ZE

Zedev 134m

ZedevGGUF by mradermacherUpdated 2026-10-10
Download on Hugging Face
Parameters134M
Context1K
Layers26
Architectureqwen3
Smallest quant0.1 GB
Quick answer

Zedev 134m needs about 0.7 GB of memory at Q4_K_M (a 0.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 12 quants, from 0.1 GB (Q3_K_S) to 0.3 GB (F16).

Zedev 134m – 134M‑parameter Qwen3 causal language model

Zedev 134m is a 134.47M‑parameter causal language model based on the Qwen3 architecture. It supports tool usage and is released under the Apache‑2.0 license. The model was trained with a 1024‑token context window.

Good at

  • Tool‑aware generation
  • Lightweight inference
  • Low‑memory deployment

Limits

  • No vision support
  • English‑only
  • Requires 8k context for full performance

Best for

  • Chatbots with tool integration
  • Rapid prototyping of LLMs
  • Educational demos

Who it’s for. Developers needing a small, tool‑aware language model for quick experiments. Researchers exploring Qwen3 variants in low‑resource settings.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_S0.1 GB 0.6 GB
Fits Get file →
Q2_K0.1 GB 0.6 GB
Fits Get file →
IQ4_XS0.1 GB 0.6 GB
Fits Get file →
Q3_K_M0.1 GB 0.6 GB
Fits Get file →
Q3_K_L0.1 GB 0.6 GB
Fits Get file →
Q4_K_S0.1 GB 0.6 GB
Fits Get file →
Q4_K_M0.1 GB 0.6 GB
Fits Get file →
Q5_K_S0.1 GB 0.6 GB
Fits Get file →
Q5_K_M0.1 GB 0.6 GB
Fits Get file →
Q6_K0.1 GB 0.7 GB
Fits Get file →
Q8_00.1 GB 0.7 GB
Fits Get file →
F160.3 GB 0.8 GB
Fits Get file →

For 4‑GB VRAM, use Q3_K_S, Q2_K, or IQ4_XS – each 0.09 GB and ~0.7 GB RAM at 8k context. For 8‑GB VRAM, any quant up to Q8_0 (0.14 GB) works. The full F16 quant (0.27 GB) needs ~0.9 GB RAM.

What GPU do you need for Zedev 134m?

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 F16 (0.3 GB file, about 0.9 GB in use).

Which Zedev 134m quant should you choose?

Q4_K_M is the usual starting point for Zedev 134m: it balances file size and quality well. Here it is a 0.1 GB file.

The Q8_0 file is 0.1 GB, about 1.4 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 Q3_K_S at 0.1 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen3
Parameters134M
Layers26
Trained context1,024 tokens
KV cache (fp16)13 KB per token

Source

Quantized bymradermacher
FamilyZedev
Licenseapache-2.0
Downloads (HF)581
Last updated2026-10-10

Frequently asked questions about Zedev 134m

How much VRAM does Zedev 134m need?

About 0.7 GB at Q4_K_M with an 8K context window. That is the 0.1 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 Zedev 134m on an 8 GB GPU?

Yes, with F16: 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 Zedev 134m GGUF?

It depends on the quant: Q3_K_S is 0.1 GB, Q2_K is 0.1 GB, IQ4_XS is 0.1 GB, Q3_K_M is 0.1 GB, Q3_K_L is 0.1 GB, Q4_K_S is 0.1 GB and 6 more.

What context length does Zedev 134m support?

The GGUF header lists a trained context length of 1,024 tokens (1K). The KV cache grows with the context you use: about 0.1 GB at 8K and 0.0 GB at 1K.

Where can I download Zedev 134m GGUF?

The files are on Hugging Face in the mradermacher/Zedev-134m-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 Zedev 134m 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 Zedev 134m on 8 GB VRAM?

Yes. All quantized files use less than 1 GB of RAM at 8k context, fitting comfortably on 8 GB VRAM.

Does Zedev 134m support vision?

No. The model only handles text and tool usage.

What license applies to Zedev 134m?

Apache‑2.0. The model and its GGUF files are released under this license.

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Zedev models

All Zedev →

Other tiny models

All tiny models →