Mistral Small Instruct 2409 — Hardware Requirements & GPU Compatibility
Chat
Mistral Small Instruct 2409 is a 22.2B-parameter open language model from Mistral AI in the Mistral family. It supports a context window of up to 32,768 tokens. At Q4_K_M it needs about 14.12 GB of VRAM — see which GPUs and Macs can run it below.
127.5K downloads
393 likesSpecifications
- Publisher
- Mistral AI
- Family
- Mistral
- Parameters
- 22.2B
- Architecture
- MistralForCausalLM
- Context Length
- 32,768 tokens
- Vocabulary Size
- 32,768
- Release Date
- 2024-09-17
- License
- Other
Get Started
HuggingFace
How Much VRAM Does Mistral Small Instruct 2409 Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| Q2_Kest. | 3.40 | 10.2 GB | 17.3 GB | 9.46 GB | 2-bit quantization with K-quant improvements |
| Q3_K_Mest. | 3.90 | 11.6 GB | 18.7 GB | 10.85 GB | 3-bit medium quantization |
| Q4_K_Mest. | 4.80 | 14.1 GB | 21.2 GB | 13.35 GB | 4-bit medium quantization — most popular sweet spot |
| Q5_K_Mest. | 5.70 | 16.6 GB | 23.7 GB | 15.85 GB | 5-bit medium quantization — good quality/size tradeoff |
| Q6_Kest. | 6.60 | 19.1 GB | 26.2 GB | 18.35 GB | 6-bit quantization, very good quality |
| Q8_0est. | 8.00 | 23.0 GB | 30.1 GB | 22.25 GB | 8-bit quantization, near-lossless |
| BF16est. | 16.00 | 45.3 GB | 52.3 GB | 44.49 GB | Brain floating point 16 — preferred for training |
est.= calculated VRAM estimate; no published GGUF file found for that quantization yet. Other rows are verified against real community uploads.
Which GPUs Can Run Mistral Small Instruct 2409?
Q4_K_M · 14.1 GBMistral Small Instruct 2409 (Q4_K_M) requires 14.1 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 19+ GB is recommended. Using the full 33K context window can add up to 7.0 GB, bringing total usage to 21.2 GB. 17 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 Mistral Small Instruct 2409?
Q4_K_M · 14.1 GB27 devices with unified memory can run Mistral Small Instruct 2409, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, Mac Mini M4 (16 GB).
Runs great
— Plenty of headroomRelated Models
Frequently Asked Questions
- How much VRAM does Mistral Small Instruct 2409 need?
Mistral Small Instruct 2409 requires 14.1 GB of VRAM at Q4_K_M, or 45.3 GB at BF16. Full 33K context adds up to 7.0 GB (21.2 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 22.2B × 4.8 bits ÷ 8 = 13.3 GB
KV Cache + Overhead ≈ 0.8 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 7.9 GB (at full 33K context)
VRAM usage by quantization
Q4_K_M14.1 GBQ4_K_M + full context21.2 GB- Can NVIDIA GeForce RTX 4090 run Mistral Small Instruct 2409?
Yes, at Q8_0 (23.0 GB) or lower. Higher quantizations like BF16 (45.3 GB) exceed the NVIDIA GeForce RTX 4090's 24 GB.
- What's the best quantization for Mistral Small Instruct 2409?
For Mistral Small Instruct 2409, Q4_K_M (14.1 GB) offers the best balance of quality and VRAM usage. Q5_K_M (16.6 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 10.2 GB.
VRAM requirement by quantization
Q2_K10.2 GBQ4_K_M ★14.1 GBQ5_K_M16.6 GBQ6_K19.1 GBQ8_023.0 GBBF1645.3 GB★ Recommended — best balance of quality and VRAM usage.
- Can I run Mistral Small Instruct 2409 on a Mac?
Mistral Small Instruct 2409 requires at least 10.2 GB at Q2_K, 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 Mistral Small Instruct 2409 locally?
Yes — Mistral Small Instruct 2409 can run locally on consumer hardware. At Q4_K_M quantization it needs 14.1 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is Mistral Small Instruct 2409?
At Q4_K_M, Mistral Small Instruct 2409 can reach ~206 tok/s on AMD Instinct MI300X. On NVIDIA GeForce RTX 4090: ~46 tok/s. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = (bandwidth GB/s ÷ model GB) × efficiency
Example: AMD Instinct MI300X → 5300 ÷ 14.1 × 0.55 = ~206 tok/s
Estimated speed at Q4_K_M (14.1 GB)
~206 tok/s~46 tok/s~154 tok/s~128 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of Mistral Small Instruct 2409?
At Q4_K_M, the download is about 13.35 GB. The full-precision BF16 version is 44.49 GB. The smallest option (Q2_K) is 9.46 GB.
- Which GPUs can run Mistral Small Instruct 2409?
17 consumer GPUs can run Mistral Small Instruct 2409 at Q4_K_M (14.1 GB). Top options include AMD Radeon RX 7900 XTX, NVIDIA GeForce RTX 3090, NVIDIA GeForce RTX 3090 Ti, AMD Radeon RX 6800. 5 GPUs have plenty of headroom for comfortable inference.
- Which devices can run Mistral Small Instruct 2409?
27 devices with unified memory can run Mistral Small Instruct 2409 at Q4_K_M (14.1 GB), including Mac Mini M4 (16 GB), Mac Mini M4 (32 GB), Mac Mini M4 Pro (24 GB), Mac Mini M4 Pro (48 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.