KO

KONI 7B R 20250831

KoniGGUF by mradermacherUpdated 2025-12-04
Download on Hugging Face
Parameters7.26B
Context32K
Layers32
Architecturellama
Smallest quant0.0 GB
Quick answer

KONI 7B R 20250831 needs about 9.5 GB of memory at Q4_K_M (a 4.7 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 25 quants, from 0.0 GB to 6.3 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 17.2 GB.

KONI 7B R 20250831 – Korean‑centric reasoning LLM

KONI 7B R 20250831 is a 7.26B‑parameter llama‑based model tuned for Korean reasoning with full English support. It offers a 32768‑token context window and is licensed under Apache‑2.0.

Good at

  • Korean reasoning
  • English support
  • Tool‑use capability

Limits

  • No vision support
  • Requires 8k context for memory estimates
  • No mixture of experts

Best for

  • Scientific queries in Korean
  • Technical problem solving
  • Logical reasoning tasks

Who it’s for. Developers and researchers needing a Korean‑focused LLM with robust reasoning and tool‑use abilities. The model is suitable for applications that require detailed Korean language support and complex reasoning in both Korean and English.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 4.8 GB
Fits Get file →
IQ1_S2.3 GB 7.1 GB
Fits Get file →
IQ1_M2.4 GB 7.2 GB
Tight Get file →
IQ2_XXS2.6 GB 7.4 GB
Tight Get file →
IQ2_XS2.7 GB 7.5 GB
Tight Get file →
IQ2_S2.9 GB 7.7 GB
Tight Get file →
Q2_K_S3.0 GB 7.7 GB
Tight Get file →
IQ2_M3.0 GB 7.8 GB
Tight Get file →
Q2_K3.0 GB 7.8 GB
Tight Get file →
IQ3_XXS3.1 GB 7.9 GB
Tight Get file →
IQ3_XS3.3 GB 8.1 GB
Too big Get file →
IQ3_S3.5 GB 8.3 GB
Too big Get file →
Q3_K_S3.5 GB 8.3 GB
Too big Get file →
IQ3_M3.6 GB 8.4 GB
Too big Get file →
Q3_K_M3.8 GB 8.6 GB
Too big Get file →
Q3_K_L4.0 GB 8.8 GB
Too big Get file →
IQ4_XS4.0 GB 8.8 GB
Too big Get file →
IQ4_NL4.2 GB 9.0 GB
Too big Get file →
Q4_04.2 GB 9.0 GB
Too big Get file →
Q4_K_S4.4 GB 9.2 GB
Too big Get file →
Q4_14.6 GB 9.4 GB
Too big Get file →
Q4_K_M4.7 GB 9.5 GB
Too big Get file →
Q5_K_S5.1 GB 9.9 GB
Too big Get file →
Q5_K_M5.4 GB 10.2 GB
Too big Get file →
Q6_K6.3 GB 11.1 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (4.72 GB file, 9.5 GB memory). For 12 GB VRAM, Q5_K_M (5.4 GB file, 10.2 GB memory) is a good balance. Larger VRAM allows Q6_K (6.31 GB file, 11.1 GB memory).

What GPU do you need for KONI 7B R 20250831?

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: no quant fits at an 8K context.
  • 6 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 4.8 GB in use).
  • 8 GB VRAM: the best quant that fits is IQ3_XXS (3.1 GB file, about 7.9 GB in use).
  • 12 GB VRAM: the best quant that fits is Q6_K (6.3 GB file, about 11.1 GB in use).

Which KONI 7B R 20250831 quant should you choose?

Q4_K_M is the usual starting point for KONI 7B R 20250831: it balances file size and quality well. Here it is a 4.7 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

Architecturellama
Parameters7.26B
Layers32
Trained context32,768 tokens
KV cache (fp16)512 KB per token

Source

Quantized bymradermacher
FamilyKoni
Licenseapache-2.0
Downloads (HF)774
Last updated2025-12-04

Frequently asked questions about KONI 7B R 20250831

How much VRAM does KONI 7B R 20250831 need?

About 9.5 GB at Q4_K_M with an 8K context window. That is the 4.7 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 KONI 7B R 20250831 on an 8 GB GPU?

Yes, with IQ3_XXS: the 3.1 GB file needs about 7.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of KONI 7B R 20250831 GGUF?

It depends on the quant: file is 0.0 GB, IQ1_S is 2.3 GB, IQ1_M is 2.4 GB, IQ2_XXS is 2.6 GB, IQ2_XS is 2.7 GB, IQ2_S is 2.9 GB and 19 more.

What context length does KONI 7B R 20250831 support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 4.3 GB at 8K and 17.2 GB at 32K.

Where can I download KONI 7B R 20250831 GGUF?

The files are on Hugging Face in the mradermacher/KONI-7B-R-20250831-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 KONI 7B R 20250831 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 KONI 7B R on 8 GB VRAM?

Yes, the Q4_K_M quant uses 4.72 GB file size and requires about 9.5 GB memory at 8k context, which fits within 8 GB VRAM with some overhead.

Does KONI 7B R support vision tasks?

No, the model does not include vision capabilities.

What license applies to KONI 7B R?

The model is released under the Apache‑2.0 license.

Other GGUFs of KONI-7B-R-20250831

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Koni models

All Koni →

Other small models

All small models →