MI

Ministral 8B Instruct 2410

MistralGGUF by bartowskiUpdated 2024-10-16
Download on Hugging Face
Parameters8B
Context32K
Layers36
Architecturellama
Smallest quant3.0 GB
Quick answer

Ministral 8B Instruct 2410 needs about 6.6 GB of memory at Q4_K_M (a 4.9 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 24 quants, from 3.0 GB (IQ2_M) to 16.0 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.8 GB.

Ministral 8B Instruct 2410 – 8B multilingual instruction‑tuned LLM

Ministral 8B Instruct 2410 is a 8B parameter causal language model based on the Mistral architecture. It is instruction‑tuned for chat‑style interactions and supports a 32768 token context window. The model is available in multiple GGUF quantizations via llama.cpp.

Good at

  • Chat‑style instruction following
  • Multilingual text generation
  • Contextual question answering

Limits

  • No vision support
  • License not specified
  • Large context requires significant VRAM

Best for

  • Building chatbots
  • Generating instructional content
  • Fine‑tuning for specific domains

Who it’s for. Developers and researchers who need a compact, instruction‑tuned model for local deployment. It is suitable for environments with limited GPU memory but sufficient RAM for the chosen quantization.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ2_M3.0 GB 4.7 GB
Fits Get file →
Q2_K3.2 GB 4.9 GB
Fits Get file →
IQ3_XS3.5 GB 5.2 GB
Fits Get file →
Q3_K_S3.7 GB 5.4 GB
Fits Get file →
Q2_K_L3.7 GB 5.4 GB
Fits Get file →
IQ3_M3.8 GB 5.5 GB
Fits Get file →
Q3_K_M4.0 GB 5.7 GB
Fits Get file →
Q3_K_L4.3 GB 6.0 GB
Fits Get file →
IQ4_XS4.4 GB 6.2 GB
Fits Get file →
Q4_04.7 GB 6.4 GB
Fits Get file →
Q4_04.7 GB 6.4 GB
Fits Get file →
Q4_04.7 GB 6.4 GB
Fits Get file →
Q4_04.7 GB 6.4 GB
Fits Get file →
Q4_K_S4.7 GB 6.4 GB
Fits Get file →
Q3_K_XL4.8 GB 6.5 GB
Fits Get file →
Q4_K_M4.9 GB 6.6 GB
Fits Get file →
Q4_K_L5.3 GB 7.0 GB
Fits Get file →
Q5_K_S5.6 GB 7.3 GB
Tight Get file →
Q5_K_M5.7 GB 7.4 GB
Tight Get file →
Q5_K_L6.1 GB 7.8 GB
Tight Get file →
Q6_K6.6 GB 8.3 GB
Too big Get file →
Q6_K_L6.8 GB 8.6 GB
Too big Get file →
Q8_08.5 GB 10.2 GB
Too big Get file →
F1616.0 GB 17.8 GB
Too big Get file →

For 8 GB VRAM use Q4_0 (file size 4.66 GB, estimated 6.4 GB memory at 8 k context). For 12 GB VRAM use Q4_K_L (file size 5.31 GB, estimated 7 GB memory). For 16 GB VRAM use Q5_K_L (file size 6.06 GB, estimated 7.8 GB memory).

What GPU do you need for Ministral 8B Instruct 2410?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: no quant fits at an 8K context.
  • 6 GB VRAM: the best quant that fits is Q3_K_L (4.3 GB file, about 6.0 GB in use).
  • 8 GB VRAM: the best quant that fits is Q5_K_L (6.1 GB file, about 7.8 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (8.5 GB file, about 10.2 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (8.5 GB file, about 10.2 GB in use).
  • 24 GB VRAM: the best quant that fits is F16 (16.0 GB file, about 17.8 GB in use).

Which Ministral 8B Instruct 2410 quant should you choose?

Q4_K_M is the usual starting point for Ministral 8B Instruct 2410: it balances file size and quality well. Here it is a 4.9 GB file.

The Q8_0 file is 8.5 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is IQ2_M at 3.0 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters8B
Layers36
Trained context32,768 tokens
KV cache (fp16)144 KB per token

Source

Quantized bybartowski
FamilyMistral
Downloads (HF)1,996
Last updated2024-10-16

Frequently asked questions about Ministral 8B Instruct 2410

How much VRAM does Ministral 8B Instruct 2410 need?

About 6.6 GB at Q4_K_M with an 8K context window. That is the 4.9 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run Ministral 8B Instruct 2410 on an 8 GB GPU?

Yes, with Q5_K_L: the 6.1 GB file needs about 7.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Ministral 8B Instruct 2410 GGUF?

It depends on the quant: IQ2_M is 3.0 GB, Q2_K is 3.2 GB, IQ3_XS is 3.5 GB, Q3_K_S is 3.7 GB, Q2_K_L is 3.7 GB, IQ3_M is 3.8 GB and 18 more.

What context length does Ministral 8B Instruct 2410 support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.2 GB at 8K and 4.8 GB at 32K.

Where can I download Ministral 8B Instruct 2410 GGUF?

The files are on Hugging Face in the bartowski/Ministral-8B-Instruct-2410-HF-GGUF-TEST repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Can I run Q4_0 on 8 GB VRAM?

Yes, Q4_0 requires about 6.4 GB memory at 8 k context, which fits in 8 GB VRAM with some headroom.

What is the largest quantization that fits in 12 GB VRAM?

Q4_K_L fits in 12 GB VRAM, using about 7 GB memory at 8 k context.

Does the model support vision tasks?

No, the model has no vision capabilities.

Similar models

Browse all →

More from bartowski

All by bartowski →

More Mistral models

All Mistral →

Other small models

All small models →