DA

Datamix 9b 60 40

DatamixGGUF by mradermacherUpdated 2026-10-23
Download on Hugging Face
Parameters9.93B
Context2K
Layers32
Architecturellama
Smallest quant4.1 GB
Quick answer

Datamix 9b 60 40 needs about 11.0 GB of memory at Q4_K_M (a 6.2 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 12 quants, from 4.1 GB (Q2_K) to 19.9 GB (F16).

Datamix 9b 60 40 – a 9.93B‑parameter Llama‑style decoder

Datamix 9b 60 40 is a decoder‑only model with 9.93B parameters and a 2048‑token context window. It is trained on a multilingual mix of English, code, math and European languages. The model is released under the Apache‑2.0 license.

Good at

  • Coding
  • Multilingual text generation
  • Math problem solving

Limits

  • No vision support
  • Requires at least 8 GB VRAM for Q2_K
  • License allows free use

Best for

  • Developers building code assistants
  • Researchers testing multilingual LLMs
  • Educators creating math tutoring tools

Who it’s for. The model is suitable for developers, researchers, and educators who need a versatile, open‑source LLM with strong coding and multilingual capabilities. It is ideal for projects that can accommodate a 2048‑token context window and the memory requirements of the chosen quant.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K4.1 GB 5.7 GB
Fits Get file →
Q3_K_S4.7 GB 6.3 GB
Fits Get file →
Q3_K_M5.1 GB 6.7 GB
Fits Get file →
Q3_K_L5.5 GB 7.0 GB
Fits Get file →
IQ4_XS5.6 GB 7.2 GB
Tight Get file →
Q4_K_S5.9 GB 7.5 GB
Tight Get file →
Q4_K_M6.2 GB 7.8 GB
Tight Get file →
Q5_K_S7.0 GB 8.6 GB
Too big Get file →
Q5_K_M7.1 GB 8.7 GB
Too big Get file →
Q6_K8.2 GB 9.7 GB
Too big Get file →
Q8_010.6 GB 12.1 GB
Too big Get file →
F1619.9 GB 21.4 GB
Too big Get file →

For 8 GB VRAM use Q2_K (4.1 GB file, ~8.9 GB memory). With 10 GB VRAM Q3_K_S (4.7 GB file, ~9.5 GB memory) or Q4_K_S (5.91 GB file, ~10.7 GB memory). For 16 GB VRAM Q5_K_M (7.14 GB file, ~11.9 GB memory) or Q6_K (8.16 GB file, ~13 GB memory).

What GPU do you need for Datamix 9b 60 40?

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: no quant fits at an 8K context.
  • 8 GB VRAM: no quant fits at an 8K context.
  • 12 GB VRAM: the best quant that fits is Q5_K_M (7.1 GB file, about 11.9 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (10.6 GB file, about 15.4 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_0 (10.6 GB file, about 15.4 GB in use).
  • 32 GB VRAM: the best quant that fits is F16 (19.9 GB file, about 24.7 GB in use).

Which Datamix 9b 60 40 quant should you choose?

Q4_K_M is the usual starting point for Datamix 9b 60 40: it balances file size and quality well. Here it is a 6.2 GB file.

The Q8_0 file is 10.6 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 4.1 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
Parameters9.93B
Layers32
Trained context2,048 tokens
KV cache (fp16)512 KB per token

Source

Quantized bymradermacher
FamilyDatamix
Licenseapache-2.0
Downloads (HF)783
Last updated2026-10-23

Frequently asked questions about Datamix 9b 60 40

How much VRAM does Datamix 9b 60 40 need?

About 11.0 GB at Q4_K_M with an 8K context window. That is the 6.2 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 Datamix 9b 60 40 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 8.9 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Datamix 9b 60 40 GGUF?

It depends on the quant: Q2_K is 4.1 GB, Q3_K_S is 4.7 GB, Q3_K_M is 5.1 GB, Q3_K_L is 5.5 GB, IQ4_XS is 5.6 GB, Q4_K_S is 5.9 GB and 6 more.

What context length does Datamix 9b 60 40 support?

The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 4.3 GB at 8K and 1.1 GB at 2K.

Where can I download Datamix 9b 60 40 GGUF?

The files are on Hugging Face in the mradermacher/datamix-9b-60-40-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 Datamix 9b 60 40 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 Datamix 9b 60 40 on 8 GB VRAM?

Yes, using the Q2_K quant which requires about 8.9 GB of VRAM at 8K context.

Does the model support image inputs?

No, Datamix 9b 60 40 is a text‑only decoder model.

What license applies to this model?

The model is released under the Apache‑2.0 license, allowing free use and modification.

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Datamix models

All Datamix →

Other medium models

All medium models →