NadevA23_Kronumos-Kairos-v2-GGUF by Bartowski: Open Model

Model Card

By Bartowski, published under apache-2.0, revision 4c22382169ac.

Using llama.cpp release b11259 for quantization. Don't know which to choose? Grab Q4KM (4.78GB) - usually a good mix of size and performance. Download instructions available here First, make sure you have the Hugging Face CLI installed: These quants run with llama.cpp - installable in one line via llama.app: llama-server includes a built-in chat web UI, served at http://localhost:8080 by default. These quants were made with llama.cpp release b11259 - if this model's architecture is newly supported, you'll need that release or newer to run them. They also work in: quants made using imatrix option, with a calibration corpus rendered through this model's own chat template. The corpus pairs…

Read Bartowski's full model card

Llamacpp imatrix Quantizations of Kronumos-Kairos-v2 by NadevA23

Using llama.cpp release b11259 for quantization.

Original model: https://huggingface.co/NadevA23/Kronumos-Kairos-v2

Model details: - Parameter count: 8B (source checkpoint) - Input support: text - Speculative decoding: no - imatrix: yes - details

How to run

Prompt format

<|im_start|>system
{system_prompt}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant

Prompt format with tool definitions

<|im_start|>system
{system_prompt}

# Tools

You may call one or more functions to assist with the user query.

You are provided with function signatures within <tools></tools> XML tags:
<tools>
{"type": "function", "function": {"name": "get_stock_price", "description": "Get the current stock price", "parameters": {"type": "object", "properties": {"symbol": {"type": "string", "description": "The stock symbol, e.g. AAPL, GOOG"}}, "required": ["symbol"]}}}
</tools>

For each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:
<tool_call>
{"name": <function-name>, "arguments": <args-json-object>}
</tool_call><|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant

Don't know which to choose? Grab Q4_K_M (4.78GB) - usually a good mix of size and performance. Download instructions available here

Available files:

Filename	Quant type	File Size	Split	Description
NadevA23_Kronumos-Kairos-v2-bf16.gguf	bf16	15.24GB	false	Full BF16 weights.
NadevA23_Kronumos-Kairos-v2-Q8_0.gguf	Q8_0	8.10GB	false	Extremely high quality, generally unneeded but max available quant.
NadevA23_Kronumos-Kairos-v2-Q6_K_L.gguf	Q6_K_L	6.67GB	false	Uses Q8_0 for embed and output weights. Very high quality, near perfect, recommended.
NadevA23_Kronumos-Kairos-v2-Q6_K.gguf	Q6_K	6.40GB	false	Very high quality, near perfect, recommended.
NadevA23_Kronumos-Kairos-v2-Q5_K_M.gguf	Q5_K_M	5.52GB	false	High quality, recommended.
NadevA23_Kronumos-Kairos-v2-Q5_K_S.gguf	Q5_K_S	5.34GB	false	High quality, recommended.
NadevA23_Kronumos-Kairos-v2-Q4_K_L.gguf	Q4_K_L	5.19GB	false	Uses Q8_0 for embed and output weights. Good quality, recommended.
NadevA23_Kronumos-Kairos-v2-Q4_1.gguf	Q4_1	4.91GB	false	Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon.
NadevA23_Kronumos-Kairos-v2-Q4_K_M.gguf	Q4_K_M	4.78GB	false	Good quality, default size for most use cases, recommended.
NadevA23_Kronumos-Kairos-v2-Q4_K_S.gguf	Q4_K_S	4.51GB	false	Slightly lower quality with more space savings, recommended.
NadevA23_Kronumos-Kairos-v2-IQ4_NL.gguf	IQ4_NL	4.49GB	false	Similar to IQ4_XS, but slightly larger.
NadevA23_Kronumos-Kairos-v2-Q4_0.gguf	Q4_0	4.49GB	false	Legacy format, kept for compatibility with older tools.
NadevA23_Kronumos-Kairos-v2-IQ4_XS.gguf	IQ4_XS	4.28GB	false	Decent quality, smaller than Q4_K_S with similar performance, recommended.
NadevA23_Kronumos-Kairos-v2-Q3_K_L.gguf	Q3_K_L	4.11GB	false	Lower quality but usable, good for low RAM availability.
NadevA23_Kronumos-Kairos-v2-Q3_K_M.gguf	Q3_K_M	3.88GB	false	Low quality.
NadevA23_Kronumos-Kairos-v2-IQ3_M.gguf	IQ3_M	3.65GB	false	Medium-low quality, new method with decent performance comparable to Q3_K_M.
NadevA23_Kronumos-Kairos-v2-Q3_K_S.gguf	Q3_K_S	3.56GB	false	Low quality, not recommended.
NadevA23_Kronumos-Kairos-v2-IQ3_XS.gguf	IQ3_XS	3.44GB	false	Lower quality, new method with decent performance, slightly better than Q3_K_S.
NadevA23_Kronumos-Kairos-v2-IQ3_XXS.gguf	IQ3_XXS	3.22GB	false	Lower quality, new method with decent performance, comparable to Q3 quants.
NadevA23_Kronumos-Kairos-v2-Q2_K.gguf	Q2_K	3.10GB	false	Very low quality but surprisingly usable.
NadevA23_Kronumos-Kairos-v2-IQ2_M.gguf	IQ2_M	2.98GB	false	Relatively low quality, uses SOTA techniques to be surprisingly usable.

Download a specific file:

hf download bartowski/NadevA23_Kronumos-Kairos-v2-GGUF --include "NadevA23_Kronumos-Kairos-v2-Q4_K_M.gguf" --local-dir ./

Downloading using the Hugging Face CLI

Click to view download instructions

First, make sure you have the Hugging Face CLI installed:

pip install -U "huggingface_hub[cli]"

Download a specific file:

hf download bartowski/NadevA23_Kronumos-Kairos-v2-GGUF --include "NadevA23_Kronumos-Kairos-v2-Q4_K_M.gguf" --local-dir ./

How to run

These quants run with llama.cpp - installable in one line via llama.app:

curl -LsSf https://llama.app/install.sh | sh
llama-server -hf bartowski/NadevA23_Kronumos-Kairos-v2-GGUF:Q4_K_M

llama-server includes a built-in chat web UI, served at http://localhost:8080 by default.

These quants were made with llama.cpp release b11259 - if this model's architecture is newly supported, you'll need that release or newer to run them.

They also work in: LM Studio · koboldcpp · ramalama · Jan AI · Text Generation Web UI · LoLLMs · Atomic Chat

imatrix

All quants made using imatrix option, with a calibration corpus rendered through this model's own chat template. The corpus pairs plain prose with tool-calling and reasoning conversations (corpus source data), encoded exactly as this model sees them at inference and processed with --parse-special, so chat-format special tokens contribute to the importance matrix. The corpus rendered for this model is included in this repo: NadevA23_Kronumos-Kairos-v2-calibration-v6.txt. The imatrix is available here: NadevA23_Kronumos-Kairos-v2-imatrix.gguf.

Calibration render details

{
  "recipe": "calibration-v6",
  "encoder": "chat_template",
  "library_versions": {
    "transformers": "5.9.0",
    "tokenizers": "0.22.2",
    "tiktoken": "0.14.0",
    "blobfile": "3.3.0",
    "huggingface_hub": "1.31.0"
  },
  "chunk_size": 512,
  "prose_chunks": 218,
  "tool_chunks": 271,
  "total_chunks": 489,
  "n_conversations": 161,
  "conversation_token_lengths": [
    335,
    863,
    599,
    1206,
    832,
    656,
    740,
    2115,
    1113,
    436,
    633,
    993,
    826,
    1216,
    497,
    695,
    2107,
    787,
    722,
    649,
    711,
    383,
    332,
    653,
    693,
    631,
    1025,
    601,
    563,
    812,
    1556,
    823,
    663,
    503,
    650,
    1255,
    1015,
    481,
    525,
    734,
    446,
    1278,
    1096,
    719,
    260,
    794,
    661,
    662,
    1000,
    1571,
    895,
    1739,
    706,
    960,
    562,
    2352,
    2110,
    466,
    2421,
    505,
    682,
    482,
    353,
    393,
    2004,
    544,
    633,
    677,
    662,
    745,
    605,
    742,
    667,
    585,
    732,
    715,
    624,
    1141,
    422,
    802,
    1609,
    837,
    281,
    151,
    366,
    747,
    2791,
    1976,
    373,
    1293,
    498,
    647,
    526,
    744,
    333,
    718,
    414,
    817,
    642,
    871,
    1052,
    815,
    662,
    862,
    853,
    555,
    643,
    389,
    504,
    1174,
    2175,
    2113,
    349,
    334,
    1264,
    873,
    860,
    2102,
    1378,
    630,
    311,
    597,
    1137,
    1107,
    1432,
    1136,
    543,
    534,
    667,
    2102,
    422,
    444,
    451,
    951,
    264,
    1097,
    474,
    168,
    145,
    2008,
    478,
    666,
    1712,
    1412,
    2051,
    2088,
    493,
    652,
    513,
    554,
    651,
    584,
    374,
    802,
    564,
    420,
    1121,
    633,
    532,
    765,
    1036
  ]
}

Embed/output weights

Some of these quants (Q3_K_XL, Q4_K_L etc) are the standard quantization method with the embeddings and output weights quantized to Q8_0 instead of what they would normally default to.

ARM/AVX information

llama.cpp automatically "repacks" weights into an interleaved layout at load time for faster inference on ARM and AVX machines - details in this PR. This once required downloading special Q4_0_4_4/4_8/8_8 files; those are long gone. Online repacking now covers Q4_0, IQ4_NL, and most K-quants, so no special quant choice is needed for CPU inference.

Which file should I choose?

Click here for details

An older (early 2024) but still useful write-up with charts comparing quant performances is provided by Artefact2 [here](https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9) The first thing to figure out is how big a model you can run. To do this, you'll need to figure out how much RAM and/or VRAM you have. If you want your model running as FAST as possible, you'll want to fit the whole thing on your GPU's VRAM. Aim for a quant with a file size 1-2GB smaller than your GPU's total VRAM. If you want the absolute maximum quality, add both your system RAM and your GPU's VRAM together, then similarly grab a quant with a file size 1-2GB Smaller than that total. Hugging Face can also do this math for you: add your hardware in your [Local Apps settings](https://huggingface.co/settings/local-apps) and the model page will show which files fit. Next, you'll need to decide if you want to use an 'I-quant' or a 'K-quant'. If you don't want to think too much, grab one of the K-quants. These are in format 'QX_K_X', like Q5_K_M. If you want to get more into the weeds, you can check out this extremely useful feature chart: [llama.cpp feature matrix](https://github.com/ggml-org/llama.cpp/wiki/Feature-matrix) But basically, if you're aiming for below Q4, and you're running cuBLAS (Nvidia) or rocBLAS (AMD), you should look towards the I-quants. These are in format IQX_X, like IQ3_M. These are newer and offer better performance for their size. These I-quants can also be used on CPU, but will be slower than their K-quant equivalent, so speed vs performance is a tradeoff you'll have to decide.

Credits

Thank you kalomaze and Dampf for assistance in creating the imatrix calibration dataset.

Thank you ZeroWw for the inspiration to experiment with embed/output.

Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski

Identity and Version

Repository: bartowski/NadevA23_Kronumos-Kairos-v2-GGUF
Publisher: Bartowski
Task: Text generation
Modality: Text
Library: transformers
Parameters: Not stated by the source
Languages: en
Revision: 4c22382169accfa07c0d082da2d3949d671ccdce
First published: 2026-09-30
Last updated: 2026-09-30

Files and Weights

25 files, 107.9 GB in total. The weights are 22 files totalling 107.9 GB in gguf.

Weights22 files · 107.9 GB

Documentation1 file · 14.3 KB

Other1 file · 1.0 MB

Repository1 file · 3.2 KB

Every file

File	Type	Size	SHA-256
NadevA23_Kronumos-Kairos-v2-IQ2_M.gguf	Weights	3.0 GB	03dbafc40b01
NadevA23_Kronumos-Kairos-v2-IQ3_M.gguf	Weights	3.7 GB	1c226de0fae3
NadevA23_Kronumos-Kairos-v2-IQ3_XS.gguf	Weights	3.4 GB	4bf6b15593aa
NadevA23_Kronumos-Kairos-v2-IQ3_XXS.gguf	Weights	3.2 GB	3fa0446c05e3
NadevA23_Kronumos-Kairos-v2-IQ4_NL.gguf	Weights	4.5 GB	63339ff5e752
NadevA23_Kronumos-Kairos-v2-IQ4_XS.gguf	Weights	4.3 GB	1bb47d10b134
NadevA23_Kronumos-Kairos-v2-Q2_K.gguf	Weights	3.1 GB	3dd0c7fbd60c
NadevA23_Kronumos-Kairos-v2-Q3_K_L.gguf	Weights	4.1 GB	fbd9826eaab9
NadevA23_Kronumos-Kairos-v2-Q3_K_M.gguf	Weights	3.9 GB	5ff34f0cf6d8
NadevA23_Kronumos-Kairos-v2-Q3_K_S.gguf	Weights	3.6 GB	dcc5ecf30211
NadevA23_Kronumos-Kairos-v2-Q4_0.gguf	Weights	4.5 GB	9e2f94e0e35b
NadevA23_Kronumos-Kairos-v2-Q4_1.gguf	Weights	4.9 GB	6fec6d9851a4
NadevA23_Kronumos-Kairos-v2-Q4_K_L.gguf	Weights	5.2 GB	19fd6a90bc6a
NadevA23_Kronumos-Kairos-v2-Q4_K_M.gguf	Weights	4.8 GB	8b3207956ce0
NadevA23_Kronumos-Kairos-v2-Q4_K_S.gguf	Weights	4.5 GB	ee8a6e6ffb34
NadevA23_Kronumos-Kairos-v2-Q5_K_M.gguf	Weights	5.5 GB	337d465b7ad3
NadevA23_Kronumos-Kairos-v2-Q5_K_S.gguf	Weights	5.3 GB	4aa0e10c7768
NadevA23_Kronumos-Kairos-v2-Q6_K.gguf	Weights	6.4 GB	6a56cfe0498f
NadevA23_Kronumos-Kairos-v2-Q6_K_L.gguf	Weights	6.7 GB	8cb094a7511c
NadevA23_Kronumos-Kairos-v2-Q8_0.gguf	Weights	8.1 GB	b65dee26acbe
NadevA23_Kronumos-Kairos-v2-bf16.gguf	Weights	15.2 GB	aa43a228af2e
NadevA23_Kronumos-Kairos-v2-imatrix.gguf	Weights	4.6 MB	5598ea7b9f1f
README.md	Documentation	14.3 KB	—
NadevA23_Kronumos-Kairos-v2-calibration-v6.txt	Other	1.0 MB	—
.gitattributes	Repository	3.2 KB	—

License and Download

License: apache-2.0
Access: Open weights, no gate
Download size: 107.9 GB

Download from Bartowski

Released by Bartowski through its official repository on Hugging Face. Read the license.

Built From

Derived from NadevA23/Kronumos-Kairos-v2
Quantized from NadevA23/Kronumos-Kairos-v2
Trained on (disclosed) princeton-nlp/SWE-bench_Verified

Memory Requirements

Precision	Weights in memory
As published	107.9 GB

Weights only, from the published parameter count; the key-value cache and runtime add to this.

Questions About NadevA23_Kronumos-Kairos-v2-GGUF

Can I use NadevA23_Kronumos-Kairos-v2-GGUF commercially?

Yes. NadevA23_Kronumos-Kairos-v2-GGUF is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors.

Similar Models

Model · Text generation

opt-125m

AI at Meta

OPT was first introduced in Open Pre-trained Transformer Language Models and first released in metaseq's repository on May 3rd 2022 by Meta AI. Disclaimer: The team releasing OPT wrote an official model card, which is available in Appendix D of the paper. Content from this model card has been written by the Hugging Face team. To quote the first two paragraphs of the official paper OPT was predominantly pretrained with English text, but a small amount of non-English data is still present within the training corpus via CommonCrawl. The model was pretrained using a causal language modeling (CLM) objective. OPT belongs to the same family of decoder-only models like GPT-3. As such, it was…

Open weights other 2,048 tokens transformers

View model

Model · Text generation

Ornith-1.5-9B-GGUF

Ornith

Chirp Chirp! We are introducing Ornith-1.5, a major step toward building foundation models through end-to-end self-improvement. Ornith-1.5 extends Ornith-1.0 (which was developed on top of Qwen3.5 and Gemma4 with additional continued pretraining, mid-training, and post-training) by expanding the self-improvement loop from scaffold and rollout optimization to jointly optimizing task generation, scaffold construction, and solution rollouts. Rather than relying on a fixed set of human-curated tasks and manually designed harnesses, Ornith-1.5 continuously generates new training tasks, discovers effective strategies for solving them, and improves the policy through reinforcement learning. For…

Open weights mit transformers

View model

Model · Text generation

Ornith-1.5-35B-A3B-GGUF

Ornith

Chirp Chirp! We are introducing Ornith-1.5, a major step toward building foundation models through end-to-end self-improvement. Ornith-1.5 extends Ornith-1.0 (which was developed on top of Qwen3.5 and Gemma4 with additional continued pretraining, mid-training, and post-training) by expanding the self-improvement loop from scaffold and rollout optimization to jointly optimizing task generation, scaffold construction, and solution rollouts. Rather than relying on a fixed set of human-curated tasks and manually designed harnesses, Ornith-1.5 continuously generates new training tasks, discovers effective strategies for solving them, and improves the policy through reinforcement learning. For…

Open weights mit transformers

View model

Model · Text generation

Ternary-Bonsai-2-27B-gguf

Prism ML

Full 27B-class reasoning in ternary transformer weights, for llama.cpp (CUDA, Metal, CPU) - \~5.9 GB language model (down from \~54 GB FP16) — full 27B-class reasoning on a standard laptop or a single GPU - 98.2% of FP16 intelligence retained: 84.78 average across 14 thinking-mode benchmarks — far above the conventional IQ2XXS build (72.59) at about 82% of its footprint, and within 0.4 points of UD-Q4KXL at three times the footprint - Retains thinking, reasoning, and agentic behavior deep in the sub-4-bit regime, where conventional low-bit representations collapse: math within half a point of full precision (96.57), coding level with the baseline (89.42), agentic tool calling at 74.92…

Open weights apache-2.0 llama.cpp

View model

Model · Text generation

Qwen3.8-27B-Uncensored-GGUF

Jonathan Coletti

Uncensored Qwen3.8-27B, published as GGUF quantizations with the multi token prediction (MTP) head retained and verified. Refusal behaviour has been substantially reduced, not eliminated. See Measured behaviour for the numbers. Capabilities, training data, and architecture are otherwise unchanged. - Refusal directions removed with Heretic, which co minimizes refusal count against KL divergence from the base model. No handwritten refusal removal code, no finetuning, no additional training data. - Abliteration runs at bf16 (no 4 bit quantization). the resulting LoRA is merged into the bf16 base, so the published weights are not a quantized round trip. - mtp. tensors are copied verbatim from…

Open weights apache-2.0 llama.cpp

View model

Model · Text generation

Ornith-1.0-9B-GGUF

Ornith

Aloha! Today, we are releasing Ornith-1.0, a self-improving family of open-source models for agentic coding. This model card documents Ornith-1.0-9B, the most lightweight member of the Ornith family, designed for efficient single-GPU deployment. Ornith-1.0-9B is a dense ~9B model (≈19 GB in bf16), so it serves comfortably on a single 80GB GPU. The recipes below stand up an OpenAI-compatible server; add --tensor-parallel-size / --tp if you want to shard across more GPUs. For a quick local test (or to script offline generation), load the model directly with Transformers. Make sure you have a recent release installed — see the Transformers installation guide; Ornith-1.0-9B requires…

Open weights mit transformers

View model