Ministral 8B Instruct 2410 — Hardware Requirements & GPU Compatibility
Chat
Ministral 8B Instruct 2410 is Mistral AI's 8-billion-parameter instruction-tuned model, part of the "Ministraux" family aimed at edge and on-device deployment. It uses a 36-layer dense transformer with interleaved sliding-window attention, trained heavily on multilingual and code data, suiting chat, function calling, and general assistant tasks across ten languages. Its compact size means it runs comfortably on a single mainstream consumer GPU once quantized. The model supports a 32K token context window. It is released under Mistral's own license, listed as "Other," which restricts use to research purposes and requires a separate commercial license from Mistral AI, so review the terms before commercial use. It was published in October 2024 alongside the smaller Ministral 3B.
152.8K downloads
586 likesSpecifications
- Publisher
- Mistral AI
- Family
- Mistral
- Parameters
- 8.0B
- Architecture
- MistralForCausalLM
- Context Length
- 32,768 tokens
- Vocabulary Size
- 131,072
- Release Date
- 2024-10-15
- License
- Other
Get Started
HuggingFace
How Much VRAM Does Ministral 8B Instruct 2410 Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| Q2_K | 3.40 | 4.0 GB | 8.5 GB | 3.41 GB | 2-bit quantization with K-quant improvements |
| Q3_K_S | 3.50 | 4.1 GB | 8.6 GB | 3.51 GB | 3-bit small quantization |
| Q3_K_M | 3.90 | 4.5 GB | 9.0 GB | 3.91 GB | 3-bit medium quantization |
| Q4_0 | 4.00 | 4.6 GB | 9.1 GB | 4.01 GB | 4-bit legacy quantization |
| Q4_K_M | 4.80 | 5.4 GB | 9.9 GB | 4.81 GB | 4-bit medium quantization — most popular sweet spot |
| Q5_K_M | 5.70 | 6.3 GB | 10.8 GB | 5.71 GB | 5-bit medium quantization — good quality/size tradeoff |
| Q6_K | 6.60 | 7.2 GB | 11.8 GB | 6.62 GB | 6-bit quantization, very good quality |
| Q8_0 | 8.00 | 8.6 GB | 13.2 GB | 8.02 GB | 8-bit quantization, near-lossless |
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 Ministral 8B Instruct 2410?
Q4_K_M · 5.4 GBMinistral 8B Instruct 2410 (Q4_K_M) requires 5.4 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 8+ GB is recommended. Using the full 33K context window can add up to 4.5 GB, bringing total usage to 9.9 GB. 52 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti, NVIDIA GeForce RTX 3070 Ti.
Runs great
— Plenty of headroom
Decent
— Enough VRAM, may be tightWhich Devices Can Run Ministral 8B Instruct 2410?
Q4_K_M · 5.4 GB58 devices with unified memory can run Ministral 8B Instruct 2410, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, MacBook Air 13" M3 (8 GB).
Runs great
— Plenty of headroomWhere to Download Ministral 8B Instruct 2410
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 Ministral 8B Instruct 2410 need?
Ministral 8B Instruct 2410 requires 5.4 GB of VRAM at Q4_K_M, or 16.6 GB at BF16. Full 33K context adds up to 4.5 GB (9.9 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 8.0B × 4.8 bits ÷ 8 = 4.8 GB
KV Cache + Overhead ≈ 0.6 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 5.1 GB (at full 33K context)
VRAM usage by quantization
Q4_K_M5.4 GBQ4_K_M + full context9.9 GB- What's the best quantization for Ministral 8B Instruct 2410?
For Ministral 8B Instruct 2410, Q4_K_M (5.4 GB) offers the best balance of quality and VRAM usage. Q4_K_L (5.5 GB) provides better quality if you have the VRAM. The smallest option is IQ2_M at 3.3 GB.
VRAM requirement by quantization
IQ2_M3.3 GBIQ3_M4.2 GBQ4_K_S5.1 GBQ4_K_M ★5.4 GBQ5_K_M6.3 GBBF1616.6 GB★ Recommended — best balance of quality and VRAM usage.
- Can I run Ministral 8B Instruct 2410 on a Mac?
Ministral 8B Instruct 2410 requires at least 3.3 GB at IQ2_M, 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 Ministral 8B Instruct 2410 locally?
Yes — Ministral 8B Instruct 2410 can run locally on consumer hardware. At Q4_K_M quantization it needs 5.4 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is Ministral 8B Instruct 2410?
At Q4_K_M, Ministral 8B Instruct 2410 can reach ~887 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~121 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 ÷ 5.4 × 0.65 = ~961 tok/s
Estimated speed at Q4_K_M (5.4 GB)
~961 tok/s~121 tok/s~961 tok/s~887 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of Ministral 8B Instruct 2410?
At Q4_K_M, the download is about 4.81 GB. The full-precision BF16 version is 16.04 GB. The smallest option (IQ2_M) is 2.71 GB.
- Which GPUs can run Ministral 8B Instruct 2410?
52 consumer GPUs can run Ministral 8B Instruct 2410 at Q4_K_M (5.4 GB). Top options include AMD Radeon RX 6700 XT, AMD Radeon RX 6800, AMD Radeon RX 6800 XT, AMD Radeon RX 7600. 40 GPUs have plenty of headroom for comfortable inference.
- Which devices can run Ministral 8B Instruct 2410?
59 devices with unified memory can run Ministral 8B Instruct 2410 at Q4_K_M (5.4 GB), including AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10, Apple iPhone 17 Pro, Asus ROG Flow Z13 (2025, 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.