 GB of VRAM, more than a single 32 GB desktop card holds. The cheapest live single-card fit is a 80.0 GB A100 at $1.21/hr.
What is the least VRAM Mistral-Small-24B-Instruct-2501 can run in?
13.2 GB, at INT4 (quantized), which fits a 16 GB card, against 52.7 GB at BF16. That row assumes an INT4 checkpoint has actually been published for this model, so check its Hugging Face page before planning around it.
Does quantizing Mistral-Small-24B-Instruct-2501 lower the GPU bill?
Yes. At BF16 the cheapest live fit is one A100 at $1.21/hr. At INT4 (quantized) it drops to one RTX A4000 at $0.167/hr, provided a quantized checkpoint exists for it.
How to run Mistral-Small-24B-Instruct-2501
Run Mistral-Small-24B-Instruct-2501 with vLLM
From mistralai/Mistral-Small-24B-Instruct-2501's own deployment docs.
vllm serve mistralai/Mistral-Small-24B-Instruct-2501 --tokenizer_mode mistral --config_format mistral --load_format mistral --tool-call-parser mistral --enable-auto-tool-choiceSource: https://huggingface.co/mistralai/Mistral-Small-24B-Instruct-2501/raw/main/README.md
Run Mistral-Small-24B-Instruct-2501 with GGUF quantizations
Prebuilt GGUF weights published at bartowski/Mistral-Small-24B-Instruct-2501-GGUF. Run with llama.cpp's llama-server or load the repo directly in LM Studio.
llama-server -hf bartowski/Mistral-Small-24B-Instruct-2501-GGUFSource: https://huggingface.co/bartowski/Mistral-Small-24B-Instruct-2501-GGUF
Deploy Mistral-Small-24B-Instruct-2501 on Aquanode
Aquanode has no one-click deploy template for Mistral-Small-24B-Instruct-2501; you install the inference engine yourself with the commands below. Aquanode sells GPU pods billed per second, not a hosted inference API.
- Launch a bare GPU pod sized to the requirement above (1× A100 or larger).
- Open a terminal on the pod, or save one of the commands above as a startup script so it runs automatically the first time the pod boots.
- Run the command and connect to the resulting endpoint.
Launch a GPU podWeight-to-VRAM math, the fit rules, and how live prices are normalized: full methodology.
More Mistral Small models
- Dolphin3.0-R1-Mistral-24B (23.6B, BF16)
- Dolphin-Mistral-24B-Venice-Edition (24.0B, BF16)
Lineage
Quantized and fine-tuned versions
Also published as: unsloth/Mistral-Small-24B-Instruct-2501. Identical copies of this model under another account.
More on Mistral-Small-24B-Instruct-2501
Fits on an 80 GB GPU at BF16: every model that fits in 80 GB.
Fits on a 32 GB GPU at FP8: every model that fits in 32 GB.
Fits on a 16 GB GPU at INT4: every model that fits in 16 GB.
How to run Mistral Small and how to fine-tune Mistral Small.
Related reading: A100 pricing and specs, How much VRAM you need for LLMs, and What AI inference is.
