Mistral Small 3 24B — Hardware Requirements & GPU Compatibility
Chat
Mistral Small 3 24B is a 24B-parameter open language model from EasierAI in the Mistral family. At Q4_K_M it needs about 15.84 GB of VRAM — see which GPUs and Macs can run it below.
Runs well on a 24 GB GPU
Runs from 16 GB (Q4_K_M · 2K)Best on 24 GB (Q4_K_M · ~41 tok/s · 32K)Macs from 24 GB (Q4_K_M · ~14 tok/s)
Apache 2.0
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Mistral Small 3 24B
One recommended way. Every other method, OS and quant is in the step-by-step guide.Each way opens a step-by-step guide for your OS and quant.
Recommended
vllm serve EasierAI/Mistral-Small-3-24B --max-model-len 16384vLLM repo with its own quantisation
Download: Weights on Hugging Face
Ways to runOther ways
each opens step-by-stepRun in cloud
Runs on RTX 3090 (24 GB) (4 GB headroom) · Q4_K_M
- Generation speed
- ~38 tok/s
- generation speed
- Cost per 1M output tokens
- $1.43
- per 1M output tokens
How Much VRAM Does Mistral Small 3 24B Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 11.2 GB | 18.7 GB | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Fits: 32K context · ~58 tok/s | |
| 11.6 GB | 19 GB | 3-bit small — 3-bit small quantization | Fits: 32K context · ~57 tok/s | |
| 12.9 GB | 20.4 GB | 3-bit medium — 3-bit medium quantization | Fits: 32K context · ~51 tok/s | |
| 13.2 GB | 20.7 GB | 4-bit · legacy — 4-bit legacy quantization | Fits: 32K context · ~50 tok/s | |
| 15.8 GB | 23.3 GB | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Fits: 32K context · ~41 tok/s | |
| 18.8 GB | 26.3 GB | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Fits: 16K context · ~35 tok/s | |
| 21.8 GB | 29.3 GB | 6-bit, very good — 6-bit quantization, very good quality | Fits: 8K context · ~30 tok/s | |
| 26.4 GB | 33.9 GB | 8-bit, near-lossless — 8-bit quantization, near-lossless | Does not fit: needs 29.9 GB |
Selected Q4_K_M
4-bit medium quantization19.3GBat 16K context
- Weights
- 15.0 GB
- KV cache
- 4.0 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 4.7 GB free · ~41 tok/s
≥50 tok/s needs ≥1.22 TB/s · RTX 5090 ~74
Which Hardware Can Run Mistral Small 3 24B?
Q4_K_M · 15.8 GBMistral Small 3 24B (Q4_K_M) requires 15.8 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 21+ GB is recommended. 26 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti, NVIDIA GeForce RTX 5080. 122 devices with unified memory can run Mistral Small 3 24B, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB), Mac Mini M5 Pro (24 GB).
20 GB
fits · 0.7 GB free · up to 16K ctx
1 GPU
RX 7900 XT~30Simulate output on RX 7900 XT32–40 GB
fits · 12.7 GB free · up to 32K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~74Simulate output on RTX 5090M5 Max36 GB~20Simulate output on Mac Studio M5 Max (36 GB)M532 GB~7Simulate output on MacBook Air 13" M5 (32 GB)Orin~8Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~6Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at Q4_K_M
Alternatives to Mistral Small 3 24B
Mistral family · 35 models →Similar models
4| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| LFM2.5 24B A2BLiquid AI | — | 15 GB | ~221 | same size |
| Gemma 4 26B A4BGoogle | — | 16.5 GB | ~171 | same size |
| Ariarhymes-ai | — | 20.2 GB | ~168 | same size |
| EuroLLM 22B Instruct 2512utter-project | — | 17.5 GB | ~46 | same size |
Specifications
- Publisher
- EasierAI
- Family
- Mistral
- Parameters
- 24B
- Release Date
- 2025-02-13
- License
- Apache 2.0
Frequently Asked Questions
How much VRAM does Mistral Small 3 24B need?
Mistral Small 3 24B requires 15.8 GB of VRAM at Q4_K_M, or 52.8 GB at BF16.
VRAM = Weights + KV Cache + Overhead
Weights = 24B × 4.8 bits ÷ 8 = 14.4 GB
KV Cache + Overhead ≈ 1.4 GB (at 2K context + ~0.3 GB framework)
Fit ratings and hardware model lists check this model with room for a 16K-token context, which needs a little more memory.
VRAM usage by quantization
Can NVIDIA GeForce RTX 4090 run Mistral Small 3 24B?
Yes, at Q6_K (21.8 GB) or lower. Higher quantizations like Q8_0 (26.4 GB) exceed the NVIDIA GeForce RTX 4090's 24 GB.
What's the best quantization for Mistral Small 3 24B?
For Mistral Small 3 24B, Q4_K_M (15.8 GB) offers the best balance of quality and VRAM usage. Q4_K_L (16.2 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 11.2 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run Mistral Small 3 24B on a Mac?
Yes — Mac Mini M5 Pro (24 GB) and 106 other Macs can run Mistral Small 3 24B. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 15.8 GB of usable unified memory (RAM minus macOS overhead).
Can I run Mistral Small 3 24B locally?
Yes — Mistral Small 3 24B can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Mistral Small 3 24B?
At Q4_K_M, Mistral Small 3 24B can reach ~303 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~41 tok/s. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = (bandwidth GB/s ÷ model GB) × efficiency
Example: NVIDIA B200 → 8000 ÷ 15.84 × 0.65 = ~328 tok/s
Estimated speed at Q4_K_M (15.8 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of Mistral Small 3 24B?
At Q4_K_M, the download is about 14.40 GB. The full-precision BF16 version is 48.00 GB. The smallest option (Q2_K) is 10.20 GB.
Which GPUs can run Mistral Small 3 24B?
26 consumer GPUs can run Mistral Small 3 24B at Q4_K_M. Top options include AMD Radeon RX 7900 XTX, NVIDIA GeForce RTX 3090, NVIDIA GeForce RTX 3090 Ti, AMD Radeon RX 6800. 7 GPUs have plenty of headroom for comfortable inference.
Which devices can run Mistral Small 3 24B?
122 devices with unified memory can run Mistral Small 3 24B at Q4_K_M (15.8 GB), including AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10, Beelink GTR9 Pro (Ryzen AI Max+ 395, 128 GB), Framework Desktop (Ryzen AI Max+ 395, 128 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.