TI

TinyMistral 6x248M

TinymistralGGUF by mradermacherUpdated 2025-07-11
Download on Hugging Face
Parameters1B
Context32K
Layers12
Architecturellama
Smallest quant0.2 GB
Quick answer

TinyMistral 6x248M needs about 1.2 GB of memory at Q4_K_M (a 0.6 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 24 quants, from 0.2 GB (IQ1_S) to 0.8 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 0.4 GB.

TinyMistral 6x248M – a 1 billion‑parameter MoE model for coding

TinyMistral 6x248M is a 1 billion‑parameter mixture of experts built from several TinyMistral variants. It supports a 32 768‑token context window and is released under the apache‑2.0 license. The model is optimized for code generation tasks.

Good at

  • Code generation
  • Small‑scale LLM inference
  • Fast inference with low‑precision quants

Limits

  • MoE architecture may cause performance degradation on some APIs
  • No vision support
  • Requires 8 k context for memory estimates

Best for

  • Writing scripts and functions
  • Debugging code snippets
  • Rapid prototyping of code models

Who it’s for. Developers and researchers needing a lightweight code‑focused LLM. The model is suitable for local inference on machines with moderate VRAM and for educational purposes.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S0.2 GB 0.8 GB
Fits Get file →
IQ1_M0.2 GB 0.8 GB
Fits Get file →
IQ2_XXS0.3 GB 0.9 GB
Fits Get file →
IQ2_XS0.3 GB 0.9 GB
Fits Get file →
IQ2_S0.3 GB 0.9 GB
Fits Get file →
IQ2_M0.3 GB 0.9 GB
Fits Get file →
Q2_K_S0.4 GB 1.0 GB
Fits Get file →
Q2_K0.4 GB 1.0 GB
Fits Get file →
IQ3_XXS0.4 GB 1.0 GB
Fits Get file →
IQ3_XS0.4 GB 1.0 GB
Fits Get file →
Q3_K_S0.4 GB 1.0 GB
Fits Get file →
IQ3_S0.4 GB 1.0 GB
Fits Get file →
IQ3_M0.5 GB 1.1 GB
Fits Get file →
Q3_K_M0.5 GB 1.1 GB
Fits Get file →
Q3_K_L0.5 GB 1.1 GB
Fits Get file →
IQ4_XS0.5 GB 1.1 GB
Fits Get file →
IQ4_NL0.6 GB 1.2 GB
Fits Get file →
Q4_00.6 GB 1.2 GB
Fits Get file →
Q4_K_S0.6 GB 1.2 GB
Fits Get file →
Q4_K_M0.6 GB 1.2 GB
Fits Get file →
Q4_10.6 GB 1.2 GB
Fits Get file →
Q5_K_S0.7 GB 1.3 GB
Fits Get file →
Q5_K_M0.7 GB 1.3 GB
Fits Get file →
Q6_K0.8 GB 1.4 GB
Fits Get file →

For 8 GB VRAM, use Q4_K_M (0.61 GB file, ~1.2 GB memory at 8 k context). If 4 GB VRAM is available, Q3_K_M (0.49 GB, ~1.1 GB memory) is a good compromise. For the smallest footprint, IQ1_S (0.22 GB, ~0.8 GB memory) works well on 2 GB VRAM.

What GPU do you need for TinyMistral 6x248M?

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 Q6_K (0.8 GB file, about 1.4 GB in use).

Which TinyMistral 6x248M quant should you choose?

Q4_K_M is the usual starting point for TinyMistral 6x248M: it balances file size and quality well. Here it is a 0.6 GB file.

If memory is tight, the smallest file is IQ1_S at 0.2 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
Parameters1B (approximate, mixture of experts)
Layers12
Trained context32,768 tokens
KV cache (fp16)12 KB per token

Source

Quantized bymradermacher
Licenseapache-2.0
Downloads (HF)719
Last updated2025-07-11

Frequently asked questions about TinyMistral 6x248M

How much VRAM does TinyMistral 6x248M need?

About 1.2 GB at Q4_K_M with an 8K context window. That is the 0.6 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 6x248M on an 8 GB GPU?

Yes, with Q6_K: the 0.8 GB file needs about 1.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of TinyMistral 6x248M GGUF?

It depends on the quant: IQ1_S is 0.2 GB, IQ1_M is 0.2 GB, IQ2_XXS is 0.3 GB, IQ2_XS is 0.3 GB, IQ2_S is 0.3 GB, IQ2_M is 0.3 GB and 18 more.

What context length does TinyMistral 6x248M 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 6x248M GGUF?

The files are on Hugging Face in the mradermacher/TinyMistral-6x248M-i1-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 6x248M 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 6x248M on 8 GB VRAM?

Yes, using Q4_K_M or Q3_K_M quants keeps memory usage below 8 GB, including context overhead.

Does TinyMistral 6x248M support image inputs?

No, the model has no vision capabilities.

What license applies to TinyMistral 6x248M?

The model is released under the apache‑2.0 license.

Other GGUFs of TinyMistral-6x248M

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Tinymistral models

All Tinymistral →

Other tiny models

All tiny models →