How much VRAM does Ministral 3 8B Instruct need?

About 6.0 GB at Q4_K_M with 4K of context and batch 1, rising to roughly 10.1 GB at 32K. That figure is weights plus KV cache plus a 10% activation buffer, calculated from the model's architecture rather than measured on a card.

Will Ministral 3 8B Instruct run on a 8GB GPU?

Yes — at Q4_K_M and 4K context it needs about 6.0 GB, which leaves 2.0 GB spare on a RTX 5060 Ti 8G. That is the smallest card in this index that clears it comfortably; 61 of 61 do.

Which quantization of Ministral 3 8B Instruct should I use?

No published quality comparison exists for this model, so pick by footprint: Q4_K_M is the level most people run, and a higher bits-per-weight level is more faithful. All 3 levels in the index are Q4_K_M, Q5_K_M, Q8_0.

Ministral 3 8B Instruct

Mistral Ministral 3

Mistral ships the GGUF itself, in 3B / 8B / 14B and Instruct or Reasoning variants — the 8B is the one that fits an 8GB card at Q4 with room for real context. Plain full attention on all 34 layers, so the memory estimates below behave the way the calculator assumes. Quality loss per level has not been published.

⬇ 97.2K HF downloads♥ 201 likesmistralai/Ministral-3-8B-Instruct-2512· stats from 9/11/2026

Consumer GPUMac / Apple SiliconCPU / VPS

262K

Max Context

Quant Variants

GGUF Q8_0

Best Quality

—

Accuracy Retained

Calculate VRAM Hugging Face Compare

Quantization Variants

Per-quant VRAM, quality loss, and inference speed on RTX 4090

Measured = site benchmarks · Estimated = formula · Community = public reports

Format	Level	BPW	VRAM	PPL Loss	Speed	Source	Actions
GGUF	Q4_K_M	4.9	5.2 GB	—	—	Community	Calc HF
GGUF	Q5_K_M	5.71	6.1 GB	—	—	Community	Calc HF
GGUF	Q8_0	8.51	9.0 GB	—	—	Community	Calc HF

Similar models

Compare with Llama 3.1

Llama 3.1 8B Instruct

Meta Llama 3.1

Consumer GPUMac / Apple Silicon

3.2 GBmin VRAM99.9%accuracy

Meta's flagship 8B model with 128K context. Best-in-class for local deployment.

Qwen2.5 7B Instruct

Alibaba Qwen2.5

Consumer GPUMac / Apple Silicon

4.8 GBmin VRAM99.3%accuracy

Alibaba's highly optimized 7B. Punches well above its weight, especially in coding.

3.8B

Phi-3.5 Mini Instruct

Microsoft Phi

Consumer GPUMac / Apple Silicon

2.5 GBmin VRAM99.8%accuracy

Microsoft's tiny powerhouse. Best 4B model for on-device deployment.

Nous Hermes 3 Llama 3.1 8B

NousResearch

Consumer GPUMac / Apple Silicon

5.4 GBmin VRAM97.7%accuracy

Fine-tuned Llama 3.1 8B with improved roleplay and instruction following.

Running Ministral 3 8B Instruct locally

At Q4_K_M and 4K of context, Ministral 3 8B Instruct needs about 6.0 GB — 4.9 GB of weights, 0.53 GB of KV cache and a 0.6 GB activation buffer. The smallest card in this index that clears that comfortably is the RTX 5060 Ti 8G at 8 GB, and 61 of the 61 cards here do. These are calculated figures, not measurements: the estimate stops counting a card as comfortable at 88% of its VRAM, which is roughly the room a desktop session needs.

What longer context costs

Going from 4K to 32K adds about 3.72 GB, taking the total to 10.1 GB. Weights do not move with context — only the KV cache does, and it grows linearly, so this is the number to watch when planning for long documents. The model's native window is 256K; holding all of it at Q4_K_M would need about 43 GB.

Which build to download

This index only tracks Ministral 3 8B Instruct in GGUF, across 3 levels (Q4_K_M, Q5_K_M, Q8_0). No per-level perplexity sweep has been published for this model, so the quality column is empty rather than estimated — within one model, more bits per weight is the only ordering the data supports. No throughput has been measured for this model on this site's hardware. GGUF runs on llama.cpp and Ollama across NVIDIA, AMD and Apple silicon; AWQ and GPTQ target vLLM on CUDA and ROCm; EXL2 is ExLlamaV2 and CUDA only.

Common questions

How much VRAM does Ministral 3 8B Instruct need?: About 6.0 GB at Q4_K_M with 4K of context and batch 1, rising to roughly 10.1 GB at 32K. That figure is weights plus KV cache plus a 10% activation buffer, calculated from the model's architecture rather than measured on a card.
Will Ministral 3 8B Instruct run on a 8GB GPU?: Yes — at Q4_K_M and 4K context it needs about 6.0 GB, which leaves 2.0 GB spare on a RTX 5060 Ti 8G. That is the smallest card in this index that clears it comfortably; 61 of 61 do.
Which quantization of Ministral 3 8B Instruct should I use?: No published quality comparison exists for this model, so pick by footprint: Q4_K_M is the level most people run, and a higher bits-per-weight level is more faithful. All 3 levels in the index are Q4_K_M, Q5_K_M, Q8_0.

How to actually run this

Deployment guides for this model and this class of hardware.