bartowski/magnaraxy-9b-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/magnaraxy-9b-GGUF
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-08-25 01:45:12 +08:00
commit f2d5733f42
28 changed files with 255 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
magnaraxy-9b-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
magnaraxy-9b-Q6_K_L.gguf filter=lfs diff=lfs merge=lfs -text
magnaraxy-9b-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
magnaraxy-9b-Q5_K_L.gguf filter=lfs diff=lfs merge=lfs -text
magnaraxy-9b-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
magnaraxy-9b-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
magnaraxy-9b-Q4_K_L.gguf filter=lfs diff=lfs merge=lfs -text
magnaraxy-9b-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
magnaraxy-9b-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
magnaraxy-9b-Q4_0_8_8.gguf filter=lfs diff=lfs merge=lfs -text
magnaraxy-9b-Q4_0_4_8.gguf filter=lfs diff=lfs merge=lfs -text
magnaraxy-9b-Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text
magnaraxy-9b-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
magnaraxy-9b-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
magnaraxy-9b-Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
magnaraxy-9b-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
magnaraxy-9b-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
magnaraxy-9b-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
magnaraxy-9b-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
magnaraxy-9b-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
magnaraxy-9b-Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text
magnaraxy-9b-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
magnaraxy-9b-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text
magnaraxy-9b-f16.gguf filter=lfs diff=lfs merge=lfs -text
magnaraxy-9b.imatrix filter=lfs diff=lfs merge=lfs -text

119
README.md Normal file
View File

@@ -0,0 +1,119 @@
---
base_model: lodrick-the-lafted/magnaraxy-9b
license: apache-2.0
pipeline_tag: text-generation
quantized_by: bartowski
---
## Llamacpp imatrix Quantizations of magnaraxy-9b
Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b3658">b3658</a> for quantization.
Original model: https://huggingface.co/lodrick-the-lafted/magnaraxy-9b
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 |
| -------- | ---------- | --------- | ----- | ----------- |
| [magnaraxy-9b-f16.gguf](https://huggingface.co/bartowski/magnaraxy-9b-GGUF/blob/main/magnaraxy-9b-f16.gguf) | f16 | 18.49GB | false | Full F16 weights. |
| [magnaraxy-9b-Q8_0.gguf](https://huggingface.co/bartowski/magnaraxy-9b-GGUF/blob/main/magnaraxy-9b-Q8_0.gguf) | Q8_0 | 9.83GB | false | Extremely high quality, generally unneeded but max available quant. |
| [magnaraxy-9b-Q6_K_L.gguf](https://huggingface.co/bartowski/magnaraxy-9b-GGUF/blob/main/magnaraxy-9b-Q6_K_L.gguf) | Q6_K_L | 7.81GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. |
| [magnaraxy-9b-Q6_K.gguf](https://huggingface.co/bartowski/magnaraxy-9b-GGUF/blob/main/magnaraxy-9b-Q6_K.gguf) | Q6_K | 7.59GB | false | Very high quality, near perfect, *recommended*. |
| [magnaraxy-9b-Q5_K_L.gguf](https://huggingface.co/bartowski/magnaraxy-9b-GGUF/blob/main/magnaraxy-9b-Q5_K_L.gguf) | Q5_K_L | 6.87GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. |
| [magnaraxy-9b-Q5_K_M.gguf](https://huggingface.co/bartowski/magnaraxy-9b-GGUF/blob/main/magnaraxy-9b-Q5_K_M.gguf) | Q5_K_M | 6.65GB | false | High quality, *recommended*. |
| [magnaraxy-9b-Q5_K_S.gguf](https://huggingface.co/bartowski/magnaraxy-9b-GGUF/blob/main/magnaraxy-9b-Q5_K_S.gguf) | Q5_K_S | 6.48GB | false | High quality, *recommended*. |
| [magnaraxy-9b-Q4_K_L.gguf](https://huggingface.co/bartowski/magnaraxy-9b-GGUF/blob/main/magnaraxy-9b-Q4_K_L.gguf) | Q4_K_L | 5.98GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. |
| [magnaraxy-9b-Q4_K_M.gguf](https://huggingface.co/bartowski/magnaraxy-9b-GGUF/blob/main/magnaraxy-9b-Q4_K_M.gguf) | Q4_K_M | 5.76GB | false | Good quality, default size for must use cases, *recommended*. |
| [magnaraxy-9b-Q4_K_S.gguf](https://huggingface.co/bartowski/magnaraxy-9b-GGUF/blob/main/magnaraxy-9b-Q4_K_S.gguf) | Q4_K_S | 5.48GB | false | Slightly lower quality with more space savings, *recommended*. |
| [magnaraxy-9b-Q4_0.gguf](https://huggingface.co/bartowski/magnaraxy-9b-GGUF/blob/main/magnaraxy-9b-Q4_0.gguf) | Q4_0 | 5.46GB | false | Legacy format, generally not worth using over similarly sized formats |
| [magnaraxy-9b-Q4_0_8_8.gguf](https://huggingface.co/bartowski/magnaraxy-9b-GGUF/blob/main/magnaraxy-9b-Q4_0_8_8.gguf) | Q4_0_8_8 | 5.44GB | false | Optimized for ARM inference. Requires 'sve' support (see link below). |
| [magnaraxy-9b-Q4_0_4_8.gguf](https://huggingface.co/bartowski/magnaraxy-9b-GGUF/blob/main/magnaraxy-9b-Q4_0_4_8.gguf) | Q4_0_4_8 | 5.44GB | false | Optimized for ARM inference. Requires 'i8mm' support (see link below). |
| [magnaraxy-9b-Q4_0_4_4.gguf](https://huggingface.co/bartowski/magnaraxy-9b-GGUF/blob/main/magnaraxy-9b-Q4_0_4_4.gguf) | Q4_0_4_4 | 5.44GB | false | Optimized for ARM inference. Should work well on all ARM chips, pick this if you're unsure. |
| [magnaraxy-9b-Q3_K_XL.gguf](https://huggingface.co/bartowski/magnaraxy-9b-GGUF/blob/main/magnaraxy-9b-Q3_K_XL.gguf) | Q3_K_XL | 5.35GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. |
| [magnaraxy-9b-IQ4_XS.gguf](https://huggingface.co/bartowski/magnaraxy-9b-GGUF/blob/main/magnaraxy-9b-IQ4_XS.gguf) | IQ4_XS | 5.18GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
| [magnaraxy-9b-Q3_K_L.gguf](https://huggingface.co/bartowski/magnaraxy-9b-GGUF/blob/main/magnaraxy-9b-Q3_K_L.gguf) | Q3_K_L | 5.13GB | false | Lower quality but usable, good for low RAM availability. |
| [magnaraxy-9b-Q3_K_M.gguf](https://huggingface.co/bartowski/magnaraxy-9b-GGUF/blob/main/magnaraxy-9b-Q3_K_M.gguf) | Q3_K_M | 4.76GB | false | Low quality. |
| [magnaraxy-9b-IQ3_M.gguf](https://huggingface.co/bartowski/magnaraxy-9b-GGUF/blob/main/magnaraxy-9b-IQ3_M.gguf) | IQ3_M | 4.49GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
| [magnaraxy-9b-Q3_K_S.gguf](https://huggingface.co/bartowski/magnaraxy-9b-GGUF/blob/main/magnaraxy-9b-Q3_K_S.gguf) | Q3_K_S | 4.34GB | false | Low quality, not recommended. |
| [magnaraxy-9b-IQ3_XS.gguf](https://huggingface.co/bartowski/magnaraxy-9b-GGUF/blob/main/magnaraxy-9b-IQ3_XS.gguf) | IQ3_XS | 4.14GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
| [magnaraxy-9b-Q2_K_L.gguf](https://huggingface.co/bartowski/magnaraxy-9b-GGUF/blob/main/magnaraxy-9b-Q2_K_L.gguf) | Q2_K_L | 4.03GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. |
| [magnaraxy-9b-Q2_K.gguf](https://huggingface.co/bartowski/magnaraxy-9b-GGUF/blob/main/magnaraxy-9b-Q2_K.gguf) | Q2_K | 3.81GB | false | Very low quality but surprisingly usable. |
| [magnaraxy-9b-IQ2_M.gguf](https://huggingface.co/bartowski/magnaraxy-9b-GGUF/blob/main/magnaraxy-9b-IQ2_M.gguf) | IQ2_M | 3.43GB | 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/magnaraxy-9b-GGUF --include "magnaraxy-9b-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/magnaraxy-9b-GGUF --include "magnaraxy-9b-Q8_0/*" --local-dir ./
```
You can either specify a new local-dir (magnaraxy-9b-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
magnaraxy-9b-IQ2_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3c38ee73441a963eb8048b32b2ab38c115d7009763e330967700dcc217f691de
size 3434668512

3
magnaraxy-9b-IQ3_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:67944e425685d7e58e363e314fcd8bf41028a7bc8434777b9a5b0cbfdb5da1dc
size 4494615008

3
magnaraxy-9b-IQ3_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:85cdd12d911386fa2fd824e5f85f083efe813e06cc9a7f18b12478c4bb15616e
size 4144988640

3
magnaraxy-9b-IQ4_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3e96dede453a30db503ba79fabc07abe1f6a1b54b916f58074da97591bd6fe42
size 5183029728

3
magnaraxy-9b-Q2_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:106aefacb0eb7ec7dc4fdcce7a4da49413ccc35ee24f014d4dfe34474ab0a5f9
size 3805397472

3
magnaraxy-9b-Q2_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f600647168becac6a42c19ba64f08a5e9720913acfc6e34c3ad7b1bcd2f8007d
size 4027605472

3
magnaraxy-9b-Q3_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f25232b61e41263132f3957fea9e29e55f541a321a39b1bcb1e225be39d53813
size 5132452320

3
magnaraxy-9b-Q3_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:25aabb0f0f21c6a852d7c9cd05f3f0f914ec1caf51487a2a213800df04cdad57
size 4761780704

3
magnaraxy-9b-Q3_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1165f403b86383212f2c817dbff14fa3fa10ca18cb6c92c588c6a99806ed574f
size 4337664480

3
magnaraxy-9b-Q3_K_XL.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:184fbd9574e96042aab6ed0671b1c0ef11f353e64daffdb2cab73c059eb754c6
size 5354660320

3
magnaraxy-9b-Q4_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:34e78b8d91975b6b803a537b212c26d6b915a924ed07a631bd6f8db08c0cbf38
size 5459198432

3
magnaraxy-9b-Q4_0_4_4.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2d22ef4dfcbc6f0ebed9835eff5ed407336dca0b443754ef73275d75de44f3e3
size 5443142112

3
magnaraxy-9b-Q4_0_4_8.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:468c2138f5bf147c98299e92c707e97e11feec414a5531f4d061065692d3cc1f
size 5443142112

3
magnaraxy-9b-Q4_0_8_8.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a5a0c9542a167116a0291a9baddf4f39c4e33047a13440fee86c719a2dd078bb
size 5443142112

3
magnaraxy-9b-Q4_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b4d461a99e636054acc2645ceef892055bf4687ed4f39525555c73889b9b405e
size 5983265248

3
magnaraxy-9b-Q4_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:083a5363f3591ef9ccdc625678191fa3b1075ea5b5cf326c975c392da3ca7e02
size 5761057248

3
magnaraxy-9b-Q4_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5ba7a1c6a1e9186f09b66da7ccbf75045b72ae656518ea67afa0cfe001fe7ab6
size 5478924768

3
magnaraxy-9b-Q5_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:fcfc264af3a0c447ce426a96cfedf5bec8f12c87a26b449a2372cb55d2182cff
size 6869574112

3
magnaraxy-9b-Q5_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c18512becdb129c1247c88c033eb3dd276d1de208a32f6f8ebf1c68ab93bcb72
size 6647366112

3
magnaraxy-9b-Q5_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2996fdfa152a31cebffc438f6664cc6e23ba998fce3e8e38275307975152d9e6
size 6483591648

3
magnaraxy-9b-Q6_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:fef21144d9801cdd619b1c420d13dbb955e87e4592114ac5acc21e1a512cf9ce
size 7589069280

3
magnaraxy-9b-Q6_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:56966ad9bda143837567d1fce8f26e015e59ad4078e3197b682cdebfbaa6ab00
size 7811277280

3
magnaraxy-9b-Q8_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:52f502b5fffb2cc0aacd6871bfd78f102d7f678503da5be588daeabe215f3f87
size 9827148256

3
magnaraxy-9b-f16.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a77b9d7e574c0d4553f73cf1d680abc40125f62f704f5560789c7279cda3556b
size 18490679520

3
magnaraxy-9b.imatrix Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c4337b61bafeebd8ce2f8689549c9d821020ae7e8912ca2ddfde87b942536211
size 6116900