KI

Kisoku 1.6b

KisokuGGUF by mradermacherUpdated 2026-10-22
Download on Hugging Face
Parameters1.6B
Context128K
Layers22
Architectureqwen3
Smallest quant0.0 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 25 quants, from 0.0 GB to 1.3 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 1.5 GB.

Kisoku 1.6B – a 1.6‑billion‑parameter base model with long context

Kisoku 1.6B is a 1.6‑billion‑parameter base language model trained on 0.5 trillion tokens. It supports a 131072‑token context window and is available in multiple GGUF quantizations. The model is released under the Apache‑2.0 license.

Good at

  • Long‑context text generation
  • Coding tasks
  • Token‑efficient pretraining

Limits

  • No instruction following or chat capability
  • No vision support
  • Requires a 131072‑token context for full performance

Best for

  • Code generation in research projects
  • Long‑form document summarization
  • Fine‑tuning for specialized domains

Who it’s for. Researchers and developers who need a large base model with extended context and coding abilities. The model is suitable for users who can fine‑tune or integrate it into custom pipelines.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 0.9 GB
Fits Get file →
IQ1_S0.5 GB 1.3 GB
Fits Get file →
IQ1_M0.5 GB 1.4 GB
Fits Get file →
IQ2_XXS0.5 GB 1.4 GB
Fits Get file →
IQ2_XS0.6 GB 1.5 GB
Fits Get file →
IQ2_S0.6 GB 1.5 GB
Fits Get file →
IQ2_M0.6 GB 1.5 GB
Fits Get file →
Q2_K_S0.7 GB 1.5 GB
Fits Get file →
IQ3_XXS0.7 GB 1.6 GB
Fits Get file →
Q2_K0.7 GB 1.6 GB
Fits Get file →
IQ3_XS0.8 GB 1.6 GB
Fits Get file →
Q3_K_S0.8 GB 1.7 GB
Fits Get file →
IQ3_S0.8 GB 1.7 GB
Fits Get file →
IQ3_M0.8 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_01.0 GB 1.8 GB
Fits Get file →
IQ4_NL1.0 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 →
Q4_11.1 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 →

For 8 GB VRAM, use Q4_0 (file size 0.98 GB, estimated 1.8 GB memory at 8 k context). For 12 GB VRAM, Q5_K_M (1.17 GB, 2 GB memory) or Q6_K (1.32 GB, 2.2 GB memory). Higher‑quality IQ quants are available for larger budgets.

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 Q6_K (1.3 GB file, about 2.2 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.

If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.

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)2,464
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 Q6_K: the 1.3 GB file needs about 2.2 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: file is 0.0 GB, IQ1_S is 0.5 GB, IQ1_M is 0.5 GB, IQ2_XXS is 0.5 GB, IQ2_XS is 0.6 GB, IQ2_S is 0.6 GB and 19 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-i1-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_0 quant uses 0.98 GB file size and requires about 1.8 GB memory at 8 k context, which fits within 8 GB VRAM.

Is Kisoku 1.6B compatible with llama.cpp?

Yes, all GGUF files are designed for llama.cpp and can be loaded directly with the provided quantizations.

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 →