bartowski/google_gemma-3-4b-it-qat-GGUF
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: bartowski/google_gemma-3-4b-it-qat-GGUF
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-08-16 07:09:13 +08:00
commit f6c06eecfe
29 changed files with 312 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

47
.gitattributes vendored Normal file
View File

@@ -0,0 +1,47 @@
*.7z filter=lfs diff=lfs merge=lfs -text
*.arrow filter=lfs diff=lfs merge=lfs -text
*.bin filter=lfs diff=lfs merge=lfs -text
*.bin.* filter=lfs diff=lfs merge=lfs -text
*.bz2 filter=lfs diff=lfs merge=lfs -text
*.ftz filter=lfs diff=lfs merge=lfs -text
*.gz filter=lfs diff=lfs merge=lfs -text
*.h5 filter=lfs diff=lfs merge=lfs -text
*.joblib filter=lfs diff=lfs merge=lfs -text
*.lfs.* filter=lfs diff=lfs merge=lfs -text
*.model filter=lfs diff=lfs merge=lfs -text
*.msgpack filter=lfs diff=lfs merge=lfs -text
*.onnx filter=lfs diff=lfs merge=lfs -text
*.ot filter=lfs diff=lfs merge=lfs -text
*.parquet filter=lfs diff=lfs merge=lfs -text
*.pb filter=lfs diff=lfs merge=lfs -text
*.pt filter=lfs diff=lfs merge=lfs -text
*.pth filter=lfs diff=lfs merge=lfs -text
*.rar filter=lfs diff=lfs merge=lfs -text
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
*.tar.* filter=lfs diff=lfs merge=lfs -text
*.tflite filter=lfs diff=lfs merge=lfs -text
*.tgz filter=lfs diff=lfs merge=lfs -text
*.xz filter=lfs diff=lfs merge=lfs -text
*.zip filter=lfs diff=lfs merge=lfs -text
*.zstandard filter=lfs diff=lfs merge=lfs -text
*.tfevents* filter=lfs diff=lfs merge=lfs -text
*.db* filter=lfs diff=lfs merge=lfs -text
*.ark* filter=lfs diff=lfs merge=lfs -text
**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
*.safetensors filter=lfs diff=lfs merge=lfs -text
*.ckpt filter=lfs diff=lfs merge=lfs -text
*.gguf* filter=lfs diff=lfs merge=lfs -text
*.ggml filter=lfs diff=lfs merge=lfs -text
*.llamafile* filter=lfs diff=lfs merge=lfs -text
*.pt2 filter=lfs diff=lfs merge=lfs -text
*.mlmodel filter=lfs diff=lfs merge=lfs -text
*.npy filter=lfs diff=lfs merge=lfs -text
*.npz filter=lfs diff=lfs merge=lfs -text
*.pickle filter=lfs diff=lfs merge=lfs -text
*.pkl filter=lfs diff=lfs merge=lfs -text
*.tar filter=lfs diff=lfs merge=lfs -text
*.wasm filter=lfs diff=lfs merge=lfs -text
*.zst filter=lfs diff=lfs merge=lfs -text
*tfevents* filter=lfs diff=lfs merge=lfs -text

189
README.md Normal file
View File

@@ -0,0 +1,189 @@
---
quantized_by: bartowski
pipeline_tag: image-text-to-text
tags:
- gemma3
- gemma
- google
license: gemma
extra_gated_button_content: Acknowledge license
base_model_relation: quantized
extra_gated_heading: Access Gemma on Hugging Face
extra_gated_prompt: >-
To access Gemma on Hugging Face, you’re required to review and agree to
Google’s usage license. To do this, please ensure you’re logged in to Hugging
Face and click below. Requests are processed immediately.
base_model: google/gemma-3-4b-it-qat-q4_0-unquantized
---
## Llamacpp imatrix Quantizations of gemma-3-4b-it-qat by google
These are derived from the QAT (quantized aware training) weights provided by Google
*ONLY* Q4_0 is expected to be better, but figured while I'm at it I might as well make others to see what happens?
[gemma-3-4b-it-qat-Q4_0.gguf](https://huggingface.co/bartowski/google_gemma-3-4b-it-qat-GGUF/blob/main/google_gemma-3-4b-it-qat-Q4_0.gguf) | Q4_0 | 2.37GB | false | Should be improved due to QAT, offers online repacking for ARM and AVX CPU inference.
Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b5147">b5147</a> for quantization.
Original model: https://huggingface.co/google/gemma-3-4b-it-qat-q4_0-unquantized
All quants made using imatrix option with dataset from [here](https://gist.github.com/bartowski1182/eb213dccb3571f863da82e99418f81e8)
Run them in [LM Studio](https://lmstudio.ai/)
Run them directly with [llama.cpp](https://github.com/ggerganov/llama.cpp), or any other llama.cpp based project
## Prompt format
```
<bos><start_of_turn>user
{system_prompt}
{prompt}<end_of_turn>
<start_of_turn>model
<end_of_turn>
<start_of_turn>model
```
## Download a file (not the whole branch) from below:
| Filename | Quant type | File Size | Split | Description |
| -------- | ---------- | --------- | ----- | ----------- |
| [gemma-3-4b-it-qat-bf16.gguf](https://huggingface.co/bartowski/google_gemma-3-4b-it-qat-GGUF/blob/main/google_gemma-3-4b-it-qat-bf16.gguf) | bf16 | 7.77GB | false | Full BF16 weights. |
| [gemma-3-4b-it-qat-Q8_0.gguf](https://huggingface.co/bartowski/google_gemma-3-4b-it-qat-GGUF/blob/main/google_gemma-3-4b-it-qat-Q8_0.gguf) | Q8_0 | 4.13GB | false | Extremely high quality, generally unneeded but max available quant. |
| [gemma-3-4b-it-qat-Q6_K_L.gguf](https://huggingface.co/bartowski/google_gemma-3-4b-it-qat-GGUF/blob/main/google_gemma-3-4b-it-qat-Q6_K_L.gguf) | Q6_K_L | 3.35GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. |
| [gemma-3-4b-it-qat-Q6_K.gguf](https://huggingface.co/bartowski/google_gemma-3-4b-it-qat-GGUF/blob/main/google_gemma-3-4b-it-qat-Q6_K.gguf) | Q6_K | 3.19GB | false | Very high quality, near perfect, *recommended*. |
| [gemma-3-4b-it-qat-Q5_K_L.gguf](https://huggingface.co/bartowski/google_gemma-3-4b-it-qat-GGUF/blob/main/google_gemma-3-4b-it-qat-Q5_K_L.gguf) | Q5_K_L | 2.99GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. |
| [gemma-3-4b-it-qat-Q5_K_M.gguf](https://huggingface.co/bartowski/google_gemma-3-4b-it-qat-GGUF/blob/main/google_gemma-3-4b-it-qat-Q5_K_M.gguf) | Q5_K_M | 2.83GB | false | High quality, *recommended*. |
| [gemma-3-4b-it-qat-Q5_K_S.gguf](https://huggingface.co/bartowski/google_gemma-3-4b-it-qat-GGUF/blob/main/google_gemma-3-4b-it-qat-Q5_K_S.gguf) | Q5_K_S | 2.76GB | false | High quality, *recommended*. |
| [gemma-3-4b-it-qat-Q4_K_L.gguf](https://huggingface.co/bartowski/google_gemma-3-4b-it-qat-GGUF/blob/main/google_gemma-3-4b-it-qat-Q4_K_L.gguf) | Q4_K_L | 2.65GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. |
| [gemma-3-4b-it-qat-Q4_1.gguf](https://huggingface.co/bartowski/google_gemma-3-4b-it-qat-GGUF/blob/main/google_gemma-3-4b-it-qat-Q4_1.gguf) | Q4_1 | 2.56GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. |
| [gemma-3-4b-it-qat-Q4_K_M.gguf](https://huggingface.co/bartowski/google_gemma-3-4b-it-qat-GGUF/blob/main/google_gemma-3-4b-it-qat-Q4_K_M.gguf) | Q4_K_M | 2.49GB | false | Good quality, default size for most use cases, *recommended*. |
| [gemma-3-4b-it-qat-Q3_K_XL.gguf](https://huggingface.co/bartowski/google_gemma-3-4b-it-qat-GGUF/blob/main/google_gemma-3-4b-it-qat-Q3_K_XL.gguf) | Q3_K_XL | 2.40GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. |
| [gemma-3-4b-it-qat-Q4_K_S.gguf](https://huggingface.co/bartowski/google_gemma-3-4b-it-qat-GGUF/blob/main/google_gemma-3-4b-it-qat-Q4_K_S.gguf) | Q4_K_S | 2.38GB | false | Slightly lower quality with more space savings, *recommended*. |
| [gemma-3-4b-it-qat-Q4_0.gguf](https://huggingface.co/bartowski/google_gemma-3-4b-it-qat-GGUF/blob/main/google_gemma-3-4b-it-qat-Q4_0.gguf) | Q4_0 | 2.37GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. |
| [gemma-3-4b-it-qat-IQ4_NL.gguf](https://huggingface.co/bartowski/google_gemma-3-4b-it-qat-GGUF/blob/main/google_gemma-3-4b-it-qat-IQ4_NL.gguf) | IQ4_NL | 2.36GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. |
| [gemma-3-4b-it-qat-IQ4_XS.gguf](https://huggingface.co/bartowski/google_gemma-3-4b-it-qat-GGUF/blob/main/google_gemma-3-4b-it-qat-IQ4_XS.gguf) | IQ4_XS | 2.26GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
| [gemma-3-4b-it-qat-Q3_K_L.gguf](https://huggingface.co/bartowski/google_gemma-3-4b-it-qat-GGUF/blob/main/google_gemma-3-4b-it-qat-Q3_K_L.gguf) | Q3_K_L | 2.24GB | false | Lower quality but usable, good for low RAM availability. |
| [gemma-3-4b-it-qat-Q3_K_M.gguf](https://huggingface.co/bartowski/google_gemma-3-4b-it-qat-GGUF/blob/main/google_gemma-3-4b-it-qat-Q3_K_M.gguf) | Q3_K_M | 2.10GB | false | Low quality. |
| [gemma-3-4b-it-qat-IQ3_M.gguf](https://huggingface.co/bartowski/google_gemma-3-4b-it-qat-GGUF/blob/main/google_gemma-3-4b-it-qat-IQ3_M.gguf) | IQ3_M | 1.99GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
| [gemma-3-4b-it-qat-Q3_K_S.gguf](https://huggingface.co/bartowski/google_gemma-3-4b-it-qat-GGUF/blob/main/google_gemma-3-4b-it-qat-Q3_K_S.gguf) | Q3_K_S | 1.94GB | false | Low quality, not recommended. |
| [gemma-3-4b-it-qat-Q2_K_L.gguf](https://huggingface.co/bartowski/google_gemma-3-4b-it-qat-GGUF/blob/main/google_gemma-3-4b-it-qat-Q2_K_L.gguf) | Q2_K_L | 1.89GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. |
| [gemma-3-4b-it-qat-IQ3_XS.gguf](https://huggingface.co/bartowski/google_gemma-3-4b-it-qat-GGUF/blob/main/google_gemma-3-4b-it-qat-IQ3_XS.gguf) | IQ3_XS | 1.86GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
| [gemma-3-4b-it-qat-Q2_K.gguf](https://huggingface.co/bartowski/google_gemma-3-4b-it-qat-GGUF/blob/main/google_gemma-3-4b-it-qat-Q2_K.gguf) | Q2_K | 1.73GB | false | Very low quality but surprisingly usable. |
| [gemma-3-4b-it-qat-IQ3_XXS.gguf](https://huggingface.co/bartowski/google_gemma-3-4b-it-qat-GGUF/blob/main/google_gemma-3-4b-it-qat-IQ3_XXS.gguf) | IQ3_XXS | 1.69GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. |
| [gemma-3-4b-it-qat-IQ2_M.gguf](https://huggingface.co/bartowski/google_gemma-3-4b-it-qat-GGUF/blob/main/google_gemma-3-4b-it-qat-IQ2_M.gguf) | IQ2_M | 1.54GB | false | Relatively low quality, uses SOTA techniques to be surprisingly usable. |
## 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.
## Downloading using huggingface-cli
<details>
<summary>Click to view download instructions</summary>
First, make sure you have hugginface-cli installed:
```
pip install -U "huggingface_hub[cli]"
```
Then, you can target the specific file you want:
```
huggingface-cli download bartowski/google_gemma-3-4b-it-qat-GGUF --include "google_gemma-3-4b-it-qat-Q4_K_M.gguf" --local-dir ./
```
If the model is bigger than 50GB, it will have been split into multiple files. In order to download them all to a local folder, run:
```
huggingface-cli download bartowski/google_gemma-3-4b-it-qat-GGUF --include "google_gemma-3-4b-it-qat-Q8_0/*" --local-dir ./
```
You can either specify a new local-dir (google_gemma-3-4b-it-qat-Q8_0) or download them all in place (./)
</details>
## ARM/AVX information
Previously, you would download Q4_0_4_4/4_8/8_8, and these would have their weights interleaved in memory in order to improve performance on ARM and AVX machines by loading up more data in one pass.
Now, however, there is something called "online repacking" for weights. details in [this PR](https://github.com/ggerganov/llama.cpp/pull/9921). If you use Q4_0 and your hardware would benefit from repacking weights, it will do it automatically on the fly.
As of llama.cpp build [b4282](https://github.com/ggerganov/llama.cpp/releases/tag/b4282) you will not be able to run the Q4_0_X_X files and will instead need to use Q4_0.
Additionally, if you want to get slightly better quality for , you can use IQ4_NL thanks to [this PR](https://github.com/ggerganov/llama.cpp/pull/10541) which will also repack the weights for ARM, though only the 4_4 for now. The loading time may be slower but it will result in an overall speed incrase.
<details>
<summary>Click to view Q4_0_X_X information (deprecated</summary>
I'm keeping this section to show the potential theoretical uplift in performance from using the Q4_0 with online repacking.
<details>
<summary>Click to view benchmarks on an AVX2 system (EPYC7702)</summary>
| model | size | params | backend | threads | test | t/s | % (vs Q4_0) |
| ------------------------------ | ---------: | ---------: | ---------- | ------: | ------------: | -------------------: |-------------: |
| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | pp512 | 204.03 ± 1.03 | 100% |
| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | pp1024 | 282.92 ± 0.19 | 100% |
| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | pp2048 | 259.49 ± 0.44 | 100% |
| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | tg128 | 39.12 ± 0.27 | 100% |
| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | tg256 | 39.31 ± 0.69 | 100% |
| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | tg512 | 40.52 ± 0.03 | 100% |
| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | pp512 | 301.02 ± 1.74 | 147% |
| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | pp1024 | 287.23 ± 0.20 | 101% |
| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | pp2048 | 262.77 ± 1.81 | 101% |
| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | tg128 | 18.80 ± 0.99 | 48% |
| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | tg256 | 24.46 ± 3.04 | 83% |
| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | tg512 | 36.32 ± 3.59 | 90% |
| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | pp512 | 271.71 ± 3.53 | 133% |
| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | pp1024 | 279.86 ± 45.63 | 100% |
| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | pp2048 | 320.77 ± 5.00 | 124% |
| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | tg128 | 43.51 ± 0.05 | 111% |
| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | tg256 | 43.35 ± 0.09 | 110% |
| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | tg512 | 42.60 ± 0.31 | 105% |
Q4_0_8_8 offers a nice bump to prompt processing and a small bump to text generation
</details>
</details>
## Which file should I choose?
<details>
<summary>Click here for details</summary>
A great write up with charts showing various 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.
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/ggerganov/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.
</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.
Thank you to LM Studio for sponsoring my work.
Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski

1
configuration.json Normal file
View File

@@ -0,0 +1 @@
{"framework": "pytorch", "task": "image-text-to-text", "allow_remote": true}

3
google_gemma-3-4b-it-qat-IQ2_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0c2b1894f89c82501adde440286834dbaf75f77971785a18a643bf7ed444b341
size 1537982624

3
google_gemma-3-4b-it-qat-IQ3_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:65d2890dc1c82aff8ff1820aa3acb5293218f5dd6a88f79efd686d8e700f5839
size 1986803104

3
google_gemma-3-4b-it-qat-IQ3_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2976c0abcc70aad7dc4c1524fcc31add527206f52dca60eeab546a420477ea95
size 1863390624

3
google_gemma-3-4b-it-qat-IQ3_XXS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:bbb588cd5d068491bf02112881207437731dd23d0dd77a14d298e72d2df6baaf
size 1689452704

3
google_gemma-3-4b-it-qat-IQ4_NL.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:964e89d953e100a9ac67d1598cf07cb5f40aeabef73d9f1551df44a98700bf5b
size 2363512224

3
google_gemma-3-4b-it-qat-IQ4_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:4be7f6bacbef3df02216c3cefd65e07c926da9d8a43f335c9838aebc0e9f2454
size 2263242144

3
google_gemma-3-4b-it-qat-Q2_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d1b967d515da3dd59cd1c9792c044b1b6bbb92d18416f3b3ce9c6dd38d49ed0e
size 1729164704

3
google_gemma-3-4b-it-qat-Q2_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:cb70394c826e4c0c43c54f0b2e4515ba05abbe01bdeedae9513ba8fdd2244545
size 1891733664

3
google_gemma-3-4b-it-qat-Q3_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:8f04eec2665818d5a42ec92eef0aba8a406cc007149bfa1a8cd840a85d66b305
size 2236085664

3
google_gemma-3-4b-it-qat-Q3_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d981cc6b6826ee6ba608d7756f4c27de9e2d075ffd364777aca53783f0d9356b
size 2098460064

3
google_gemma-3-4b-it-qat-Q3_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2f9d48a55d415f934645218354c0cc913ac7e666183432646bb535314d9fa739
size 1937364384

3
google_gemma-3-4b-it-qat-Q3_K_XL.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:72f5466b84f8e340b0e45ec8160028b8252954c4e2ff4fa7d5d7757c9d5a3e60
size 2398654624

3
google_gemma-3-4b-it-qat-Q4_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0231e2cba887f4c7834c39b34251e26b2eebbb71dfac0f7e6e2b2c2531c1a583
size 2370065824

3
google_gemma-3-4b-it-qat-Q4_1.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f4d291a13da4e66fb9885911c12f823e3f56f11dbcbe961f4d87036c89cbdd54
size 2564052384

3
google_gemma-3-4b-it-qat-Q4_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a0dc9943512cd63de0d823db17d7ed0eb7bcd8009154a728cc70dbffca245358
size 2652463264

3
google_gemma-3-4b-it-qat-Q4_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:00165396c856791d12d935d8094b360c71243abd7475390d1efe4e109035b964
size 2489894304

3
google_gemma-3-4b-it-qat-Q4_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:dc4b486f7bd4a1c3ac6237104ffd13b06f9d1d416f10bfac299e2638c71b0553
size 2377930144

3
google_gemma-3-4b-it-qat-Q5_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d2409ae30a733a78385f82ad762f99b64016e975dfd8a62b2b91ad4515e330be
size 2992267424

3
google_gemma-3-4b-it-qat-Q5_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ca258aa4d97be94ac66d27e538552003af4c4bab1f596ef0469753d7f0f06c96
size 2829698464

3
google_gemma-3-4b-it-qat-Q5_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:cad754df66c16a98a999dbb8ed32491d2c301c88fa7820b662e13f03293421f1
size 2764592544

3
google_gemma-3-4b-it-qat-Q6_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:7791f894e35f458f2add66f597e2ba62b477934978d6ca419a04df55ec6a4e47
size 3190740384

3
google_gemma-3-4b-it-qat-Q6_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:58fbabad0e07bdb27c310fbf6c8bde399855714e954d4feef75f2315c3690d76
size 3353309344

3
google_gemma-3-4b-it-qat-Q8_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:7165216f1d87c9c1cc4932afb24e99d8c348392c0dfbf4e9756c8b5eabf82a4f
size 4130402464

3
google_gemma-3-4b-it-qat-bf16.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5c54dff5d89a4f05f83b4faebc75f4edb3ed2b5997a9eb20b07478dfab3cb8cb
size 7767803808

BIN
google_gemma-3-4b-it-qat.imatrix Normal file
View File

Binary file not shown.

3
mmproj-google_gemma-3-4b-it-qat-f16.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:8c0fb064b019a6972856aaae2c7e4792858af3ca4561be2dbf649123ba6c40cb
size 851251104