KI

Kisoku 1.6b

KisokuGGUF by mradermacherUpdated 2026-10-22
Download on Hugging Face
Parameters1.6B
Context128K
Layers22
Architectureqwen3
Smallest quant0.7 GB
Quick answer

Kisoku 1.6b needs about 1.9 GB of memory at Q4_K_M (a 1.0 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 12 quants, from 0.7 GB (Q2_K) to 3.2 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.5 GB.

Kisoku 1.6b – a 1.6B‑parameter Qwen3 base model

Kisoku 1.6b is a 1.6‑billion‑parameter Qwen3 base model trained on 0.5 trillion tokens. It supports a 131072‑token context window and is available in multiple GGUF quantizations. The model is licensed under apache‑2.0.

Good at

  • Long‑context text generation
  • Coding assistance
  • High token efficiency

Limits

  • No instruction following
  • No vision support
  • Requires 8‑k context for memory estimates

Best for

  • Developers needing a lightweight base model
  • Researchers testing long‑context performance
  • Users with limited GPU memory

Who it’s for. The model is suitable for developers and researchers who need a base Qwen3 model with extended context. It is ideal for those who can fine‑tune or chain with instruction models.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K0.7 GB 1.6 GB
Fits Get file →
Q3_K_S0.8 GB 1.7 GB
Fits Get file →
Q3_K_M0.9 GB 1.7 GB
Fits Get file →
Q3_K_L0.9 GB 1.8 GB
Fits Get file →
IQ4_XS0.9 GB 1.8 GB
Fits Get file →
Q4_K_S1.0 GB 1.9 GB
Fits Get file →
Q4_K_M1.0 GB 1.9 GB
Fits Get file →
Q5_K_S1.1 GB 2.0 GB
Fits Get file →
Q5_K_M1.2 GB 2.0 GB
Fits Get file →
Q6_K1.3 GB 2.2 GB
Fits Get file →
Q8_01.7 GB 2.6 GB
Fits Get file →
F163.2 GB 4.1 GB
Fits Get file →

For 8‑GB VRAM use Q4_K_M (1.02 GB file, 1.9 GB memory). For 12‑GB VRAM use Q5_K_M (1.17 GB file, 2 GB memory). For 16‑GB VRAM use Q6_K (1.32 GB file, 2.2 GB memory).

What GPU do you need for Kisoku 1.6b?

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 (1.7 GB file, about 2.6 GB in use).
  • 6 GB VRAM: the best quant that fits is F16 (3.2 GB file, about 4.1 GB in use).

Which Kisoku 1.6b quant should you choose?

Q4_K_M is the usual starting point for Kisoku 1.6b: it balances file size and quality well. Here it is a 1.0 GB file.

The Q8_0 file is 1.7 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 0.7 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

Architectureqwen3
Parameters1.6B
Layers22
Trained context131,072 tokens
KV cache (fp16)44 KB per token

Source

Quantized bymradermacher
FamilyKisoku
Licenseapache-2.0
Downloads (HF)678
Last updated2026-10-22

Frequently asked questions about Kisoku 1.6b

How much VRAM does Kisoku 1.6b need?

About 1.9 GB at Q4_K_M with an 8K context window. That is the 1.0 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 Kisoku 1.6b on an 8 GB GPU?

Yes, with F16: the 3.2 GB file needs about 4.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Kisoku 1.6b GGUF?

It depends on the quant: Q2_K is 0.7 GB, Q3_K_S is 0.8 GB, Q3_K_M is 0.9 GB, Q3_K_L is 0.9 GB, IQ4_XS is 0.9 GB, Q4_K_S is 1.0 GB and 6 more.

What context length does Kisoku 1.6b support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.4 GB at 8K and 1.5 GB at 32K.

Where can I download Kisoku 1.6b GGUF?

The files are on Hugging Face in the mradermacher/kisoku-1.6b-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 Kisoku 1.6b 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 Kisoku 1.6b on 8 GB VRAM?

Yes, the Q4_K_M quant uses 1.9 GB memory at 8‑k context, fitting within 8 GB VRAM with headroom.

Does Kisoku 1.6b support vision tasks?

No, it is a text‑only base model with no vision capability.

What license applies to Kisoku 1.6b?

The model is released under the apache‑2.0 license.

Other GGUFs of kisoku-1.6b

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Kisoku models

All Kisoku →

Other tiny models

All tiny models →