Mistral Small 24B Instruct 2501 Quantized.w8a8 — Hardware Requirements & GPU Compatibility
Chat
Mistral Small 24B Instruct 2501 Quantized.w8a8 is a 23.6B-parameter open language model from RedHatAI in the Mistral family. It supports a context window of up to 32,768 tokens. At Q4_K_M it needs about 14.86 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 · 4K)Best on 24 GB (Q4_K_M · ~44 tok/s · 32K)Macs from 18 GB (Q2_K · ~10 tok/s)
Apache 2.0
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Mistral Small 24B Instruct 2501 Quantized.w8a8
One recommended way. Every other method, OS and quant is in the step-by-step guide.
Recommended
vllm serve RedHatAI/Mistral-Small-24B-Instruct-2501-quantized.w8a8 --max-model-len 16384vLLM repo with its own quantisation
Download: Weights on Hugging Face
Other ways
each opens step-by-stepRun in cloud
Fits on RTX 3090 (24 GB) (6 GB headroom) · Q4_K_M
- Generation speed
- ~41 tok/s
- generation speed
- Cost per 1M output tokens
- $1.46
- per 1M output tokens
How Much VRAM Does Mistral Small 24B Instruct 2501 Quantized.w8a8 Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 10.7 GB | 17 GB | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Fits: 32K context · ~61 tok/s | |
| 12.2 GB | 18.5 GB | 3-bit medium — 3-bit medium quantization | Fits: 32K context · ~54 tok/s | |
| 14.9 GB | 21.2 GB | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Fits: 32K context · ~44 tok/s | |
| 17.5 GB | 23.8 GB | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Fits: 32K context · ~37 tok/s | |
| 20.2 GB | 26.5 GB | 6-bit, very good — 6-bit quantization, very good quality | Fits: 16K context · ~33 tok/s | |
| 24.3 GB | 30.6 GB | 8-bit, near-lossless — 8-bit quantization, near-lossless | Does not fit: needs 27.2 GB | |
| 47.9 GB | 54.2 GB | 16-bit · bfloat — Brain floating point 16 — preferred for training | Does not fit: needs 50.8 GB |
Selected Q4_K_M
4-bit medium quantization17.8GBat 16K context
- Weights
- 14.1 GB
- KV cache
- 3.4 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 6.2 GB free · ~44 tok/s
≥50 tok/s needs ≥1.14 TB/s · RTX 5090 ~78
Which Hardware Can Run Mistral Small 24B Instruct 2501 Quantized.w8a8?
Q4_K_M · 14.9 GBMistral Small 24B Instruct 2501 Quantized.w8a8 (Q4_K_M) requires 14.9 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 33K context window can add up to 6.3 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. 122 devices with unified memory can run Mistral Small 24B Instruct 2501 Quantized.w8a8, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB), Mac Mini M5 Pro (24 GB).
20 GB
fits · 2.2 GB free · up to 16K ctx
1 GPU
RX 7900 XT~32Simulate output on RX 7900 XT32–40 GB
fits · 14.2 GB free · up to 32K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~78Simulate output on RTX 5090M5 Max36 GB~22Simulate output on Mac Studio M5 Max (36 GB)M532 GB~7Simulate 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
Alternatives to Mistral Small 24B Instruct 2501 Quantized.w8a8
Mistral family · 34 models →Similar models
3| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| LFM2.5 24B A2BLiquid AI | — | 15 GB | ~221 | same size |
| Ariarhymes-ai | — | 20.2 GB | ~168 | same size |
| EuroLLM 22B Instruct 2512utter-project | — | 17.5 GB | ~46 | same size |
Specifications
- Publisher
- RedHatAI
- Family
- Mistral
- Parameters
- 23.6B
- Architecture
- MistralForCausalLM
- Context Length
- 32,768 tokens
- Vocabulary Size
- 131,072
- Release Date
- 2025-03-03
- License
- Apache 2.0
Frequently Asked Questions
How much VRAM does Mistral Small 24B Instruct 2501 Quantized.w8a8 need?
Mistral Small 24B Instruct 2501 Quantized.w8a8 requires 14.9 GB of VRAM at Q4_K_M, or 47.9 GB at BF16. Full 33K context adds up to 6.3 GB (21.2 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 23.6B × 4.8 bits ÷ 8 = 14.1 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 ≈ 7.1 GB (at full 33K context)
VRAM usage by quantization
Can NVIDIA GeForce RTX 4090 run Mistral Small 24B Instruct 2501 Quantized.w8a8?
Yes, at Q6_K (20.2 GB) or lower. Higher quantizations like Q8_0 (24.3 GB) exceed the NVIDIA GeForce RTX 4090's 24 GB.
What's the best quantization for Mistral Small 24B Instruct 2501 Quantized.w8a8?
For Mistral Small 24B Instruct 2501 Quantized.w8a8, Q4_K_M (14.9 GB) offers the best balance of quality and VRAM usage. Q5_K_M (17.5 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 10.7 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run Mistral Small 24B Instruct 2501 Quantized.w8a8 on a Mac?
Yes — MacBook Pro 14" M3 Pro (18 GB) and 108 other Macs can run Mistral Small 24B Instruct 2501 Quantized.w8a8, the smallest at Q2_K. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 14.9 GB of usable unified memory (RAM minus macOS overhead), from Mac Mini M5 Pro (24 GB).
Can I run Mistral Small 24B Instruct 2501 Quantized.w8a8 locally?
Yes — Mistral Small 24B Instruct 2501 Quantized.w8a8 can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Mistral Small 24B Instruct 2501 Quantized.w8a8?
At Q4_K_M, Mistral Small 24B Instruct 2501 Quantized.w8a8 can reach ~323 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~44 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 ÷ 14.86 × 0.65 = ~350 tok/s
Estimated speed at Q4_K_M (14.9 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 24B Instruct 2501 Quantized.w8a8?
At Q4_K_M, the download is about 14.15 GB. The full-precision BF16 version is 47.15 GB. The smallest option (Q2_K) is 10.02 GB.
Which GPUs can run Mistral Small 24B Instruct 2501 Quantized.w8a8?
26 consumer GPUs can run Mistral Small 24B Instruct 2501 Quantized.w8a8 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 24B Instruct 2501 Quantized.w8a8?
122 devices with unified memory can run Mistral Small 24B Instruct 2501 Quantized.w8a8 at Q4_K_M (14.9 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.