bartowski/Replete-LLM-V2.5-Qwen-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/Replete-LLM-V2.5-Qwen-3b-GGUF
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-09-13 09:22:12 +08:00
commit fa33c36a4e
22 changed files with 232 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

54
.gitattributes vendored Normal file
View File

@@ -0,0 +1,54 @@
*.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
Replete-LLM-V2.5-Qwen-3b-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
Replete-LLM-V2.5-Qwen-3b-Q6_K_L.gguf filter=lfs diff=lfs merge=lfs -text
Replete-LLM-V2.5-Qwen-3b-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
Replete-LLM-V2.5-Qwen-3b-Q5_K_L.gguf filter=lfs diff=lfs merge=lfs -text
Replete-LLM-V2.5-Qwen-3b-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
Replete-LLM-V2.5-Qwen-3b-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
Replete-LLM-V2.5-Qwen-3b-Q4_K_L.gguf filter=lfs diff=lfs merge=lfs -text
Replete-LLM-V2.5-Qwen-3b-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
Replete-LLM-V2.5-Qwen-3b-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
Replete-LLM-V2.5-Qwen-3b-Q4_0_8_8.gguf filter=lfs diff=lfs merge=lfs -text
Replete-LLM-V2.5-Qwen-3b-Q4_0_4_8.gguf filter=lfs diff=lfs merge=lfs -text
Replete-LLM-V2.5-Qwen-3b-Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text
Replete-LLM-V2.5-Qwen-3b-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
Replete-LLM-V2.5-Qwen-3b-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
Replete-LLM-V2.5-Qwen-3b-Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
Replete-LLM-V2.5-Qwen-3b-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
Replete-LLM-V2.5-Qwen-3b-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
Replete-LLM-V2.5-Qwen-3b-f16.gguf filter=lfs diff=lfs merge=lfs -text
Replete-LLM-V2.5-Qwen-3b.imatrix filter=lfs diff=lfs merge=lfs -text

120
README.md Normal file
View File

@@ -0,0 +1,120 @@
---
base_model: rombodawg/Rombos-LLM-V2.5-Qwen-3b
library_name: transformers
license: apache-2.0
pipeline_tag: text-generation
quantized_by: bartowski
---
## Llamacpp imatrix Quantizations of Rombos-LLM-V2.5-Qwen-3b
Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b3825">b3825</a> for quantization.
Original model: https://huggingface.co/rombodawg/Rombos-LLM-V2.5-Qwen-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
```
<|im_start|>system
{system_prompt}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
```
## Download a file (not the whole branch) from below:
| Filename | Quant type | File Size | Split | Description |
| -------- | ---------- | --------- | ----- | ----------- |
| [Replete-LLM-V2.5-Qwen-3b-f16.gguf](https://huggingface.co/bartowski/Replete-LLM-V2.5-Qwen-3b-GGUF/blob/main/Replete-LLM-V2.5-Qwen-3b-f16.gguf) | f16 | 6.80GB | false | Full F16 weights. |
| [Replete-LLM-V2.5-Qwen-3b-Q8_0.gguf](https://huggingface.co/bartowski/Replete-LLM-V2.5-Qwen-3b-GGUF/blob/main/Replete-LLM-V2.5-Qwen-3b-Q8_0.gguf) | Q8_0 | 3.62GB | false | Extremely high quality, generally unneeded but max available quant. |
| [Replete-LLM-V2.5-Qwen-3b-Q6_K_L.gguf](https://huggingface.co/bartowski/Replete-LLM-V2.5-Qwen-3b-GGUF/blob/main/Replete-LLM-V2.5-Qwen-3b-Q6_K_L.gguf) | Q6_K_L | 2.94GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. |
| [Replete-LLM-V2.5-Qwen-3b-Q6_K.gguf](https://huggingface.co/bartowski/Replete-LLM-V2.5-Qwen-3b-GGUF/blob/main/Replete-LLM-V2.5-Qwen-3b-Q6_K.gguf) | Q6_K | 2.79GB | false | Very high quality, near perfect, *recommended*. |
| [Replete-LLM-V2.5-Qwen-3b-Q5_K_L.gguf](https://huggingface.co/bartowski/Replete-LLM-V2.5-Qwen-3b-GGUF/blob/main/Replete-LLM-V2.5-Qwen-3b-Q5_K_L.gguf) | Q5_K_L | 2.63GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. |
| [Replete-LLM-V2.5-Qwen-3b-Q5_K_M.gguf](https://huggingface.co/bartowski/Replete-LLM-V2.5-Qwen-3b-GGUF/blob/main/Replete-LLM-V2.5-Qwen-3b-Q5_K_M.gguf) | Q5_K_M | 2.44GB | false | High quality, *recommended*. |
| [Replete-LLM-V2.5-Qwen-3b-Q5_K_S.gguf](https://huggingface.co/bartowski/Replete-LLM-V2.5-Qwen-3b-GGUF/blob/main/Replete-LLM-V2.5-Qwen-3b-Q5_K_S.gguf) | Q5_K_S | 2.38GB | false | High quality, *recommended*. |
| [Replete-LLM-V2.5-Qwen-3b-Q4_K_L.gguf](https://huggingface.co/bartowski/Replete-LLM-V2.5-Qwen-3b-GGUF/blob/main/Replete-LLM-V2.5-Qwen-3b-Q4_K_L.gguf) | Q4_K_L | 2.34GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. |
| [Replete-LLM-V2.5-Qwen-3b-Q3_K_XL.gguf](https://huggingface.co/bartowski/Replete-LLM-V2.5-Qwen-3b-GGUF/blob/main/Replete-LLM-V2.5-Qwen-3b-Q3_K_XL.gguf) | Q3_K_XL | 2.11GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. |
| [Replete-LLM-V2.5-Qwen-3b-Q4_K_M.gguf](https://huggingface.co/bartowski/Replete-LLM-V2.5-Qwen-3b-GGUF/blob/main/Replete-LLM-V2.5-Qwen-3b-Q4_K_M.gguf) | Q4_K_M | 2.10GB | false | Good quality, default size for must use cases, *recommended*. |
| [Replete-LLM-V2.5-Qwen-3b-Q4_K_S.gguf](https://huggingface.co/bartowski/Replete-LLM-V2.5-Qwen-3b-GGUF/blob/main/Replete-LLM-V2.5-Qwen-3b-Q4_K_S.gguf) | Q4_K_S | 2.01GB | false | Slightly lower quality with more space savings, *recommended*. |
| [Replete-LLM-V2.5-Qwen-3b-Q4_0_8_8.gguf](https://huggingface.co/bartowski/Replete-LLM-V2.5-Qwen-3b-GGUF/blob/main/Replete-LLM-V2.5-Qwen-3b-Q4_0_8_8.gguf) | Q4_0_8_8 | 2.00GB | false | Optimized for ARM inference. Requires 'sve' support (see link below). |
| [Replete-LLM-V2.5-Qwen-3b-Q4_0_4_8.gguf](https://huggingface.co/bartowski/Replete-LLM-V2.5-Qwen-3b-GGUF/blob/main/Replete-LLM-V2.5-Qwen-3b-Q4_0_4_8.gguf) | Q4_0_4_8 | 2.00GB | false | Optimized for ARM inference. Requires 'i8mm' support (see link below). |
| [Replete-LLM-V2.5-Qwen-3b-Q4_0_4_4.gguf](https://huggingface.co/bartowski/Replete-LLM-V2.5-Qwen-3b-GGUF/blob/main/Replete-LLM-V2.5-Qwen-3b-Q4_0_4_4.gguf) | Q4_0_4_4 | 2.00GB | false | Optimized for ARM inference. Should work well on all ARM chips, pick this if you're unsure. |
| [Replete-LLM-V2.5-Qwen-3b-Q4_0.gguf](https://huggingface.co/bartowski/Replete-LLM-V2.5-Qwen-3b-GGUF/blob/main/Replete-LLM-V2.5-Qwen-3b-Q4_0.gguf) | Q4_0 | 2.00GB | false | Legacy format, generally not worth using over similarly sized formats |
| [Replete-LLM-V2.5-Qwen-3b-IQ4_XS.gguf](https://huggingface.co/bartowski/Replete-LLM-V2.5-Qwen-3b-GGUF/blob/main/Replete-LLM-V2.5-Qwen-3b-IQ4_XS.gguf) | IQ4_XS | 1.90GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
| [Replete-LLM-V2.5-Qwen-3b-Q3_K_L.gguf](https://huggingface.co/bartowski/Replete-LLM-V2.5-Qwen-3b-GGUF/blob/main/Replete-LLM-V2.5-Qwen-3b-Q3_K_L.gguf) | Q3_K_L | 1.84GB | false | Lower quality but usable, good for low RAM availability. |
| [Replete-LLM-V2.5-Qwen-3b-IQ3_M.gguf](https://huggingface.co/bartowski/Replete-LLM-V2.5-Qwen-3b-GGUF/blob/main/Replete-LLM-V2.5-Qwen-3b-IQ3_M.gguf) | IQ3_M | 1.62GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
## 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/Replete-LLM-V2.5-Qwen-3b-GGUF --include "Replete-LLM-V2.5-Qwen-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/Replete-LLM-V2.5-Qwen-3b-GGUF --include "Replete-LLM-V2.5-Qwen-3b-Q8_0/*" --local-dir ./
```
You can either specify a new local-dir (Replete-LLM-V2.5-Qwen-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

3
Replete-LLM-V2.5-Qwen-3b-IQ3_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:6d2b027e72c44df903a323e4097c76d43367dc138b9503c63dcf35a3052dc24e
size 1622598624

3
Replete-LLM-V2.5-Qwen-3b-IQ4_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:08ec2f3f371eb7f77e85f1df3b5d6d36459842310b75b84fa01f8dc6ea046eda
size 1904401376

3
Replete-LLM-V2.5-Qwen-3b-Q3_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:af26e88f1fcb26b73a758fbcce945d1ac4b471e25625efa99fe76a9b1c1c7fee
size 1841095648

3
Replete-LLM-V2.5-Qwen-3b-Q3_K_XL.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:33574c79324fcb7d476644359f6d5d1de727460afd086ed04d088cc5cb80c25e
size 2113364960

3
Replete-LLM-V2.5-Qwen-3b-Q4_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0db82ac5c694852e9e91d881e3802bfbc3c48e304607b45704c96a6271a93f0b
size 2003516384

3
Replete-LLM-V2.5-Qwen-3b-Q4_0_4_4.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c766948b6bff33337112e4170c7426b18c62819c3d60354753f6c56c8352fffe
size 1997880288

3
Replete-LLM-V2.5-Qwen-3b-Q4_0_4_8.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:356ed36f6bb2740dbe6f3b3a905188dbe57dad2a7192ae5a2d9819acdd0875f2
size 1997880288

3
Replete-LLM-V2.5-Qwen-3b-Q4_0_8_8.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:7710e8b1ca2ef5255aea6116ae30cfb17f7bce0214df3dc63042a56cde4ec5d5
size 1997880288

3
Replete-LLM-V2.5-Qwen-3b-Q4_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:7ed0fc7d48e865548cac66d6cb000bddb6400876fa530e2ca17c7bb30b4a3536
size 2335876064

3
Replete-LLM-V2.5-Qwen-3b-Q4_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:561f4f40c1d152c6280efe450419432fcb28d91471f2c7ec6647c510b962b519
size 2104933344

3
Replete-LLM-V2.5-Qwen-3b-Q4_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:7077f25fd416ff6fa705a1f0d038214d71e59aa17976152ee5b9e2bd97a6a3c5
size 2009414624

3
Replete-LLM-V2.5-Qwen-3b-Q5_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:42de9b9f1e3091e2436cdcbb5ff16fa7051c933790a8623d2386e89c3ab6344e
size 2630788064

3
Replete-LLM-V2.5-Qwen-3b-Q5_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1cd7c0b589a4a88127869e2b997c5162b24bd88ce88beb03c2a3119386da201a
size 2438740960

3
Replete-LLM-V2.5-Qwen-3b-Q5_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:30fbbff2cd3479ac2c60cac5b0db78d32fd944c77039353b566aecc236f512db
size 2383592416

3
Replete-LLM-V2.5-Qwen-3b-Q6_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f1f843a5b1099f0cb37740ca2128f8bdc8f3d7bf7f8b44588f8fbaa4ce6a0186
size 2793411552

3
Replete-LLM-V2.5-Qwen-3b-Q6_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9eb52fe67fc06599f745feec36d57215ba69e93b1b02cdc7daba3afd89aaa433
size 2944132064

3
Replete-LLM-V2.5-Qwen-3b-Q8_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:80d07ef30a3c07f1108636a9e83439ef80f74494148a7d13ee9e5c4e964b8f0a
size 3616089056

3
Replete-LLM-V2.5-Qwen-3b-f16.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:10093c60a56fcc6bc6d4b39359986e94e605c5439c1d4245ee328be2dfe83360
size 6800646848

3
Replete-LLM-V2.5-Qwen-3b.imatrix Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2781fbcbe53d1d8ee2f948f395e3f34a5b4dc2a58744ad2f75ed1afee9a34c45
size 3362990

1
configuration.json Normal file
View File

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