Mistral Small Instruct 2409 — Hardware Requirements & GPU Compatibility
ChatFunctions
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.
Runs well on a 24 GB GPU
Runs from 12 GB (IQ2_XS · 16K)Best on 24 GB (Q4_K_M · ~46 tok/s · 32K)Macs from 16 GB (IQ2_XS · ~19 tok/s)
Other
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Mistral Small Instruct 2409
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
ollama run hf.co/MaziyarPanahi/Mistral-Small-Instruct-2409-GGUF:Q4_K_MQ4_K_M fits fully on the RTX 4090 · 6.6 GB free · 16K context
Download: Mistral-Small-Instruct-2409.Q4_K_M.gguf13.34 GBMaziyarPanahi
Ways to runOther ways
each opens step-by-stepRun in cloud
Your own private copy · Q4_K_M · 24 GB GPU
- The easiest way to try this model
- Running in a few minutes, easy setup
- Chat right here or connect any app
$5+ bonus for new users
Runs on RTX 3090 (24 GB) (6 GB headroom) · Q4_K_M
- Generation speed
- ~43 tok/s
- generation speed
- Cost per 1M output tokens
- $1.09
- per 1M output tokens
How Much VRAM Does Mistral Small Instruct 2409 Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 7.4 GB | 14.5 GB | 2-bit · i-quant extra small — Importance-weighted 2-bit, extra small | Fits: 32K context · ~88 tok/s | |
| 10.2 GB | 17.3 GB | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Fits: 32K context · ~64 tok/s | |
| 10.5 GB | 17.6 GB | 3-bit small — 3-bit small quantization | Fits: 32K context · ~62 tok/s | |
| 11.6 GB | 18.7 GB | 3-bit medium — 3-bit medium quantization | Fits: 32K context · ~56 tok/s | |
| 14.1 GB | 21.2 GB | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Fits: 32K context · ~46 tok/s | |
| 16.6 GB | 23.7 GB | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Fits: 32K context · ~39 tok/s | |
| 19.1 GB | 26.2 GB | 6-bit, very good — 6-bit quantization, very good quality | Fits: 16K context · ~34 tok/s | |
| 23.0 GB | 30.1 GB | 8-bit, near-lossless — 8-bit quantization, near-lossless | Fits: 4K context · ~29 tok/s |
Selected Q4_K_M
4-bit medium quantization17.4GBat 16K context
- Weights
- 13.4 GB
- KV cache
- 3.8 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 6.6 GB free · ~46 tok/s
≥50 tok/s needs ≥1.08 TB/s · RTX 5090 ~83
Which Hardware 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. 26 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti, NVIDIA GeForce RTX 5080. 124 devices with unified memory can run Mistral Small Instruct 2409, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB), Mac Mini M5 Pro (24 GB).
20 GB
fits · 2.6 GB free · up to 16K ctx
1 GPU
RX 7900 XT~34Simulate output on RX 7900 XT32–40 GB
fits · 14.6 GB free · up to 32K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~83Simulate output on RTX 5090M5 Max36 GB~23Simulate output on Mac Studio M5 Max (36 GB)M532 GB~8Simulate output on MacBook Air 13" M5 (32 GB)Orin~9Simulate 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
How good is Mistral Small Instruct 2409?
llmrun Score blends public benchmark boards into one number; 100 = the average open model.
Not enough data yet for an llmrun Score.
A Score needs results on enough independent boards. How the Composite Score is built
Benchmarks
Here are all 2 boards that have results for this model, sorted by their weight in the llmrun Score; badges show who ran the test.
Alternatives to Mistral Small Instruct 2409
Mistral family · 35 models →Similar models
6| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| LFM2.5 24B A2BLiquid AI | — | 15 GB | ~221 | same size |
| InternVL3 5 GPT OSS 20B A4B Preview HFOpenGVLab | — | 13.6 GB | ~180 | same size |
| Tri 21B Thinktrillionlabs | — | 45.1 GB | —needs > 24 GB | same size |
| EuroLLM 22B Instruct 2512utter-project | — | 17.5 GB | ~46 | same size |
| ERNIE 4.5 21B A3B ThinkingBaidu | — | 14.3 GB | ~213 | same size |
| GPT Neox 20BEleutherAI | — | 13.7 GB | ~48 | same size |
Specifications
- 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
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)
Fit ratings and hardware model lists check this model with room for a 16K-token context, which needs a little more memory.
KV Cache + Overhead ≈ 7.9 GB (at full 33K context)
VRAM usage by quantization
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_S (16.1 GB) provides better quality if you have the VRAM. The smallest option is IQ2_XS at 7.4 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run Mistral Small Instruct 2409 on a Mac?
Yes — Mac Mini M2 Pro (16 GB) and 133 other Macs can run Mistral Small Instruct 2409, the smallest at IQ2_XS. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 14.1 GB of usable unified memory (RAM minus macOS overhead), from MacBook Pro 14" M3 Pro (18 GB).
Can I run Mistral Small Instruct 2409 locally?
Yes — Mistral Small Instruct 2409 can run locally on consumer hardware. 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 ~340 tok/s on AMD Instinct MI350X. 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: NVIDIA B200 → 8000 ÷ 14.12 × 0.65 = ~368 tok/s
Estimated speed at Q4_K_M (14.1 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 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 (IQ2_XS) is 6.67 GB.
Which GPUs can run Mistral Small Instruct 2409?
26 consumer GPUs can run Mistral Small Instruct 2409 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 Instruct 2409?
124 devices with unified memory can run Mistral Small Instruct 2409 at Q4_K_M (14.1 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.