bartowski/granite-3.0-3b-a800m-instruct-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/granite-3.0-3b-a800m-instruct-GGUF
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-08-04 09:59:13 +08:00
commit a8cef873c6
27 changed files with 378 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

59
.gitattributes vendored Normal file
View File

@@ -0,0 +1,59 @@
*.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
granite-3.0-3b-a800m-instruct-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
granite-3.0-3b-a800m-instruct-Q6_K_L.gguf filter=lfs diff=lfs merge=lfs -text
granite-3.0-3b-a800m-instruct-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
granite-3.0-3b-a800m-instruct-Q5_K_L.gguf filter=lfs diff=lfs merge=lfs -text
granite-3.0-3b-a800m-instruct-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
granite-3.0-3b-a800m-instruct-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
granite-3.0-3b-a800m-instruct-Q4_K_L.gguf filter=lfs diff=lfs merge=lfs -text
granite-3.0-3b-a800m-instruct-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
granite-3.0-3b-a800m-instruct-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
granite-3.0-3b-a800m-instruct-Q4_0_8_8.gguf filter=lfs diff=lfs merge=lfs -text
granite-3.0-3b-a800m-instruct-Q4_0_4_8.gguf filter=lfs diff=lfs merge=lfs -text
granite-3.0-3b-a800m-instruct-Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text
granite-3.0-3b-a800m-instruct-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
granite-3.0-3b-a800m-instruct-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
granite-3.0-3b-a800m-instruct-Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
granite-3.0-3b-a800m-instruct-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
granite-3.0-3b-a800m-instruct-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
granite-3.0-3b-a800m-instruct-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
granite-3.0-3b-a800m-instruct-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
granite-3.0-3b-a800m-instruct-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
granite-3.0-3b-a800m-instruct-Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text
granite-3.0-3b-a800m-instruct-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
granite-3.0-3b-a800m-instruct-f16.gguf filter=lfs diff=lfs merge=lfs -text
granite-3.0-3b-a800m-instruct.imatrix filter=lfs diff=lfs merge=lfs -text

246
README.md Normal file
View File

@@ -0,0 +1,246 @@
---
base_model: ibm-granite/granite-3.0-3b-a800m-instruct
license: apache-2.0
pipeline_tag: text-generation
tags:
- language
- granite-3.0
quantized_by: bartowski
inference: false
model-index:
- name: granite-3.0-2b-instruct
results:
- task:
type: text-generation
dataset:
name: IFEval
type: instruction-following
metrics:
- type: pass@1
value: 42.49
name: pass@1
- type: pass@1
value: 7.02
name: pass@1
- task:
type: text-generation
dataset:
name: AGI-Eval
type: human-exams
metrics:
- type: pass@1
value: 25.7
name: pass@1
- type: pass@1
value: 50.16
name: pass@1
- type: pass@1
value: 20.51
name: pass@1
- task:
type: text-generation
dataset:
name: OBQA
type: commonsense
metrics:
- type: pass@1
value: 40.8
name: pass@1
- type: pass@1
value: 59.95
name: pass@1
- type: pass@1
value: 71.86
name: pass@1
- type: pass@1
value: 67.01
name: pass@1
- type: pass@1
value: 48.0
name: pass@1
- task:
type: text-generation
dataset:
name: BoolQ
type: reading-comprehension
metrics:
- type: pass@1
value: 78.65
name: pass@1
- type: pass@1
value: 6.71
name: pass@1
- task:
type: text-generation
dataset:
name: ARC-C
type: reasoning
metrics:
- type: pass@1
value: 50.94
name: pass@1
- type: pass@1
value: 26.85
name: pass@1
- type: pass@1
value: 37.7
name: pass@1
- task:
type: text-generation
dataset:
name: HumanEvalSynthesis
type: code
metrics:
- type: pass@1
value: 39.63
name: pass@1
- type: pass@1
value: 40.85
name: pass@1
- type: pass@1
value: 35.98
name: pass@1
- type: pass@1
value: 27.4
name: pass@1
- task:
type: text-generation
dataset:
name: GSM8K
type: math
metrics:
- type: pass@1
value: 47.54
name: pass@1
- type: pass@1
value: 19.86
name: pass@1
- task:
type: text-generation
dataset:
name: PAWS-X (7 langs)
type: multilingual
metrics:
- type: pass@1
value: 50.23
name: pass@1
- type: pass@1
value: 28.87
name: pass@1
---
## Llamacpp imatrix Quantizations of granite-3.0-3b-a800m-instruct
Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b3930">b3930</a> for quantization.
Original model: https://huggingface.co/ibm-granite/granite-3.0-3b-a800m-instruct
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
```
<|start_of_role|>system<|end_of_role|>{system_prompt}<|end_of_text|>
<|start_of_role|>user<|end_of_role|>{prompt}<|end_of_text|>
<|start_of_role|>assistant<|end_of_role|>
```
## Download a file (not the whole branch) from below:
| Filename | Quant type | File Size | Split | Description |
| -------- | ---------- | --------- | ----- | ----------- |
| [granite-3.0-3b-a800m-instruct-f16.gguf](https://huggingface.co/bartowski/granite-3.0-3b-a800m-instruct-GGUF/blob/main/granite-3.0-3b-a800m-instruct-f16.gguf) | f16 | 6.75GB | false | Full F16 weights. |
| [granite-3.0-3b-a800m-instruct-Q8_0.gguf](https://huggingface.co/bartowski/granite-3.0-3b-a800m-instruct-GGUF/blob/main/granite-3.0-3b-a800m-instruct-Q8_0.gguf) | Q8_0 | 3.59GB | false | Extremely high quality, generally unneeded but max available quant. |
| [granite-3.0-3b-a800m-instruct-Q6_K_L.gguf](https://huggingface.co/bartowski/granite-3.0-3b-a800m-instruct-GGUF/blob/main/granite-3.0-3b-a800m-instruct-Q6_K_L.gguf) | Q6_K_L | 2.81GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. |
| [granite-3.0-3b-a800m-instruct-Q6_K.gguf](https://huggingface.co/bartowski/granite-3.0-3b-a800m-instruct-GGUF/blob/main/granite-3.0-3b-a800m-instruct-Q6_K.gguf) | Q6_K | 2.78GB | false | Very high quality, near perfect, *recommended*. |
| [granite-3.0-3b-a800m-instruct-Q5_K_L.gguf](https://huggingface.co/bartowski/granite-3.0-3b-a800m-instruct-GGUF/blob/main/granite-3.0-3b-a800m-instruct-Q5_K_L.gguf) | Q5_K_L | 2.45GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. |
| [granite-3.0-3b-a800m-instruct-Q5_K_M.gguf](https://huggingface.co/bartowski/granite-3.0-3b-a800m-instruct-GGUF/blob/main/granite-3.0-3b-a800m-instruct-Q5_K_M.gguf) | Q5_K_M | 2.41GB | false | High quality, *recommended*. |
| [granite-3.0-3b-a800m-instruct-Q5_K_S.gguf](https://huggingface.co/bartowski/granite-3.0-3b-a800m-instruct-GGUF/blob/main/granite-3.0-3b-a800m-instruct-Q5_K_S.gguf) | Q5_K_S | 2.34GB | false | High quality, *recommended*. |
| [granite-3.0-3b-a800m-instruct-Q4_K_L.gguf](https://huggingface.co/bartowski/granite-3.0-3b-a800m-instruct-GGUF/blob/main/granite-3.0-3b-a800m-instruct-Q4_K_L.gguf) | Q4_K_L | 2.12GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. |
| [granite-3.0-3b-a800m-instruct-Q4_K_M.gguf](https://huggingface.co/bartowski/granite-3.0-3b-a800m-instruct-GGUF/blob/main/granite-3.0-3b-a800m-instruct-Q4_K_M.gguf) | Q4_K_M | 2.06GB | false | Good quality, default size for must use cases, *recommended*. |
| [granite-3.0-3b-a800m-instruct-Q4_K_S.gguf](https://huggingface.co/bartowski/granite-3.0-3b-a800m-instruct-GGUF/blob/main/granite-3.0-3b-a800m-instruct-Q4_K_S.gguf) | Q4_K_S | 1.94GB | false | Slightly lower quality with more space savings, *recommended*. |
| [granite-3.0-3b-a800m-instruct-Q4_0_8_8.gguf](https://huggingface.co/bartowski/granite-3.0-3b-a800m-instruct-GGUF/blob/main/granite-3.0-3b-a800m-instruct-Q4_0_8_8.gguf) | Q4_0_8_8 | 1.93GB | false | Optimized for ARM inference. Requires 'sve' support (see link below). *Don't use on Mac or Windows*. |
| [granite-3.0-3b-a800m-instruct-Q4_0_4_8.gguf](https://huggingface.co/bartowski/granite-3.0-3b-a800m-instruct-GGUF/blob/main/granite-3.0-3b-a800m-instruct-Q4_0_4_8.gguf) | Q4_0_4_8 | 1.93GB | false | Optimized for ARM inference. Requires 'i8mm' support (see link below). *Don't use on Mac or Windows*. |
| [granite-3.0-3b-a800m-instruct-Q4_0_4_4.gguf](https://huggingface.co/bartowski/granite-3.0-3b-a800m-instruct-GGUF/blob/main/granite-3.0-3b-a800m-instruct-Q4_0_4_4.gguf) | Q4_0_4_4 | 1.93GB | false | Optimized for ARM inference. Should work well on all ARM chips, pick this if you're unsure. *Don't use on Mac or Windows*. |
| [granite-3.0-3b-a800m-instruct-Q4_0.gguf](https://huggingface.co/bartowski/granite-3.0-3b-a800m-instruct-GGUF/blob/main/granite-3.0-3b-a800m-instruct-Q4_0.gguf) | Q4_0 | 1.93GB | false | Legacy format, generally not worth using over similarly sized formats |
| [granite-3.0-3b-a800m-instruct-Q3_K_XL.gguf](https://huggingface.co/bartowski/granite-3.0-3b-a800m-instruct-GGUF/blob/main/granite-3.0-3b-a800m-instruct-Q3_K_XL.gguf) | Q3_K_XL | 1.84GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. |
| [granite-3.0-3b-a800m-instruct-IQ4_XS.gguf](https://huggingface.co/bartowski/granite-3.0-3b-a800m-instruct-GGUF/blob/main/granite-3.0-3b-a800m-instruct-IQ4_XS.gguf) | IQ4_XS | 1.82GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
| [granite-3.0-3b-a800m-instruct-Q3_K_L.gguf](https://huggingface.co/bartowski/granite-3.0-3b-a800m-instruct-GGUF/blob/main/granite-3.0-3b-a800m-instruct-Q3_K_L.gguf) | Q3_K_L | 1.77GB | false | Lower quality but usable, good for low RAM availability. |
| [granite-3.0-3b-a800m-instruct-Q3_K_M.gguf](https://huggingface.co/bartowski/granite-3.0-3b-a800m-instruct-GGUF/blob/main/granite-3.0-3b-a800m-instruct-Q3_K_M.gguf) | Q3_K_M | 1.64GB | false | Low quality. |
| [granite-3.0-3b-a800m-instruct-IQ3_M.gguf](https://huggingface.co/bartowski/granite-3.0-3b-a800m-instruct-GGUF/blob/main/granite-3.0-3b-a800m-instruct-IQ3_M.gguf) | IQ3_M | 1.52GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
| [granite-3.0-3b-a800m-instruct-Q3_K_S.gguf](https://huggingface.co/bartowski/granite-3.0-3b-a800m-instruct-GGUF/blob/main/granite-3.0-3b-a800m-instruct-Q3_K_S.gguf) | Q3_K_S | 1.49GB | false | Low quality, not recommended. |
| [granite-3.0-3b-a800m-instruct-IQ3_XS.gguf](https://huggingface.co/bartowski/granite-3.0-3b-a800m-instruct-GGUF/blob/main/granite-3.0-3b-a800m-instruct-IQ3_XS.gguf) | IQ3_XS | 1.41GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
| [granite-3.0-3b-a800m-instruct-Q2_K_L.gguf](https://huggingface.co/bartowski/granite-3.0-3b-a800m-instruct-GGUF/blob/main/granite-3.0-3b-a800m-instruct-Q2_K_L.gguf) | Q2_K_L | 1.34GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. |
| [granite-3.0-3b-a800m-instruct-Q2_K.gguf](https://huggingface.co/bartowski/granite-3.0-3b-a800m-instruct-GGUF/blob/main/granite-3.0-3b-a800m-instruct-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/granite-3.0-3b-a800m-instruct-GGUF --include "granite-3.0-3b-a800m-instruct-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/granite-3.0-3b-a800m-instruct-GGUF --include "granite-3.0-3b-a800m-instruct-Q8_0/*" --local-dir ./
```
You can either specify a new local-dir (granite-3.0-3b-a800m-instruct-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
granite-3.0-3b-a800m-instruct-IQ3_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:412c4aeee5505663a4c0de06ac4d3b3ac23d0f42003266bcf25361e8702f125d
size 1518585088

3
granite-3.0-3b-a800m-instruct-IQ3_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:92376f0700be4ce976aa06ad4bfa9a542213d78e222b5e3d022de49ccb57e42c
size 1413006592

3
granite-3.0-3b-a800m-instruct-IQ4_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:8821703b576f2b58805b8eda2508836753987ba46bf95c13b08b989394b64304
size 1823327968

3
granite-3.0-3b-a800m-instruct-Q2_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b12f2ba4e635cbb2bcb35823f183f344d40b9742173d844f983ec9b02d8d7238
size 1266139968

3
granite-3.0-3b-a800m-instruct-Q2_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:bd3859f813e3a330961bdce2ebe30f129dfa7098e92774415a419722d811fab5
size 1339872416

3
granite-3.0-3b-a800m-instruct-Q3_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:39b7f5604f2c7d78c593dd5de35bf16d25a4768dbd2f87ae5d0203475f084228
size 1773978880

3
granite-3.0-3b-a800m-instruct-Q3_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1b5d7c48f51a1ccb5f4cbe70d5b8054d7cb468f62416f6e955fa90e92e42986b
size 1643627776

3
granite-3.0-3b-a800m-instruct-Q3_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:8f780c04cd806dbd1aac147e35644e64fa82cc8ce8d73a5839512e45bda91f00
size 1488504064

3
granite-3.0-3b-a800m-instruct-Q3_K_XL.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:cd6c152fcb8f1d8632f3f483dc2fbfb8ee8bbec3891e9fe60ac793e12ac6a171
size 1840043168

3
granite-3.0-3b-a800m-instruct-Q4_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:eafec73c02ddb49b799f1ad6b85d1488ebcc9c2acedb8ba70e6cd0c83093429a
size 1934215008

3
granite-3.0-3b-a800m-instruct-Q4_0_4_4.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5dc8bb24e8def6214912114011ff270d12552101373b4b03d3ccf86e7b832cd9
size 1926350688

3
granite-3.0-3b-a800m-instruct-Q4_0_4_8.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a059a239658fdf8647db19960b04d15230a3b5c389aba1aea99636089ce774c0
size 1926350688

3
granite-3.0-3b-a800m-instruct-Q4_0_8_8.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e073b1e3b551fe3131debb97ed09092b52b37862127c224729f817d0af72b541
size 1926350688

3
granite-3.0-3b-a800m-instruct-Q4_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b6921ac06c2166c2616c8bbee5ee8acdebad0676a7382684ba477b7764123c3f
size 2115392672

3
granite-3.0-3b-a800m-instruct-Q4_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:aa6287bafd182d06a6d11b0d001458deec902e8c0522875fc20cde2f561ebf6d
size 2059356000

3
granite-3.0-3b-a800m-instruct-Q4_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e878a92fa345e756562c47757ed1aba9dc0671709f891b5f2716713ddcde925f
size 1942472544

3
granite-3.0-3b-a800m-instruct-Q5_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2cb242c5d4833cf6076089ea04969c96b81ec6a845fdc8d0cc91ff3985ea7b51
size 2453558432

3
granite-3.0-3b-a800m-instruct-Q5_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:fa91e50ce32b7a44023707368ed0981f522db3a6502cc4f0386b0fe2c8dc97b5
size 2406959520

3
granite-3.0-3b-a800m-instruct-Q5_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:8572b2ac45a1167e858185b282e4094bfa769d972a004a0e30c08f564927a1bc
size 2338441632

3
granite-3.0-3b-a800m-instruct-Q6_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:7b36d31498a39cd7267cfa4f6e3dcb8722cf945fa44f459f8e9f89c76aaee4e3
size 2776288288

3
granite-3.0-3b-a800m-instruct-Q6_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:4ee35a65e1ccab9e53200a4c816a7ae0b9d9bb5e4cc7107c9b1c9bb328a7f1dc
size 2812859552

3
granite-3.0-3b-a800m-instruct-Q8_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b5ee3140bb0a0f7574c835d0b2e18c5ee179f66a7daded44fa488ebf3fd6c397
size 3593000096

3
granite-3.0-3b-a800m-instruct-f16.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1551bd36604702527d101c1857181760f0516374fad72f1ed3a9a68cc98cc590
size 6754465088

3
granite-3.0-3b-a800m-instruct.imatrix Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2fc3baa2bf9138213058c5a839da92f08d78bb90d88128d084fd51e8bb194f07
size 18195136