Ling-3.0-flash-Fin-GGUF

Llamacpp imatrix Quantizations of Ling-3.0-flash-Fin by inclusionAI#

Using llama.cpp release b10776 for quantization.

Original model: https://huggingface.co/inclusionAI/Ling-3.0-flash-Fin

Model details:

• Parameter count: 127B
• Input support: text
• Speculative decoding: yes (MTP) - details
• imatrix: yes - details

How to run

Prompt format#

<role>SYSTEM</role>{system_prompt}
detailed thinking on<|role_end|><role>HUMAN</role>{prompt}<|role_end|><role>ASSISTANT</role>
<think>

Don't know which to choose? Grab Q4_K_M (77.80GB) - usually a good mix of size and performance. Download instructions available here

Available files:#

Download a specific file:

hf download bartowski/Ling-3.0-flash-Fin-GGUF --include "Ling-3.0-flash-Fin-Q4_K_M/*" --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/Ling-3.0-flash-Fin-GGUF --include "Ling-3.0-flash-Fin-Q4_K_M/*" --local-dir ./

The files marked true in the Split column above are stored as multiple parts in a folder. To download all the parts to a local folder, run:

hf download bartowski/Ling-3.0-flash-Fin-GGUF --include "Ling-3.0-flash-Fin-Q8_0/*" --local-dir ./

You can either specify a new local-dir (Ling-3.0-flash-Fin-Q8_0) or download them all in place (./)

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/Ling-3.0-flash-Fin-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 b10776 - 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

MTP#

This model has MTP (Multi-Token Prediction) layers, and they are included in these quants

MTP layers act as a built-in draft model, letting llama.cpp run speculative decoding for faster generation. To use them, add the following flag to your llama.cpp command:

--spec-type draft-mtp

Note: the MTP layers are stored at Q4_0 in the imatrix quants (except for the Q8_0 quant), since imatrix calibration does not exercise them. Q4_0 is chosen for its speed which massively benefits MTP performance.

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: Ling-3.0-flash-Fin-calibration-v6.txt. The imatrix is available here: Ling-3.0-flash-Fin-imatrix.gguf.

Calibration render details

{
  "generator": "auto_quant_v2 calibration renderer",
  "recipe": "calibration-v6",
  "model": "Ling-3.0-flash-Fin",
  "encoder": "chat_template",
  "chunk_size": 512,
  "prose_chunks": 220,
  "tool_chunks": 345,
  "total_chunks": 565,
  "tool_chunk_fraction": 0.611,
  "n_conversations": 137,
  "extension_convs_used": 0,
  "conversation_token_lengths": [
    523,
    1594,
    1193,
    1476,
    1046,
    1300,
    3127,
    754,
    1163,
    1353,
    1019,
    2059,
    836,
    1200,
    2755,
    1189,
    1099,
    948,
    694,
    677,
    1326,
    990,
    1308,
    1167,
    1839,
    1463,
    1601,
    844,
    1376,
    1604,
    1472,
    1161,
    1211,
    1003,
    1019,
    1650,
    1619,
    1147,
    433,
    1912,
    1392,
    1048,
    1355,
    1973,
    2023,
    1230,
    1569,
    824,
    2903,
    1063,
    2811,
    723,
    955,
    915,
    924,
    655,
    2396,
    840,
    1100,
    1045,
    1166,
    1133,
    868,
    1151,
    1114,
    1530,
    873,
    1483,
    2099,
    803,
    333,
    1071,
    3285,
    2856,
    671,
    865,
    974,
    1022,
    1244,
    1052,
    1074,
    753,
    1152,
    983,
    1244,
    1468,
    1321,
    2041,
    795,
    608,
    2714,
    658,
    1345,
    1626,
    1936,
    1168,
    581,
    1336,
    1136,
    1653,
    1759,
    1625,
    782,
    961,
    976,
    2730,
    697,
    679,
    709,
    1354,
    1011,
    1544,
    731,
    361,
    327,
    2569,
    947,
    1085,
    1815,
    1970,
    2651,
    2644,
    759,
    931,
    797,
    884,
    1190,
    944,
    809,
    1266,
    793,
    668,
    1711,
    965,
    880,
    1240,
    1409
  ],
  "warnings": []
}

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

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 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

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