Ministral 3 14B Reasoning 2512 — Hardware Requirements & GPU Compatibility
Reasoning
Ministral 3 14B Reasoning 2512 is a 13.9B-parameter open language model from Mistral AI in the Mistral family. It supports a context window of up to 262,144 tokens. At Q4_K_M it needs about 9.09 GB of VRAM — see which GPUs and Macs can run it below.
109.5K downloads
152 likesSpecifications
- Publisher
- Mistral AI
- Family
- Mistral
- Parameters
- 13.9B
- Architecture
- Mistral3ForConditionalGeneration
- Context Length
- 262,144 tokens
- Vocabulary Size
- 131,072
- Release Date
- 2025-10-31
- License
- Apache 2.0
Get Started
HuggingFace
How Much VRAM Does Ministral 3 14B Reasoning 2512 Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| Q2_K | 3.40 | 6.7 GB | 59.9 GB | 5.93 GB | 2-bit quantization with K-quant improvements |
| Q3_K_M | 3.90 | 7.5 GB | 60.8 GB | 6.80 GB | 3-bit medium quantization |
| Q3_K_L | 4.10 | 7.9 GB | 61.1 GB | 7.15 GB | 3-bit large quantization |
| Q4_K_M | 4.80 | 9.1 GB | 62.4 GB | 8.37 GB | 4-bit medium quantization — most popular sweet spot |
| Q5_K_M | 5.70 | 10.7 GB | 63.9 GB | 9.94 GB | 5-bit medium quantization — good quality/size tradeoff |
| Q6_K | 6.60 | 12.2 GB | 65.5 GB | 11.50 GB | 6-bit quantization, very good quality |
| Q8_0est. | 8.00 | 14.7 GB | 67.9 GB | 13.95 GB | 8-bit quantization, near-lossless |
| BF16est. | 16.00 | 28.6 GB | 81.9 GB | 27.89 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 Ministral 3 14B Reasoning 2512?
Q4_K_M · 9.1 GBMinistral 3 14B Reasoning 2512 (Q4_K_M) requires 9.1 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 12+ GB is recommended. Using the full 262K context window can add up to 53.3 GB, bringing total usage to 62.4 GB. 40 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti, NVIDIA GeForce RTX 3080 Ti.
Runs great
— Plenty of headroom
Decent
— Enough VRAM, may be tightWhich Devices Can Run Ministral 3 14B Reasoning 2512?
Q4_K_M · 9.1 GB49 devices with unified memory can run Ministral 3 14B Reasoning 2512, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, iPad Pro M5 13" (16 GB).
Runs great
— Plenty of headroomDecent
— Enough memory, may be tightWhere to Download Ministral 3 14B Reasoning 2512
Community quantizations of this model — GGUF for llama.cpp, Ollama, and LM Studio, plus AWQ/MLX variants where available.
Related Models
Frequently Asked Questions
- How much VRAM does Ministral 3 14B Reasoning 2512 need?
Ministral 3 14B Reasoning 2512 requires 9.1 GB of VRAM at Q4_K_M, or 28.6 GB at BF16. Full 262K context adds up to 53.3 GB (62.4 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 13.9B × 4.8 bits ÷ 8 = 8.4 GB
KV Cache + Overhead ≈ 0.7 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 54 GB (at full 262K context)
VRAM usage by quantization
Q4_K_M9.1 GBQ4_K_M + full context62.4 GB- Can NVIDIA GeForce RTX 4090 run Ministral 3 14B Reasoning 2512?
Yes, at Q8_0 (14.7 GB) or lower. Higher quantizations like BF16 (28.6 GB) exceed the NVIDIA GeForce RTX 4090's 24 GB.
- What's the best quantization for Ministral 3 14B Reasoning 2512?
For Ministral 3 14B Reasoning 2512, Q4_K_M (9.1 GB) offers the best balance of quality and VRAM usage. Q5_K_M (10.7 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 6.7 GB.
VRAM requirement by quantization
Q2_K6.7 GBQ3_K_L7.9 GBQ4_K_M ★9.1 GBQ5_K_M10.7 GBQ6_K12.2 GBBF1628.6 GB★ Recommended — best balance of quality and VRAM usage.
- Can I run Ministral 3 14B Reasoning 2512 on a Mac?
Ministral 3 14B Reasoning 2512 requires at least 6.7 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 Ministral 3 14B Reasoning 2512 locally?
Yes — Ministral 3 14B Reasoning 2512 can run locally on consumer hardware. At Q4_K_M quantization it needs 9.1 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is Ministral 3 14B Reasoning 2512?
At Q4_K_M, Ministral 3 14B Reasoning 2512 can reach ~528 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~72 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 ÷ 9.1 × 0.65 = ~572 tok/s
Estimated speed at Q4_K_M (9.1 GB)
~572 tok/s~72 tok/s~572 tok/s~528 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of Ministral 3 14B Reasoning 2512?
At Q4_K_M, the download is about 8.37 GB. The full-precision BF16 version is 27.89 GB. The smallest option (Q2_K) is 5.93 GB.
- Which GPUs can run Ministral 3 14B Reasoning 2512?
40 consumer GPUs can run Ministral 3 14B Reasoning 2512 at Q4_K_M (9.1 GB). Top options include AMD Radeon RX 6800, AMD Radeon RX 6800 XT, AMD Radeon RX 6900 XT, AMD Radeon RX 6700 XT. 26 GPUs have plenty of headroom for comfortable inference.
- Which devices can run Ministral 3 14B Reasoning 2512?
52 devices with unified memory can run Ministral 3 14B Reasoning 2512 at Q4_K_M (9.1 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.