bartowski/raspberry-3B-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/raspberry-3B-GGUF
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-06-21 17:39:15 +08:00
commit 916815c52b
26 changed files with 253 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

58
.gitattributes vendored Normal file
View File

@@ -0,0 +1,58 @@
*.7z filter=lfs diff=lfs merge=lfs -text
*.arrow filter=lfs diff=lfs merge=lfs -text
*.bin filter=lfs diff=lfs merge=lfs -text
*.bz2 filter=lfs diff=lfs merge=lfs -text
*.ckpt 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
*.mlmodel filter=lfs diff=lfs merge=lfs -text
*.model filter=lfs diff=lfs merge=lfs -text
*.msgpack filter=lfs diff=lfs merge=lfs -text
*.npy filter=lfs diff=lfs merge=lfs -text
*.npz 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
*.pickle filter=lfs diff=lfs merge=lfs -text
*.pkl 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
*.safetensors filter=lfs diff=lfs merge=lfs -text
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
*.tar.* 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
*.wasm filter=lfs diff=lfs merge=lfs -text
*.xz filter=lfs diff=lfs merge=lfs -text
*.zip filter=lfs diff=lfs merge=lfs -text
*.zst filter=lfs diff=lfs merge=lfs -text
*tfevents* filter=lfs diff=lfs merge=lfs -text
raspberry-3B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
raspberry-3B-Q6_K_L.gguf filter=lfs diff=lfs merge=lfs -text
raspberry-3B-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
raspberry-3B-Q5_K_L.gguf filter=lfs diff=lfs merge=lfs -text
raspberry-3B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
raspberry-3B-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
raspberry-3B-Q4_K_L.gguf filter=lfs diff=lfs merge=lfs -text
raspberry-3B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
raspberry-3B-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
raspberry-3B-Q4_0_8_8.gguf filter=lfs diff=lfs merge=lfs -text
raspberry-3B-Q4_0_4_8.gguf filter=lfs diff=lfs merge=lfs -text
raspberry-3B-Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text
raspberry-3B-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
raspberry-3B-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
raspberry-3B-Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
raspberry-3B-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
raspberry-3B-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
raspberry-3B-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
raspberry-3B-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
raspberry-3B-Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text
raspberry-3B-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
raspberry-3B-f16.gguf filter=lfs diff=lfs merge=lfs -text
raspberry-3B.imatrix filter=lfs diff=lfs merge=lfs -text

125
README.md Normal file
View File

@@ -0,0 +1,125 @@
---
base_model: qnguyen3/raspberry-3B
library_name: transformers
license: other
license_name: qwen-research
license_link: https://huggingface.co/Qwen/Qwen2.5-3B-Instruct/blob/main/LICENSE
pipeline_tag: text-generation
tags:
- generated_from_trainer
quantized_by: bartowski
model-index:
- name: outputs/gelato-3b
results: []
---
## Llamacpp imatrix Quantizations of raspberry-3B
Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b3878">b3878</a> for quantization.
Original model: https://huggingface.co/qnguyen3/raspberry-3B
All quants made using imatrix option with dataset from [here](https://gist.github.com/bartowski1182/eb213dccb3571f863da82e99418f81e8)
Run them in [LM Studio](https://lmstudio.ai/)
## Prompt format
No prompt format found, check original model page
## Download a file (not the whole branch) from below:
| Filename | Quant type | File Size | Split | Description |
| -------- | ---------- | --------- | ----- | ----------- |
| [raspberry-3B-f16.gguf](https://huggingface.co/bartowski/raspberry-3B-GGUF/blob/main/raspberry-3B-f16.gguf) | f16 | 6.18GB | false | Full F16 weights. |
| [raspberry-3B-Q8_0.gguf](https://huggingface.co/bartowski/raspberry-3B-GGUF/blob/main/raspberry-3B-Q8_0.gguf) | Q8_0 | 3.29GB | false | Extremely high quality, generally unneeded but max available quant. |
| [raspberry-3B-Q6_K_L.gguf](https://huggingface.co/bartowski/raspberry-3B-GGUF/blob/main/raspberry-3B-Q6_K_L.gguf) | Q6_K_L | 2.61GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. |
| [raspberry-3B-Q6_K.gguf](https://huggingface.co/bartowski/raspberry-3B-GGUF/blob/main/raspberry-3B-Q6_K.gguf) | Q6_K | 2.54GB | false | Very high quality, near perfect, *recommended*. |
| [raspberry-3B-Q5_K_L.gguf](https://huggingface.co/bartowski/raspberry-3B-GGUF/blob/main/raspberry-3B-Q5_K_L.gguf) | Q5_K_L | 2.30GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. |
| [raspberry-3B-Q5_K_M.gguf](https://huggingface.co/bartowski/raspberry-3B-GGUF/blob/main/raspberry-3B-Q5_K_M.gguf) | Q5_K_M | 2.22GB | false | High quality, *recommended*. |
| [raspberry-3B-Q5_K_S.gguf](https://huggingface.co/bartowski/raspberry-3B-GGUF/blob/main/raspberry-3B-Q5_K_S.gguf) | Q5_K_S | 2.17GB | false | High quality, *recommended*. |
| [raspberry-3B-Q4_K_L.gguf](https://huggingface.co/bartowski/raspberry-3B-GGUF/blob/main/raspberry-3B-Q4_K_L.gguf) | Q4_K_L | 2.01GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. |
| [raspberry-3B-Q4_K_M.gguf](https://huggingface.co/bartowski/raspberry-3B-GGUF/blob/main/raspberry-3B-Q4_K_M.gguf) | Q4_K_M | 1.93GB | false | Good quality, default size for must use cases, *recommended*. |
| [raspberry-3B-Q4_K_S.gguf](https://huggingface.co/bartowski/raspberry-3B-GGUF/blob/main/raspberry-3B-Q4_K_S.gguf) | Q4_K_S | 1.83GB | false | Slightly lower quality with more space savings, *recommended*. |
| [raspberry-3B-Q4_0.gguf](https://huggingface.co/bartowski/raspberry-3B-GGUF/blob/main/raspberry-3B-Q4_0.gguf) | Q4_0 | 1.83GB | false | Legacy format, generally not worth using over similarly sized formats |
| [raspberry-3B-Q4_0_8_8.gguf](https://huggingface.co/bartowski/raspberry-3B-GGUF/blob/main/raspberry-3B-Q4_0_8_8.gguf) | Q4_0_8_8 | 1.82GB | false | Optimized for ARM inference. Requires 'sve' support (see link below). |
| [raspberry-3B-Q4_0_4_8.gguf](https://huggingface.co/bartowski/raspberry-3B-GGUF/blob/main/raspberry-3B-Q4_0_4_8.gguf) | Q4_0_4_8 | 1.82GB | false | Optimized for ARM inference. Requires 'i8mm' support (see link below). |
| [raspberry-3B-Q4_0_4_4.gguf](https://huggingface.co/bartowski/raspberry-3B-GGUF/blob/main/raspberry-3B-Q4_0_4_4.gguf) | Q4_0_4_4 | 1.82GB | false | Optimized for ARM inference. Should work well on all ARM chips, pick this if you're unsure. |
| [raspberry-3B-Q3_K_XL.gguf](https://huggingface.co/bartowski/raspberry-3B-GGUF/blob/main/raspberry-3B-Q3_K_XL.gguf) | Q3_K_XL | 1.78GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. |
| [raspberry-3B-IQ4_XS.gguf](https://huggingface.co/bartowski/raspberry-3B-GGUF/blob/main/raspberry-3B-IQ4_XS.gguf) | IQ4_XS | 1.74GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
| [raspberry-3B-Q3_K_L.gguf](https://huggingface.co/bartowski/raspberry-3B-GGUF/blob/main/raspberry-3B-Q3_K_L.gguf) | Q3_K_L | 1.71GB | false | Lower quality but usable, good for low RAM availability. |
| [raspberry-3B-IQ3_M.gguf](https://huggingface.co/bartowski/raspberry-3B-GGUF/blob/main/raspberry-3B-IQ3_M.gguf) | IQ3_M | 1.49GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
| [raspberry-3B-Q3_K_S.gguf](https://huggingface.co/bartowski/raspberry-3B-GGUF/blob/main/raspberry-3B-Q3_K_S.gguf) | Q3_K_S | 1.45GB | false | Low quality, not recommended. |
| [raspberry-3B-IQ3_XS.gguf](https://huggingface.co/bartowski/raspberry-3B-GGUF/blob/main/raspberry-3B-IQ3_XS.gguf) | IQ3_XS | 1.39GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
| [raspberry-3B-Q2_K_L.gguf](https://huggingface.co/bartowski/raspberry-3B-GGUF/blob/main/raspberry-3B-Q2_K_L.gguf) | Q2_K_L | 1.35GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. |
| [raspberry-3B-Q2_K.gguf](https://huggingface.co/bartowski/raspberry-3B-GGUF/blob/main/raspberry-3B-Q2_K.gguf) | Q2_K | 1.27GB | false | Very low quality but 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.
Some say that this improves the quality, others don't notice any difference. If you use these models PLEASE COMMENT with your findings. I would like feedback that these are actually used and useful so I don't keep uploading quants no one is using.
Thanks!
## Downloading using huggingface-cli
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/raspberry-3B-GGUF --include "raspberry-3B-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/raspberry-3B-GGUF --include "raspberry-3B-Q8_0/*" --local-dir ./
```
You can either specify a new local-dir (raspberry-3B-Q8_0) or download them all in place (./)
## Q4_0_X_X
These are *NOT* for Metal (Apple) offloading, only ARM chips.
If you're using an ARM chip, the Q4_0_X_X quants will have a substantial speedup. Check out Q4_0_4_4 speed comparisons [on the original pull request](https://github.com/ggerganov/llama.cpp/pull/5780#pullrequestreview-21657544660)
To check which one would work best for your ARM chip, you can check [AArch64 SoC features](https://gpages.juszkiewicz.com.pl/arm-socs-table/arm-socs.html) (thanks EloyOn!).
## Which file should I choose?
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 and Apple Metal, but will be slower than their K-quant equivalent, so speed vs performance is a tradeoff you'll have to decide.
The I-quants are *not* compatible with Vulcan, which is also AMD, so if you have an AMD card double check if you're using the rocBLAS build or the Vulcan build. At the time of writing this, LM Studio has a preview with ROCm support, and other inference engines have specific builds for ROCm.
## 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

1
configuration.json Normal file
View File

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

3
raspberry-3B-IQ3_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:72ab6539b1ef0a732dad94215b1e064d2153939b2490fd9325b88cdee011062d
size 1488894976

3
raspberry-3B-IQ3_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e67827028343b36e97abe7d6aa3c631bca63e22554e01cf860a74ce473d8ba62
size 1391836160

3
raspberry-3B-IQ4_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5f31d669285555f79147c2c86f82a7fc924718c5c056ef77060118ba8998729c
size 1739095040

3
raspberry-3B-Q2_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b4a8810101cce9790cca457345623c66512341651355418ac48d55a54078749a
size 1274756096

3
raspberry-3B-Q2_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e6c7b89e1f988cfb2d429e7df481e708368e573de64148dae16c7fde3bab3b10
size 1350116352

3
raspberry-3B-Q3_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5da6df49372e102be49538c291423b1c9e0d5b11421c330f2bb8d5a11e757ea5
size 1707392000

3
raspberry-3B-Q3_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:78ecfe5e42cade62153031d057d3bfa155b086eac24038fef91b02b25ea0cd8a
size 1454357504

3
raspberry-3B-Q3_K_XL.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:08d89e53927e12fa5e680debc43aa59975f7379b21fcf33cea4aebd466545567
size 1782752256

3
raspberry-3B-Q4_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d8989081e05310f2ac5a9798a495004d60cf238f355772f6d9bc0d3aeae1ee7b
size 1828486144

3
raspberry-3B-Q4_0_4_4.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:de5b2318273539a52043b27d24df7d692c890a4ed181eb1627bde996896655ef
size 1822850048

3
raspberry-3B-Q4_0_4_8.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2e7b63205fa9d0a9bf35d4cc60a1a08493aa2b8511f36707fa5e8f5cb0de88f4
size 1822850048

3
raspberry-3B-Q4_0_8_8.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:94c98461db5ab4a8addd3dd86e1c6181ad80c280dcf9a9cfca30ededa4102790
size 1822850048

3
raspberry-3B-Q4_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2e05f7f007fefed5a7fec7387d1ac2b8e3b6938eea9abbb89c204208733da617
size 2005263360

3
raspberry-3B-Q4_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:fe6d393b76a189d1595b2ba0d2fe9285329e828fd8979e8c23e4730d1ab8d894
size 1929903104

3
raspberry-3B-Q4_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c52ae1314c10e54efa9ab7c6179cf89024ebafa5aa191deca927853cf14a16ac
size 1834384384

3
raspberry-3B-Q5_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c354cf5e6f7a4f74fb456d87ade35f50391d1635e77e3907adc700a7908cb609
size 2300175360

3
raspberry-3B-Q5_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:422747d0ee6949c7d2e1d15bf980863e26f3ad850283f011514cae0445485286
size 2224815104

3
raspberry-3B-Q5_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d81335e02bd84e95a4d24465eaeac08a3c0ba69e6f176025bf39f286f7726ce9
size 2169666560

3
raspberry-3B-Q6_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:07492d1d0a1e6578b57f3fec5ebacc06ac50608f483a0e4c474f1ea7af94b53b
size 2538159104

3
raspberry-3B-Q6_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:04c40a026b7787eafdc729768327f90eb34cfafba480ec3277efc379ba219280
size 2613519360

3
raspberry-3B-Q8_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:17f3529780728d9bc7f620ecd7c576f8a3ad859bf5cdf282fdca4d1cb2eefe18
size 3285476352

3
raspberry-3B-f16.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:14d52679d502cd507d83ce6a494ba7c4c5e3b6b6aaf20a604e48c5cc41a7cabb
size 6178317056

3
raspberry-3B.imatrix Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:8f20e86fa6f4dac9653094af2b225d5f4b0e25680e21f97a072dfaa406ecb31f
size 3362990