TI

TinyEnsemble-3x1.1B-TinyMoE

TinyensembleGGUF by mradermacherUpdated 2024-06-17
Download on Hugging Face
Parameters2.62B
Context4K
Layers22
Architecturellama
Smallest quant1.0 GB
Quick answer

TinyEnsemble-3x1.1B-TinyMoE needs about 2.3 GB of memory at Q4_K_M (a 1.6 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 15 quants, from 1.0 GB (Q2_K) to 5.2 GB (F16).

TinyEnsemble-3x1.1B-TinyMoE: a 2.62B‑parameter MoE model with tool‑use capability

TinyEnsemble-3x1.1B-TinyMoE is a mixture of experts built from three 1.1B models. It supports a 4096‑token context and is released under the apache‑2.0 license. The model is available in multiple GGUF quantizations.

Good at

  • Tool‑use tasks
  • Small‑to‑medium context handling
  • Low‑memory inference

Limits

  • No vision support
  • Requires 8k context for memory estimates
  • Mixture of experts may increase latency

Best for

  • Chatbots needing tool integration
  • Lightweight inference on edge devices
  • Rapid prototyping of MoE models

Who it’s for. Developers and researchers who need a compact MoE model with tool‑use support and a permissive license. The model is suitable for local deployment where GPU memory is limited.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K1.0 GB 1.6 GB
Fits Get file →
IQ3_XS1.1 GB 1.7 GB
Fits Get file →
Q3_K_S1.2 GB 1.7 GB
Fits Get file →
IQ3_S1.2 GB 1.7 GB
Fits Get file →
IQ3_M1.2 GB 1.8 GB
Fits Get file →
Q3_K_M1.3 GB 1.9 GB
Fits Get file →
Q3_K_L1.4 GB 2.0 GB
Fits Get file →
IQ4_XS1.4 GB 2.0 GB
Fits Get file →
Q4_K_S1.5 GB 2.1 GB
Fits Get file →
Q4_K_M1.6 GB 2.2 GB
Fits Get file →
Q5_K_S1.8 GB 2.4 GB
Fits Get file →
Q5_K_M1.9 GB 2.5 GB
Fits Get file →
Q6_K2.2 GB 2.7 GB
Fits Get file →
Q8_02.8 GB 3.4 GB
Fits Get file →
F165.2 GB 5.8 GB
Fits Get file →

For 8 GB VRAM, use Q4_K_M (file size 1.58 GB, estimated 2.3 GB memory). For 6 GB VRAM, Q3_K_M (1.18 GB, 1.9 GB memory). For 4 GB VRAM, Q2_K (0.98 GB, 1.7 GB memory).

What GPU do you need for TinyEnsemble-3x1.1B-TinyMoE?

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 (2.8 GB file, about 3.5 GB in use).
  • 6 GB VRAM: the best quant that fits is F16 (5.2 GB file, about 5.9 GB in use).

Which TinyEnsemble-3x1.1B-TinyMoE quant should you choose?

Q4_K_M is the usual starting point for TinyEnsemble-3x1.1B-TinyMoE: it balances file size and quality well. Here it is a 1.6 GB file.

The Q8_0 file is 2.8 GB, about 1.8 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 1.0 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
Parameters2.62B (approximate, mixture of experts)
Layers22
Trained context4,096 tokens
KV cache (fp16)22 KB per token

Source

Quantized bymradermacher
Licenseapache-2.0
Downloads (HF)1,953
Last updated2024-06-17

Frequently asked questions about TinyEnsemble-3x1.1B-TinyMoE

How much VRAM does TinyEnsemble-3x1.1B-TinyMoE need?

About 2.3 GB at Q4_K_M with an 8K context window. That is the 1.6 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 TinyEnsemble-3x1.1B-TinyMoE on an 8 GB GPU?

Yes, with F16: the 5.2 GB file needs about 5.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of TinyEnsemble-3x1.1B-TinyMoE GGUF?

It depends on the quant: Q2_K is 1.0 GB, IQ3_XS is 1.1 GB, Q3_K_S is 1.2 GB, IQ3_S is 1.2 GB, IQ3_M is 1.2 GB, Q3_K_M is 1.3 GB and 9 more.

What context length does TinyEnsemble-3x1.1B-TinyMoE support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 0.2 GB at 8K and 0.1 GB at 4K.

Where can I download TinyEnsemble-3x1.1B-TinyMoE GGUF?

The files are on Hugging Face in the mradermacher/TinyEnsemble-3x1.1B-TinyMoE-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 TinyEnsemble-3x1.1B-TinyMoE 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 TinyEnsemble-3x1.1B-TinyMoE on 8 GB VRAM?

Yes, the Q4_K_M quant requires about 2.3 GB memory at 8k context, well below 8 GB.

Does the model support vision tasks?

No, the model has no vision capability.

What license does the model use?

The model is released under the apache‑2.0 license.

Similar models

Browse all →

More from mradermacher

All by mradermacher →

Other tiny models

All tiny models →