TI

TinyMistral 248M v2 Instruct

TinymistralGGUF by M4-aiUpdated 2024-02-03
Download on Hugging Face
Parameters248M
Context32K
Layers12
Architecturellama
Smallest quant0.1 GB
Quick answer

TinyMistral 248M v2 Instruct needs about 0.8 GB of memory at Q4_K_M (a 0.2 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 6 quants, from 0.1 GB (Q2_K) to 0.3 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 0.4 GB.

TinyMistral 248M v2 Instruct – a compact instruction‑tuned LLM

TinyMistral 248M v2 Instruct is a 248 million‑parameter model fine‑tuned on the HuggingFaceH4/ultrachat_200k dataset. It supports 32 768‑token context and is released under the Apache‑2.0 license.

Good at

  • Fast inference on low‑end GPUs
  • Small model size
  • Instruction following

Limits

  • Limited to 32 768‑token context
  • No vision or multimodal support
  • Requires at least 8 k context for memory estimates

Best for

  • Quick prototyping
  • Edge device inference
  • Chatbot demos

Who it’s for. Developers needing a lightweight instruction‑tuned model for local deployment. Suitable for projects with limited GPU memory or where quick iteration is required.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K0.1 GB 0.7 GB
Fits Get file →
Q3_K_M0.1 GB 0.7 GB
Fits Get file →
Q4_K_M0.2 GB 0.8 GB
Fits Get file →
Q5_K_M0.2 GB 0.8 GB
Fits Get file →
Q6_K0.2 GB 0.8 GB
Fits Get file →
Q8_00.3 GB 0.9 GB
Fits Get file →

For 8 GB VRAM, Q4_K_M or Q5_K_M provide a good balance of size and memory usage (~0.8 GB at 8 k context). If memory is tighter, Q3_K_M or Q2_K are available (~0.7 GB). For maximum quality, use Q8_0 (~0.9 GB).

What GPU do you need for TinyMistral 248M v2 Instruct?

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: the best quant that fits is Q8_0 (0.3 GB file, about 0.9 GB in use).

Which TinyMistral 248M v2 Instruct quant should you choose?

Q4_K_M is the usual starting point for TinyMistral 248M v2 Instruct: it balances file size and quality well. Here it is a 0.2 GB file.

The Q8_0 file is 0.3 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 Q2_K at 0.1 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
Parameters248M
Layers12
Trained context32,768 tokens
KV cache (fp16)12 KB per token

Source

Quantized byM4-ai
Licenseapache-2.0
Downloads (HF)24,319
Last updated2024-02-03

Frequently asked questions about TinyMistral 248M v2 Instruct

How much VRAM does TinyMistral 248M v2 Instruct need?

About 0.8 GB at Q4_K_M with an 8K context window. That is the 0.2 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 TinyMistral 248M v2 Instruct on an 8 GB GPU?

Yes, with Q8_0: the 0.3 GB file needs about 0.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of TinyMistral 248M v2 Instruct GGUF?

It depends on the quant: Q2_K is 0.1 GB, Q3_K_M is 0.1 GB, Q4_K_M is 0.2 GB, Q5_K_M is 0.2 GB, Q6_K is 0.2 GB, Q8_0 is 0.3 GB.

What context length does TinyMistral 248M v2 Instruct support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.1 GB at 8K and 0.4 GB at 32K.

Where can I download TinyMistral 248M v2 Instruct GGUF?

The files are on Hugging Face in the M4-ai/TinyMistral-248M-v2-Instruct-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does TinyMistral 248M v2 Instruct use?

Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run TinyMistral 248M v2 Instruct on 8 GB VRAM?

Yes, using Q4_K_M or Q5_K_M quantizations will fit within 8 GB VRAM, with estimated memory around 0.8 GB at 8 k context.

Does this model support vision or multimodal inputs?

No, the model is purely text‑based and does not include vision capabilities.

What is the maximum context length I can use?

The model supports up to 32,768 tokens of context.

Other GGUFs of TinyMistral-248M-v2-Instruct

Similar models

Browse all →

More Tinymistral models

All Tinymistral →

Other tiny models

All tiny models →