JI

jijun LM

JijunGGUF by the-walking-fishUpdated 2026-10-15
Download on Hugging Face
Parameters63M
Context1K
Layers12
Architecturellama
Smallest quant0.0 GB
Quick answer

jijun LM needs about 0.7 GB of memory at Q6_K (a 0.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 6 quants, from 0.0 GB (Q4_0) to 0.3 GB (F32).

58M tool‑aware Llama model in GGUF format

jijun LM is a 0.0629 billion‑parameter Llama model quantized for GGUF. It supports tool calling and CJK prompt handling with a 1024‑token context window. The model is released under the MIT license.

Good at

  • Tool calling
  • CJK prompt handling
  • Lightweight inference

Limits

  • 1024‑token context
  • No vision support
  • MIT license

Best for

  • Tool‑driven chat
  • Lightweight dev testing
  • CJK prompt evaluation

Who it’s for. Developers and researchers who need a small, tool‑aware Llama model for local inference. The model is easy to integrate with llama.cpp, wllama, or llama‑cpp‑python.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_00.0 GB 0.6 GB
Fits Get file →
Q5_00.0 GB 0.6 GB
Fits Get file →
Q6_K0.1 GB 0.6 GB
Fits Get file →
Q8_00.1 GB 0.6 GB
Fits Get file →
F160.1 GB 0.6 GB
Fits Get file →
F320.3 GB 0.8 GB
Fits Get file →

For 8 GB VRAM, use Q4_0 or Q5_0 (0.04 GB file, ~0.7 GB memory). Q6_K and Q8_0 also fit within 8 GB. For 16 GB VRAM, F16 (0.13 GB, ~0.8 GB) or F32 (0.25 GB, ~0.9 GB) are suitable. Memory estimates are approximate.

What GPU do you need for jijun LM?

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 F32 (0.3 GB file, about 0.9 GB in use).

Which jijun LM quant should you choose?

Q6_K (0.1 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 Q4_0 at 0.0 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters63M
Layers12
Trained context1,024 tokens
KV cache (fp16)18 KB per token

Source

Quantized bythe-walking-fish
FamilyJijun
Licensemit
Downloads (HF)680
Last updated2026-10-15

Frequently asked questions about jijun LM

How much VRAM does jijun LM need?

About 0.7 GB at Q6_K 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 jijun LM on an 8 GB GPU?

Yes, with F32: 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 jijun LM GGUF?

It depends on the quant: Q4_0 is 0.0 GB, Q5_0 is 0.0 GB, Q6_K is 0.1 GB, Q8_0 is 0.1 GB, F16 is 0.1 GB, F32 is 0.3 GB.

What context length does jijun LM support?

The GGUF header lists a trained context length of 1,024 tokens (1K). The KV cache grows with the context you use: about 0.2 GB at 8K and 0.0 GB at 1K.

Where can I download jijun LM GGUF?

The files are on Hugging Face in the the-walking-fish/jijun-LM-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 jijun LM use?

Hugging Face lists the license as mit. 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 this model on 8 GB VRAM?

Yes. Q4_0, Q5_0, Q6_K, and Q8_0 quantizations all require about 0.7 GB of VRAM at 8 k context, fitting comfortably on 8 GB.

Does this model support vision?

No. The model has no vision capability and is text‑only.

How do I use tool calls with this model?

Send a raw ChatML prompt and parse the JSON tool call output. The model outputs JSON formatted tool calls directly.

Similar models

Browse all →

Other tiny models

All tiny models →