bartowski/granite-3.0-8b-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-3.0-8b-instruct-GGUF
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-07-21 03:24:07 +08:00
commit 680f708bea
28 changed files with 383 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

60
.gitattributes vendored Normal file
View File

@@ -0,0 +1,60 @@
*.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-3.0-8b-instruct-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
granite-3.0-8b-instruct-Q6_K_L.gguf filter=lfs diff=lfs merge=lfs -text
granite-3.0-8b-instruct-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
granite-3.0-8b-instruct-Q5_K_L.gguf filter=lfs diff=lfs merge=lfs -text
granite-3.0-8b-instruct-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
granite-3.0-8b-instruct-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
granite-3.0-8b-instruct-Q4_K_L.gguf filter=lfs diff=lfs merge=lfs -text
granite-3.0-8b-instruct-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
granite-3.0-8b-instruct-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
granite-3.0-8b-instruct-Q4_0_8_8.gguf filter=lfs diff=lfs merge=lfs -text
granite-3.0-8b-instruct-Q4_0_4_8.gguf filter=lfs diff=lfs merge=lfs -text
granite-3.0-8b-instruct-Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text
granite-3.0-8b-instruct-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
granite-3.0-8b-instruct-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
granite-3.0-8b-instruct-Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
granite-3.0-8b-instruct-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
granite-3.0-8b-instruct-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
granite-3.0-8b-instruct-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
granite-3.0-8b-instruct-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
granite-3.0-8b-instruct-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
granite-3.0-8b-instruct-Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text
granite-3.0-8b-instruct-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
granite-3.0-8b-instruct-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text
granite-3.0-8b-instruct-f16.gguf filter=lfs diff=lfs merge=lfs -text
granite-3.0-8b-instruct.imatrix filter=lfs diff=lfs merge=lfs -text

247
README.md Normal file
View File

@@ -0,0 +1,247 @@
---
base_model: ibm-granite/granite-3.0-8b-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: 52.27
name: pass@1
- type: pass@1
value: 8.22
name: pass@1
- task:
type: text-generation
dataset:
name: AGI-Eval
type: human-exams
metrics:
- type: pass@1
value: 40.52
name: pass@1
- type: pass@1
value: 65.82
name: pass@1
- type: pass@1
value: 34.45
name: pass@1
- task:
type: text-generation
dataset:
name: OBQA
type: commonsense
metrics:
- type: pass@1
value: 46.6
name: pass@1
- type: pass@1
value: 71.21
name: pass@1
- type: pass@1
value: 82.61
name: pass@1
- type: pass@1
value: 77.51
name: pass@1
- type: pass@1
value: 60.32
name: pass@1
- task:
type: text-generation
dataset:
name: BoolQ
type: reading-comprehension
metrics:
- type: pass@1
value: 88.65
name: pass@1
- type: pass@1
value: 21.58
name: pass@1
- task:
type: text-generation
dataset:
name: ARC-C
type: reasoning
metrics:
- type: pass@1
value: 64.16
name: pass@1
- type: pass@1
value: 33.81
name: pass@1
- type: pass@1
value: 51.55
name: pass@1
- task:
type: text-generation
dataset:
name: HumanEvalSynthesis
type: code
metrics:
- type: pass@1
value: 64.63
name: pass@1
- type: pass@1
value: 57.16
name: pass@1
- type: pass@1
value: 65.85
name: pass@1
- type: pass@1
value: 49.6
name: pass@1
- task:
type: text-generation
dataset:
name: GSM8K
type: math
metrics:
- type: pass@1
value: 68.99
name: pass@1
- type: pass@1
value: 30.94
name: pass@1
- task:
type: text-generation
dataset:
name: PAWS-X (7 langs)
type: multilingual
metrics:
- type: pass@1
value: 64.94
name: pass@1
- type: pass@1
value: 48.2
name: pass@1
---
## Llamacpp imatrix Quantizations of granite-3.0-8b-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-3.0-8b-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-3.0-8b-instruct-f16.gguf](https://huggingface.co/bartowski/granite-3.0-8b-instruct-GGUF/blob/main/granite-3.0-8b-instruct-f16.gguf) | f16 | 16.34GB | false | Full F16 weights. |
| [granite-3.0-8b-instruct-Q8_0.gguf](https://huggingface.co/bartowski/granite-3.0-8b-instruct-GGUF/blob/main/granite-3.0-8b-instruct-Q8_0.gguf) | Q8_0 | 8.68GB | false | Extremely high quality, generally unneeded but max available quant. |
| [granite-3.0-8b-instruct-Q6_K_L.gguf](https://huggingface.co/bartowski/granite-3.0-8b-instruct-GGUF/blob/main/granite-3.0-8b-instruct-Q6_K_L.gguf) | Q6_K_L | 6.75GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. |
| [granite-3.0-8b-instruct-Q6_K.gguf](https://huggingface.co/bartowski/granite-3.0-8b-instruct-GGUF/blob/main/granite-3.0-8b-instruct-Q6_K.gguf) | Q6_K | 6.71GB | false | Very high quality, near perfect, *recommended*. |
| [granite-3.0-8b-instruct-Q5_K_L.gguf](https://huggingface.co/bartowski/granite-3.0-8b-instruct-GGUF/blob/main/granite-3.0-8b-instruct-Q5_K_L.gguf) | Q5_K_L | 5.85GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. |
| [granite-3.0-8b-instruct-Q5_K_M.gguf](https://huggingface.co/bartowski/granite-3.0-8b-instruct-GGUF/blob/main/granite-3.0-8b-instruct-Q5_K_M.gguf) | Q5_K_M | 5.80GB | false | High quality, *recommended*. |
| [granite-3.0-8b-instruct-Q5_K_S.gguf](https://huggingface.co/bartowski/granite-3.0-8b-instruct-GGUF/blob/main/granite-3.0-8b-instruct-Q5_K_S.gguf) | Q5_K_S | 5.65GB | false | High quality, *recommended*. |
| [granite-3.0-8b-instruct-Q4_K_L.gguf](https://huggingface.co/bartowski/granite-3.0-8b-instruct-GGUF/blob/main/granite-3.0-8b-instruct-Q4_K_L.gguf) | Q4_K_L | 4.99GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. |
| [granite-3.0-8b-instruct-Q4_K_M.gguf](https://huggingface.co/bartowski/granite-3.0-8b-instruct-GGUF/blob/main/granite-3.0-8b-instruct-Q4_K_M.gguf) | Q4_K_M | 4.94GB | false | Good quality, default size for must use cases, *recommended*. |
| [granite-3.0-8b-instruct-Q4_K_S.gguf](https://huggingface.co/bartowski/granite-3.0-8b-instruct-GGUF/blob/main/granite-3.0-8b-instruct-Q4_K_S.gguf) | Q4_K_S | 4.69GB | false | Slightly lower quality with more space savings, *recommended*. |
| [granite-3.0-8b-instruct-Q4_0.gguf](https://huggingface.co/bartowski/granite-3.0-8b-instruct-GGUF/blob/main/granite-3.0-8b-instruct-Q4_0.gguf) | Q4_0 | 4.67GB | false | Legacy format, generally not worth using over similarly sized formats |
| [granite-3.0-8b-instruct-Q4_0_8_8.gguf](https://huggingface.co/bartowski/granite-3.0-8b-instruct-GGUF/blob/main/granite-3.0-8b-instruct-Q4_0_8_8.gguf) | Q4_0_8_8 | 4.65GB | false | Optimized for ARM inference. Requires 'sve' support (see link below). *Don't use on Mac or Windows*. |
| [granite-3.0-8b-instruct-Q4_0_4_8.gguf](https://huggingface.co/bartowski/granite-3.0-8b-instruct-GGUF/blob/main/granite-3.0-8b-instruct-Q4_0_4_8.gguf) | Q4_0_4_8 | 4.65GB | false | Optimized for ARM inference. Requires 'i8mm' support (see link below). *Don't use on Mac or Windows*. |
| [granite-3.0-8b-instruct-Q4_0_4_4.gguf](https://huggingface.co/bartowski/granite-3.0-8b-instruct-GGUF/blob/main/granite-3.0-8b-instruct-Q4_0_4_4.gguf) | Q4_0_4_4 | 4.65GB | 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-3.0-8b-instruct-IQ4_XS.gguf](https://huggingface.co/bartowski/granite-3.0-8b-instruct-GGUF/blob/main/granite-3.0-8b-instruct-IQ4_XS.gguf) | IQ4_XS | 4.43GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
| [granite-3.0-8b-instruct-Q3_K_XL.gguf](https://huggingface.co/bartowski/granite-3.0-8b-instruct-GGUF/blob/main/granite-3.0-8b-instruct-Q3_K_XL.gguf) | Q3_K_XL | 4.40GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. |
| [granite-3.0-8b-instruct-Q3_K_L.gguf](https://huggingface.co/bartowski/granite-3.0-8b-instruct-GGUF/blob/main/granite-3.0-8b-instruct-Q3_K_L.gguf) | Q3_K_L | 4.35GB | false | Lower quality but usable, good for low RAM availability. |
| [granite-3.0-8b-instruct-Q3_K_M.gguf](https://huggingface.co/bartowski/granite-3.0-8b-instruct-GGUF/blob/main/granite-3.0-8b-instruct-Q3_K_M.gguf) | Q3_K_M | 4.00GB | false | Low quality. |
| [granite-3.0-8b-instruct-IQ3_M.gguf](https://huggingface.co/bartowski/granite-3.0-8b-instruct-GGUF/blob/main/granite-3.0-8b-instruct-IQ3_M.gguf) | IQ3_M | 3.74GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
| [granite-3.0-8b-instruct-Q3_K_S.gguf](https://huggingface.co/bartowski/granite-3.0-8b-instruct-GGUF/blob/main/granite-3.0-8b-instruct-Q3_K_S.gguf) | Q3_K_S | 3.59GB | false | Low quality, not recommended. |
| [granite-3.0-8b-instruct-IQ3_XS.gguf](https://huggingface.co/bartowski/granite-3.0-8b-instruct-GGUF/blob/main/granite-3.0-8b-instruct-IQ3_XS.gguf) | IQ3_XS | 3.43GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
| [granite-3.0-8b-instruct-Q2_K_L.gguf](https://huggingface.co/bartowski/granite-3.0-8b-instruct-GGUF/blob/main/granite-3.0-8b-instruct-Q2_K_L.gguf) | Q2_K_L | 3.15GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. |
| [granite-3.0-8b-instruct-Q2_K.gguf](https://huggingface.co/bartowski/granite-3.0-8b-instruct-GGUF/blob/main/granite-3.0-8b-instruct-Q2_K.gguf) | Q2_K | 3.10GB | false | Very low quality but surprisingly usable. |
| [granite-3.0-8b-instruct-IQ2_M.gguf](https://huggingface.co/bartowski/granite-3.0-8b-instruct-GGUF/blob/main/granite-3.0-8b-instruct-IQ2_M.gguf) | IQ2_M | 2.84GB | 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.
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-3.0-8b-instruct-GGUF --include "granite-3.0-8b-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-3.0-8b-instruct-GGUF --include "granite-3.0-8b-instruct-Q8_0/*" --local-dir ./
```
You can either specify a new local-dir (granite-3.0-8b-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-3.0-8b-instruct-IQ2_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:7c999c05c7a28caba69fcc6f08fa105efe2b92c1ed3b2e5827f7d81d08bb4979
size 2836822656

3
granite-3.0-8b-instruct-IQ3_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:afd3b78d592de07dbccb42fd1fca4ba0c8ef77aa5629e2336a18891027a05c43
size 3738714336

3
granite-3.0-8b-instruct-IQ3_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c945599ed5c3ff6c567ec41275650fa8032754d1152fd1f281b0d1ebee6a7e79
size 3427991776

3
granite-3.0-8b-instruct-IQ4_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0835231d3d2112b553db32b5998ce89de305c3fcbe80c1ec36dbec95e0b61c21
size 4428071136

3
granite-3.0-8b-instruct-Q2_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d42a81dd088acf7d2c04eca4db423b4be38b3bc7de1c69e85032b13e9c6e5569
size 3103588576

3
granite-3.0-8b-instruct-Q2_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:7518317ed37585c510ec507f3f1ceba240c48edca66d3ea04487a21002356db9
size 3152350336

3
granite-3.0-8b-instruct-Q3_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:859e93f5275a191b9676a320ee122943f953c9868ff86362564472c17b84eca3
size 4349427936

3
granite-3.0-8b-instruct-Q3_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:728c2a0dbfe3ea29d7f2531ef23f699fa0f8e449805ab8844997cf001fda64e3
size 3996582112

3
granite-3.0-8b-instruct-Q3_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:341d1c8b496073b39feaa580b83915bd01ec9442b051db6d6ac3cb2040e65f56
size 3592487136

3
granite-3.0-8b-instruct-Q3_K_XL.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:13b0cb0e5ca26187c2ccd505a2b20cde887745b499763fab89c3748668a54c25
size 4398189696

3
granite-3.0-8b-instruct-Q4_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:711ebf9fa541742fe5b354532c47904566e62524d02fc0552bdf3d6ded3824a8
size 4667277536

3
granite-3.0-8b-instruct-Q4_0_4_4.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:60dac368aaf6b7fafbe3eae84bdadda0b39a364d5654204ffd31bfa53449d305
size 4650893536

3
granite-3.0-8b-instruct-Q4_0_4_8.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:4f0019328b2e07b3719bc76ad7e8c69684bb0c5c951c9de1751ecec558a4d43e
size 4650893536

3
granite-3.0-8b-instruct-Q4_0_8_8.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a6c6ab1b09b0fc15c8c52e19f571743a08f692bf6022998ea847613fe523b849
size 4650893536

3
granite-3.0-8b-instruct-Q4_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ee77985149e464dbb32e9cad4c7a0c086cc8a28473775fbf41ad90e24985c13f
size 4991618176

3
granite-3.0-8b-instruct-Q4_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:360c8e306b9a40c59080e60cb51305867457dfa7e66b99fdffdf5afaab8ba34b
size 4942856416

3
granite-3.0-8b-instruct-Q4_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d7982ee42e8a399e00bec6f345e5fc4d5d2d92a07a081480f7da5e532c6e3331
size 4685758688

3
granite-3.0-8b-instruct-Q5_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:fee8f270c97f1bd2d19a03aeffb1e9653129623fd5a908e2790cf26aaf78eec4
size 5846207616

3
granite-3.0-8b-instruct-Q5_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5010a5aab24a7756a5ce5673777e14c47ad079fe248faeb3031f5f5518129e3a
size 5797445856

3
granite-3.0-8b-instruct-Q5_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:51cb6b891298789f380438d0c46b1957cfe0faaaf0a31117d5176c858dd42799
size 5647040736

3
granite-3.0-8b-instruct-Q6_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d95fda8249c663a8ae220cd15fbb75938bc88c5719bf1ca418820fd448d42137
size 6705447136

3
granite-3.0-8b-instruct-Q6_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ebadc543c9d3a015cd321d8663d758a2fa9d857c958731cf41c1b397e158490b
size 6754208896

3
granite-3.0-8b-instruct-Q8_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b470554539f90a26c0a2d23d7df7398a4f46cff6f5cecfb2778fc110ff6483cd
size 8684244096

3
granite-3.0-8b-instruct-f16.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:42319b6506e40298da43db0a723305c32bb9d9e3a562f0da803259e0b569a5ef
size 16344103008

3
granite-3.0-8b-instruct.imatrix Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:344722d57783fec12a61032bcfff3115795fd273c78faf8419517ed7a58f7355
size 5989458