Devstral Small 2 24B Instruct 2512 — Hardware Requirements & GPU Compatibility
Chat
Devstral Small 2 24B Instruct is Mistral AI's dense 24-billion-parameter model for agentic software-engineering work, fine-tuned to follow instructions for chat, coding agents, and tool-heavy workflows. Built on the same architecture as Ministral 3, it adds vision capabilities for analyzing images alongside code and text, and its publisher designed it specifically to be lightweight enough for local, on-device use rather than requiring a large server. It supports a context window of roughly 384,000 tokens and is released under the Apache 2.0 license. Mistral notes it is light enough to run on a single RTX 4090 or a Mac with 32GB of RAM, consistent with its 4-bit memory needs of around 14GB.
301.1K downloads
669 likesSpecifications
- Publisher
- Mistral AI
- Family
- Mistral
- Parameters
- 24.0B
- Architecture
- Mistral3ForConditionalGeneration
- Context Length
- 393,216 tokens
- Vocabulary Size
- 131,072
- Release Date
- 2025-11-28
- License
- Apache 2.0
Get Started
HuggingFace
How Much VRAM Does Devstral Small 2 24B Instruct 2512 Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| Q2_K | 3.40 | 10.9 GB | 91.0 GB | 10.20 GB | 2-bit quantization with K-quant improvements |
| Q3_K_S | 3.50 | 11.2 GB | 91.3 GB | 10.50 GB | 3-bit small quantization |
| Q3_K_M | 3.90 | 12.4 GB | 92.5 GB | 11.71 GB | 3-bit medium quantization |
| Q4_0 | 4.00 | 12.7 GB | 92.8 GB | 12.01 GB | 4-bit legacy quantization |
| Q4_K_M | 4.80 | 15.1 GB | 95.2 GB | 14.41 GB | 4-bit medium quantization — most popular sweet spot |
| Q5_K_M | 5.70 | 17.8 GB | 97.9 GB | 17.11 GB | 5-bit medium quantization — good quality/size tradeoff |
| Q6_K | 6.60 | 20.5 GB | 100.6 GB | 19.81 GB | 6-bit quantization, very good quality |
| Q8_0 | 8.00 | 24.7 GB | 104.8 GB | 24.01 GB | 8-bit quantization, near-lossless |
Which GPUs Can Run Devstral Small 2 24B Instruct 2512?
Q4_K_M · 15.1 GBDevstral Small 2 24B Instruct 2512 (Q4_K_M) requires 15.1 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 20+ GB is recommended. Using the full 393K context window can add up to 80.1 GB, bringing total usage to 95.2 GB. 26 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti, NVIDIA GeForce RTX 5080.
Runs great
— Plenty of headroom
Decent
— Enough VRAM, may be tightWhich Devices Can Run Devstral Small 2 24B Instruct 2512?
Q4_K_M · 15.1 GB47 devices with unified memory can run Devstral Small 2 24B Instruct 2512, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, Mac Mini M4 (16 GB).
Runs great
— Plenty of headroomWhere to Download Devstral Small 2 24B Instruct 2512
Community quantizations of this model — GGUF for llama.cpp, Ollama, and LM Studio, plus AWQ/MLX variants where available.
Benchmarks
Benchmark details →Related Models
Frequently Asked Questions
- How much VRAM does Devstral Small 2 24B Instruct 2512 need?
Devstral Small 2 24B Instruct 2512 requires 15.1 GB of VRAM at Q4_K_M, or 48.7 GB at BF16. Full 393K context adds up to 80.1 GB (95.2 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 24.0B × 4.8 bits ÷ 8 = 14.4 GB
KV Cache + Overhead ≈ 0.7 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 80.8 GB (at full 393K context)
VRAM usage by quantization
Q4_K_M15.1 GBQ4_K_M + full context95.2 GB- Can NVIDIA GeForce RTX 4090 run Devstral Small 2 24B Instruct 2512?
Yes, at Q6_K (20.5 GB) or lower. Higher quantizations like Q8_0 (24.7 GB) exceed the NVIDIA GeForce RTX 4090's 24 GB.
- What's the best quantization for Devstral Small 2 24B Instruct 2512?
For Devstral Small 2 24B Instruct 2512, Q4_K_M (15.1 GB) offers the best balance of quality and VRAM usage. Q4_K_L (15.4 GB) provides better quality if you have the VRAM. The smallest option is IQ2_XXS at 7.3 GB.
VRAM requirement by quantization
IQ2_XXS7.3 GBIQ3_S10.9 GBQ3_K_L13.0 GBQ4_K_M ★15.1 GBQ4_K_L15.4 GBBF1648.7 GB★ Recommended — best balance of quality and VRAM usage.
- Can I run Devstral Small 2 24B Instruct 2512 on a Mac?
Devstral Small 2 24B Instruct 2512 requires at least 7.3 GB at IQ2_XXS, which exceeds the unified memory of most consumer Macs. You would need a Mac Studio or Mac Pro with a high-memory configuration.
- Can I run Devstral Small 2 24B Instruct 2512 locally?
Yes — Devstral Small 2 24B Instruct 2512 can run locally on consumer hardware. At Q4_K_M quantization it needs 15.1 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is Devstral Small 2 24B Instruct 2512?
At Q4_K_M, Devstral Small 2 24B Instruct 2512 can reach ~317 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~43 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 ÷ 15.1 × 0.65 = ~344 tok/s
Estimated speed at Q4_K_M (15.1 GB)
~344 tok/s~43 tok/s~344 tok/s~317 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of Devstral Small 2 24B Instruct 2512?
At Q4_K_M, the download is about 14.41 GB. The full-precision BF16 version is 48.02 GB. The smallest option (IQ2_XXS) is 6.60 GB.
- Which GPUs can run Devstral Small 2 24B Instruct 2512?
26 consumer GPUs can run Devstral Small 2 24B Instruct 2512 at Q4_K_M (15.1 GB). 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 Devstral Small 2 24B Instruct 2512?
49 devices with unified memory can run Devstral Small 2 24B Instruct 2512 at Q4_K_M (15.1 GB), including AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10, Asus ROG Flow Z13 (2025, Ryzen AI Max+ 395, 128 GB), Beelink GTR9 Pro (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.