bartowski/Ling-3.0-flash-GGUF overview
Llamacpp imatrix Quantizations of Ling 3.0 flash by inclusionAI Using <a href="https://github.com/ggml org/llama.cpp/" llama.cpp</a release <a href="https://gi…
Runs locally from ~465.2 MB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| Ling-3.0-flash-IQ1_M.gguf | GGUF | IQ1_M | 28.46 GB | Download |
| Ling-3.0-flash-IQ1_S.gguf | GGUF | IQ1_S | 25.68 GB | Download |
| Ling-3.0-flash-IQ2_M.gguf | GGUF | IQ2_M | 40.64 GB | Download |
| Ling-3.0-flash-IQ2_S.gguf | GGUF | IQ2_S | 36.97 GB | Download |
| Ling-3.0-flash-IQ2_XS.gguf | GGUF | IQ2_XS | 36.36 GB | Download |
| Ling-3.0-flash-IQ2_XXS.gguf | GGUF | IQ2_XXS | 32.82 GB | Download |
| Ling-3.0-flash-IQ3_M/Ling-3.0-flash-IQ3_M-00001-of-00002.gguf | GGUF | IQ3_M | 37.01 GB | Download |
| Ling-3.0-flash-IQ3_M/Ling-3.0-flash-IQ3_M-00002-of-00002.gguf | GGUF | IQ3_M | 20.28 GB | Download |
| Ling-3.0-flash-IQ3_XS/Ling-3.0-flash-IQ3_XS-00001-of-00002.gguf | GGUF | IQ3_XS | 37.24 GB | Download |
| Ling-3.0-flash-IQ3_XS/Ling-3.0-flash-IQ3_XS-00002-of-00002.gguf | GGUF | IQ3_XS | 17.65 GB | Download |
| Ling-3.0-flash-IQ3_XXS/Ling-3.0-flash-IQ3_XXS-00001-of-00002.gguf | GGUF | IQ3_XXS | 37.14 GB | Download |
| Ling-3.0-flash-IQ3_XXS/Ling-3.0-flash-IQ3_XXS-00002-of-00002.gguf | GGUF | IQ3_XXS | 13.26 GB | Download |
| Ling-3.0-flash-IQ4_NL/Ling-3.0-flash-IQ4_NL-00001-of-00002.gguf | GGUF | IQ4_NL | 37.14 GB | Download |
| Ling-3.0-flash-IQ4_NL/Ling-3.0-flash-IQ4_NL-00002-of-00002.gguf | GGUF | IQ4_NL | 30.45 GB | Download |
| Ling-3.0-flash-IQ4_XS/Ling-3.0-flash-IQ4_XS-00001-of-00002.gguf | GGUF | IQ4_XS | 37.19 GB | Download |
| Ling-3.0-flash-IQ4_XS/Ling-3.0-flash-IQ4_XS-00002-of-00002.gguf | GGUF | IQ4_XS | 26.83 GB | Download |
| Ling-3.0-flash-Q2_K.gguf | GGUF | Q2_K | 42.75 GB | Download |
| Ling-3.0-flash-Q2_K_L.gguf | GGUF | Q2_K_L | 43.11 GB | Download |
| Ling-3.0-flash-Q3_K_L/Ling-3.0-flash-Q3_K_L-00001-of-00002.gguf | GGUF | Q3_K_L | 36.96 GB | Download |
| Ling-3.0-flash-Q3_K_L/Ling-3.0-flash-Q3_K_L-00002-of-00002.gguf | GGUF | Q3_K_L | 20.25 GB | Download |
| Ling-3.0-flash-Q3_K_M/Ling-3.0-flash-Q3_K_M-00001-of-00002.gguf | GGUF | Q3_K_M | 37.25 GB | Download |
| Ling-3.0-flash-Q3_K_M/Ling-3.0-flash-Q3_K_M-00002-of-00002.gguf | GGUF | Q3_K_M | 17.67 GB | Download |
| Ling-3.0-flash-Q3_K_S/Ling-3.0-flash-Q3_K_S-00001-of-00002.gguf | GGUF | Q3_K_S | 37.02 GB | Download |
| Ling-3.0-flash-Q3_K_S/Ling-3.0-flash-Q3_K_S-00002-of-00002.gguf | GGUF | Q3_K_S | 15.40 GB | Download |
| Ling-3.0-flash-Q3_K_XL/Ling-3.0-flash-Q3_K_XL-00001-of-00002.gguf | GGUF | Q3_K_XL | 36.87 GB | Download |
| Ling-3.0-flash-Q3_K_XL/Ling-3.0-flash-Q3_K_XL-00002-of-00002.gguf | GGUF | Q3_K_XL | 20.66 GB | Download |
| Ling-3.0-flash-Q4_0/Ling-3.0-flash-Q4_0-00001-of-00002.gguf | GGUF | Q4_0 | 36.88 GB | Download |
| Ling-3.0-flash-Q4_0/Ling-3.0-flash-Q4_0-00002-of-00002.gguf | GGUF | Q4_0 | 30.96 GB | Download |
| Ling-3.0-flash-Q4_1/Ling-3.0-flash-Q4_1-00001-of-00003.gguf | GGUF | Q4_1 | 36.94 GB | Download |
| Ling-3.0-flash-Q4_1/Ling-3.0-flash-Q4_1-00002-of-00003.gguf | GGUF | Q4_1 | 37.23 GB | Download |
| Ling-3.0-flash-Q4_1/Ling-3.0-flash-Q4_1-00003-of-00003.gguf | GGUF | Q4_1 | 548.1 MB | Download |
| Ling-3.0-flash-Q4_K_L/Ling-3.0-flash-Q4_K_L-00001-of-00002.gguf | GGUF | Q4_K_L | 37.15 GB | Download |
| Ling-3.0-flash-Q4_K_L/Ling-3.0-flash-Q4_K_L-00002-of-00002.gguf | GGUF | Q4_K_L | 35.59 GB | Download |
| Ling-3.0-flash-Q4_K_M/Ling-3.0-flash-Q4_K_M-00001-of-00002.gguf | GGUF | Q4_K_M | 36.87 GB | Download |
| Ling-3.0-flash-Q4_K_M/Ling-3.0-flash-Q4_K_M-00002-of-00002.gguf | GGUF | Q4_K_M | 35.59 GB | Download |
| Ling-3.0-flash-Q4_K_S/Ling-3.0-flash-Q4_K_S-00001-of-00002.gguf | GGUF | Q4_K_S | 37.20 GB | Download |
| Ling-3.0-flash-Q4_K_S/Ling-3.0-flash-Q4_K_S-00002-of-00002.gguf | GGUF | Q4_K_S | 32.69 GB | Download |
| Ling-3.0-flash-Q5_K_L/Ling-3.0-flash-Q5_K_L-00001-of-00003.gguf | GGUF | Q5_K_L | 37.25 GB | Download |
| Ling-3.0-flash-Q5_K_L/Ling-3.0-flash-Q5_K_L-00002-of-00003.gguf | GGUF | Q5_K_L | 36.69 GB | Download |
| Ling-3.0-flash-Q5_K_L/Ling-3.0-flash-Q5_K_L-00003-of-00003.gguf | GGUF | Q5_K_L | 10.73 GB | Download |
| Ling-3.0-flash-Q5_K_M/Ling-3.0-flash-Q5_K_M-00001-of-00003.gguf | GGUF | Q5_K_M | 37.02 GB | Download |
| Ling-3.0-flash-Q5_K_M/Ling-3.0-flash-Q5_K_M-00002-of-00003.gguf | GGUF | Q5_K_M | 36.69 GB | Download |
| Ling-3.0-flash-Q5_K_M/Ling-3.0-flash-Q5_K_M-00003-of-00003.gguf | GGUF | Q5_K_M | 10.73 GB | Download |
| Ling-3.0-flash-Q5_K_S/Ling-3.0-flash-Q5_K_S-00001-of-00003.gguf | GGUF | Q5_K_S | 37.19 GB | Download |
| Ling-3.0-flash-Q5_K_S/Ling-3.0-flash-Q5_K_S-00002-of-00003.gguf | GGUF | Q5_K_S | 37.13 GB | Download |
| Ling-3.0-flash-Q5_K_S/Ling-3.0-flash-Q5_K_S-00003-of-00003.gguf | GGUF | Q5_K_S | 7.53 GB | Download |
| Ling-3.0-flash-Q6_K/Ling-3.0-flash-Q6_K-00001-of-00003.gguf | GGUF | Q6_K | 36.63 GB | Download |
| Ling-3.0-flash-Q6_K/Ling-3.0-flash-Q6_K-00002-of-00003.gguf | GGUF | Q6_K | 36.67 GB | Download |
| Ling-3.0-flash-Q6_K/Ling-3.0-flash-Q6_K-00003-of-00003.gguf | GGUF | Q6_K | 28.46 GB | Download |
| Ling-3.0-flash-Q8_0/Ling-3.0-flash-Q8_0-00001-of-00004.gguf | GGUF | Q8_0 | 36.68 GB | Download |
| Ling-3.0-flash-Q8_0/Ling-3.0-flash-Q8_0-00002-of-00004.gguf | GGUF | Q8_0 | 36.68 GB | Download |
| Ling-3.0-flash-Q8_0/Ling-3.0-flash-Q8_0-00003-of-00004.gguf | GGUF | Q8_0 | 36.68 GB | Download |
| Ling-3.0-flash-Q8_0/Ling-3.0-flash-Q8_0-00004-of-00004.gguf | GGUF | Q8_0 | 16.28 GB | Download |
| Ling-3.0-flash-bf16/Ling-3.0-flash-bf16-00001-of-00007.gguf | GGUF | BF16 | 36.95 GB | Download |
| Ling-3.0-flash-bf16/Ling-3.0-flash-bf16-00002-of-00007.gguf | GGUF | BF16 | 35.63 GB | Download |
| Ling-3.0-flash-bf16/Ling-3.0-flash-bf16-00003-of-00007.gguf | GGUF | BF16 | 35.63 GB | Download |
| Ling-3.0-flash-bf16/Ling-3.0-flash-bf16-00004-of-00007.gguf | GGUF | BF16 | 35.63 GB | Download |
| Ling-3.0-flash-bf16/Ling-3.0-flash-bf16-00005-of-00007.gguf | GGUF | BF16 | 35.63 GB | Download |
| Ling-3.0-flash-bf16/Ling-3.0-flash-bf16-00006-of-00007.gguf | GGUF | BF16 | 35.63 GB | Download |
| Ling-3.0-flash-bf16/Ling-3.0-flash-bf16-00007-of-00007.gguf | GGUF | BF16 | 22.50 GB | Download |
| Ling-3.0-flash-imatrix.gguf | GGUF | GGUF | 465.2 MB | Download |
Model Details
| Model ID | bartowski/Ling-3.0-flash-GGUF |
|---|---|
| Author | bartowski |
| Pipeline | text-generation |
| License | mit |
| Base model | inclusionAI/Ling-3.0-flash |
| Last modified | 2026-08-18T15:26:21.000Z |
Model README
---
quantized_by: bartowski
pipeline_tag: text-generation
license: mit
base_model: inclusionAI/Ling-3.0-flash
base_model_relation: quantized
---
Llamacpp imatrix Quantizations of Ling-3.0-flash by inclusionAI
Using <a href="https://github.com/ggml-org/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggml-org/llama.cpp/releases/tag/b10472">b10472</a> for quantization.
Original model: https://huggingface.co/inclusionAI/Ling-3.0-flash
Model details:
- Parameter count: 127B
- Input support: text
- Speculative decoding: yes (MTP) - details
- imatrix: yes - details
- Perplexity/KLD measured: no
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:
| Filename | Quant type | File Size | Split | Description |
| -------- | ---------- | --------- | ----- | ----------- |
| Ling-3.0-flash-bf16.gguf | bf16 | 255.09GB | true | Full BF16 weights. |
| Ling-3.0-flash-Q8_0.gguf | Q8_0 | 135.63GB | true | Extremely high quality, generally unneeded but max available quant. |
| Ling-3.0-flash-Q6_K.gguf | Q6_K | 109.26GB | true | Very high quality, near perfect, recommended. |
| Ling-3.0-flash-Q5_K_L.gguf | Q5_K_L | 90.91GB | true | Uses Q8_0 for embed and output weights. High quality, recommended. |
| Ling-3.0-flash-Q5_K_M.gguf | Q5_K_M | 90.66GB | true | High quality, recommended. |
| Ling-3.0-flash-Q5_K_S.gguf | Q5_K_S | 87.89GB | true | High quality, recommended. |
| Ling-3.0-flash-Q4_1.gguf | Q4_1 | 80.20GB | true | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. |
| Ling-3.0-flash-Q4_K_L.gguf | Q4_K_L | 78.10GB | true | Uses Q8_0 for embed and output weights. Good quality, recommended. |
| Ling-3.0-flash-Q4_K_M.gguf | Q4_K_M | 77.80GB | true | Good quality, default size for most use cases, recommended. |
| Ling-3.0-flash-Q4_K_S.gguf | Q4_K_S | 75.05GB | true | Slightly lower quality with more space savings, recommended. |
| Ling-3.0-flash-Q4_0.gguf | Q4_0 | 72.84GB | true | Legacy format, kept for compatibility with older tools. |
| Ling-3.0-flash-IQ4_NL.gguf | IQ4_NL | 72.56GB | true | Similar to IQ4_XS, but slightly larger. |
| Ling-3.0-flash-IQ4_XS.gguf | IQ4_XS | 68.74GB | true | Decent quality, smaller than Q4_K_S with similar performance, recommended. |
| Ling-3.0-flash-Q3_K_XL.gguf | Q3_K_XL | 61.78GB | true | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. |
| Ling-3.0-flash-IQ3_M.gguf | IQ3_M | 61.52GB | true | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
| Ling-3.0-flash-Q3_K_L.gguf | Q3_K_L | 61.43GB | true | Lower quality but usable, good for low RAM availability. |
| Ling-3.0-flash-Q3_K_M.gguf | Q3_K_M | 58.97GB | true | Low quality. |
| Ling-3.0-flash-IQ3_XS.gguf | IQ3_XS | 58.94GB | true | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
| Ling-3.0-flash-Q3_K_S.gguf | Q3_K_S | 56.29GB | true | Low quality, not recommended. |
| Ling-3.0-flash-IQ3_XXS.gguf | IQ3_XXS | 54.12GB | true | Lower quality, new method with decent performance, comparable to Q3 quants. |
| Ling-3.0-flash-Q2_K_L.gguf | Q2_K_L | 46.29GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. |
| Ling-3.0-flash-Q2_K.gguf | Q2_K | 45.90GB | false | Very low quality but surprisingly usable. |
| Ling-3.0-flash-IQ2_M.gguf | IQ2_M | 43.64GB | false | Relatively low quality, uses SOTA techniques to be surprisingly usable. |
| Ling-3.0-flash-IQ2_S.gguf | IQ2_S | 39.70GB | false | Low quality, uses SOTA techniques to be usable. |
| Ling-3.0-flash-IQ2_XS.gguf | IQ2_XS | 39.04GB | false | Low quality, uses SOTA techniques to be usable. |
| Ling-3.0-flash-IQ2_XXS.gguf | IQ2_XXS | 35.24GB | false | Very low quality, uses SOTA techniques to be usable. |
| Ling-3.0-flash-IQ1_M.gguf | IQ1_M | 30.56GB | false | Extremely low quality, not recommended. |
| Ling-3.0-flash-IQ1_S.gguf | IQ1_S | 27.57GB | false | Extremely low quality, not recommended. |
Download a specific file:
hf download bartowski/Ling-3.0-flash-GGUF --include "Ling-3.0-flash-Q4_K_M/*" --local-dir ./
Downloading using the Hugging Face CLI
<details>
<summary>Click to view download instructions</summary>
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-GGUF --include "Ling-3.0-flash-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-GGUF --include "Ling-3.0-flash-Q8_0/*" --local-dir ./
You can either specify a new local-dir (Ling-3.0-flash-Q8_0) or download them all in place (./)
</details>
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-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 b10472 - 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-calibration-v6.txt. The imatrix is available here: Ling-3.0-flash-imatrix.gguf.
<details>
<summary>Calibration render details</summary>
{
"generator": "auto_quant_v2 calibration renderer",
"recipe": "calibration-v6",
"model": "Ling-3.0-flash",
"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": []
}
</details>
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?
<details>
<summary>Click here for details</summary>
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:
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.
</details>
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
Run bartowski/Ling-3.0-flash-GGUF with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models