MI

MicroThinker 1B Preview

MicrothinkerGGUF by quantflexUpdated 2025-01-04
Download on Hugging Face
Parameters1.24B
Context128K
Layers16
Architecturellama
Smallest quant1.2 GB
Quick answer

MicroThinker 1B Preview needs about 2.1 GB of memory at Q6_K (a 1.3 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 4 quants, from 1.2 GB (Q5_K_M) to 5.0 GB (F32). Longer context needs more: at 32K tokens the KV cache alone adds about 1.1 GB.

MicroThinker 1B Preview is a 1.24B-parameter Microthinker model in GGUF format, quantized by quantflex. Its trained context length is 128K tokens. The repository has 4 quant files, from 1.2 GB (Q5_K_M) to 5.0 GB (F32).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q5_K_M1.2 GB 2.0 GB
Fits Get file →
Q6_K1.3 GB 2.1 GB
Fits Get file →
Q8_01.6 GB 2.3 GB
Fits Get file →
F325.0 GB 5.7 GB
Fits Get file →

What GPU do you need for MicroThinker 1B Preview?

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 (1.6 GB file, about 2.3 GB in use).
  • 6 GB VRAM: the best quant that fits is F32 (5.0 GB file, about 5.7 GB in use).

Which MicroThinker 1B Preview quant should you choose?

Q6_K (1.3 GB) is the middle option in this repository. Very close to the original quality for most uses, at a clearly larger size than 4-bit.

If memory is tight, the smallest file is Q5_K_M at 1.2 GB, with the quality trade-offs that come with fewer bits. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters1.24B
Layers16
Trained context131,072 tokens
KV cache (fp16)32 KB per token

Source

Quantized byquantflex
Licensellama3.2
Downloads (HF)88
Last updated2025-01-04

Frequently asked questions about MicroThinker 1B Preview

How much VRAM does MicroThinker 1B Preview need?

About 2.1 GB at Q6_K with an 8K context window. That is the 1.3 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 MicroThinker 1B Preview on an 8 GB GPU?

Yes, with F32: the 5.0 GB file needs about 5.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of MicroThinker 1B Preview GGUF?

It depends on the quant: Q5_K_M is 1.2 GB, Q6_K is 1.3 GB, Q8_0 is 1.6 GB, F32 is 5.0 GB.

What context length does MicroThinker 1B Preview support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.3 GB at 8K and 1.1 GB at 32K.

Where can I download MicroThinker 1B Preview GGUF?

The files are on Hugging Face in the quantflex/MicroThinker-1B-Preview-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 MicroThinker 1B Preview use?

Hugging Face lists the license as llama3.2. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Other GGUFs of MicroThinker-1B-Preview

Similar models

Browse all →

More from quantflex

All by quantflex →

More Microthinker models

All Microthinker →

Other tiny models

All tiny models →