初始化项目，由ModelHub XC社区提供模型
Model: bartowski/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-GGUF Source: Original Platform
This commit is contained in:
ModelHub XC
60
.gitattributes
vendored
Normal file
60
.gitattributes
vendored
Normal 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
|
||||||
|
Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
||||||
|
Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q6_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
||||||
|
Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
||||||
|
Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q5_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
||||||
|
Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||||
|
Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
||||||
|
Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q4_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
||||||
|
Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||||
|
Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
||||||
|
Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text
|
||||||
|
Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
||||||
|
Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text
|
||||||
|
Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
|
||||||
|
Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
|
||||||
|
Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
||||||
|
Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||||
|
Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||||
|
Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
||||||
|
Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
|
||||||
|
Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text
|
||||||
|
Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
||||||
|
Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
||||||
|
Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||||
|
Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-bf16.gguf filter=lfs diff=lfs merge=lfs -text
|
||||||
|
Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1.imatrix filter=lfs diff=lfs merge=lfs -text
|
||||||
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:4bf2e7148b8e84348464c792c376f28eb0afda7d09c05442b4d9629513c4c789
|
||||||
|
size 3051914720
|
||||||
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:4f5a110e38dd287c1626f5e9f786d9c709357cd056b7a5fa7a2adae12ab9716a
|
||||||
|
size 3896620512
|
||||||
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:3a5921c3a8724cf7e278ad95630e2ea2651177f7c120356f6c9d98b41efe16ae
|
||||||
|
size 3626874336
|
||||||
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:0388f24629f4d14bc04b814c52da1060c67bb19e979ac4579babcf1d1a1d28c3
|
||||||
|
size 3369633248
|
||||||
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:df7cf755a5db249c9dc068d9fafa9e0c9639c3069a94e676ea6187b4b284bd47
|
||||||
|
size 4793624032
|
||||||
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:5c20e614714b7c3a5a8f8685be58d4c256e472903a98f5d769647c896e77eca4
|
||||||
|
size 4561839584
|
||||||
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:9eb3af7bb40c3142381e2e6a0be08dfbe314ad074c376c9c76ca992a2118d171
|
||||||
|
size 3281733088
|
||||||
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:2080c3c8b4f1d3b86f1e00faeb6d9801d1659a54b1facb37ba48286b325d4fa2
|
||||||
|
size 3889477088
|
||||||
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:3c1db649cbaae9588640df2793962c238174e232695b8831dd8562bbd32ed986
|
||||||
|
size 4431394272
|
||||||
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:ca5a75042159e1a9ea25be89140c63e83ea200a4fd5184dd95697752a9a36396
|
||||||
|
size 4124161504
|
||||||
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:ae6ed76418819a01abaccbce2b2948506129992eedaa19eb0a6bcaca68aae684
|
||||||
|
size 3769611744
|
||||||
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:97555fd43fefdd57c7108a7fa16778119a9634f32ebe2b5b4d8d1f826c99925d
|
||||||
|
size 4975932896
|
||||||
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:4a6d73291d60c805ed72097c60c76986a87bd21d36decc3f0459a3b190eadf65
|
||||||
|
size 4787332576
|
||||||
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:d7e50a89de890b8cac53d77a1f44eea90e2184cfb5f2baca806b0c90a1c4e918
|
||||||
|
size 5247755744
|
||||||
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:9e54eb435113fdf77c49b1c6c6dea8c54505c702efa293d7f8db78333547f8cd
|
||||||
|
size 5489669600
|
||||||
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:0bfa61f0f94aa06a58b7e631fe6a51bedef6395135569d049b3c3f96867427be
|
||||||
|
size 5027784160
|
||||||
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:4fc937ac90e727ccda663be086f8389a286be64617052ca3284521d4ee702b3c
|
||||||
|
size 4802012640
|
||||||
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:80b8ad0a523e0357fd31f0c6d51a58ec1e198d0e20a8777c6b42420184c9eca7
|
||||||
|
size 6235207136
|
||||||
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:314f8fa0eae278365cfad3ff4f471e3d45669453c77d3d2297885c2ff2219b7c
|
||||||
|
size 5851112928
|
||||||
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:7f059670395093baefe7b0c3f0a163162b5b21f0736059ab56303b514b95be4b
|
||||||
|
size 5720761824
|
||||||
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:7a933d09201884b893233ad1680d85a2125b3425d95aca61fc8c914cade3ade4
|
||||||
|
size 6725899744
|
||||||
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:1623d12a30e1ea1bc7a8fdc535414635d9ee1ddadcd64169df2064627746aae9
|
||||||
|
size 7027340768
|
||||||
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:72972cf6c3ee8d7ae7ff1b01c8e81f40ae2bd413949f9976e7c59cce0163714b
|
||||||
|
size 8709518816
|
||||||
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:072f8e44dfa4c37e377eed9e1be7d3da27ad3c56a67a59d89cb2babe50daa0c8
|
||||||
|
size 16388043936
|
||||||
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:17adc815c808a497a8312679b88142da6985804928c56d49bba577478ccebb3f
|
||||||
|
size 5316782
|
||||||
172
README.md
Normal file
172
README.md
Normal file
@@ -0,0 +1,172 @@
|
|||||||
|
---
|
||||||
|
quantized_by: bartowski
|
||||||
|
pipeline_tag: text-generation
|
||||||
|
base_model: Goekdeniz-Guelmez/Josiefied-Qwen3-8B-abliterated-v1
|
||||||
|
tags:
|
||||||
|
- chat
|
||||||
|
base_model_relation: quantized
|
||||||
|
---
|
||||||
|
|
||||||
|
## Llamacpp imatrix Quantizations of Josiefied-Qwen3-8B-abliterated-v1 by Goekdeniz-Guelmez
|
||||||
|
|
||||||
|
Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b5270">b5270</a> for quantization.
|
||||||
|
|
||||||
|
Original model: https://huggingface.co/Goekdeniz-Guelmez/Josiefied-Qwen3-8B-abliterated-v1
|
||||||
|
|
||||||
|
All quants made using imatrix option with dataset from [here](https://gist.github.com/bartowski1182/eb213dccb3571f863da82e99418f81e8)
|
||||||
|
|
||||||
|
Run them in [LM Studio](https://lmstudio.ai/)
|
||||||
|
|
||||||
|
Run them directly with [llama.cpp](https://github.com/ggerganov/llama.cpp), or any other llama.cpp based project
|
||||||
|
|
||||||
|
## 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 |
|
||||||
|
| -------- | ---------- | --------- | ----- | ----------- |
|
||||||
|
| [Josiefied-Qwen3-8B-abliterated-v1-bf16.gguf](https://huggingface.co/bartowski/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-GGUF/blob/main/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-bf16.gguf) | bf16 | 16.39GB | false | Full BF16 weights. |
|
||||||
|
| [Josiefied-Qwen3-8B-abliterated-v1-Q8_0.gguf](https://huggingface.co/bartowski/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-GGUF/blob/main/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q8_0.gguf) | Q8_0 | 8.71GB | false | Extremely high quality, generally unneeded but max available quant. |
|
||||||
|
| [Josiefied-Qwen3-8B-abliterated-v1-Q6_K_L.gguf](https://huggingface.co/bartowski/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-GGUF/blob/main/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q6_K_L.gguf) | Q6_K_L | 7.03GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. |
|
||||||
|
| [Josiefied-Qwen3-8B-abliterated-v1-Q6_K.gguf](https://huggingface.co/bartowski/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-GGUF/blob/main/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q6_K.gguf) | Q6_K | 6.73GB | false | Very high quality, near perfect, *recommended*. |
|
||||||
|
| [Josiefied-Qwen3-8B-abliterated-v1-Q5_K_L.gguf](https://huggingface.co/bartowski/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-GGUF/blob/main/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q5_K_L.gguf) | Q5_K_L | 6.24GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. |
|
||||||
|
| [Josiefied-Qwen3-8B-abliterated-v1-Q5_K_M.gguf](https://huggingface.co/bartowski/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-GGUF/blob/main/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q5_K_M.gguf) | Q5_K_M | 5.85GB | false | High quality, *recommended*. |
|
||||||
|
| [Josiefied-Qwen3-8B-abliterated-v1-Q5_K_S.gguf](https://huggingface.co/bartowski/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-GGUF/blob/main/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q5_K_S.gguf) | Q5_K_S | 5.72GB | false | High quality, *recommended*. |
|
||||||
|
| [Josiefied-Qwen3-8B-abliterated-v1-Q4_K_L.gguf](https://huggingface.co/bartowski/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-GGUF/blob/main/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q4_K_L.gguf) | Q4_K_L | 5.49GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. |
|
||||||
|
| [Josiefied-Qwen3-8B-abliterated-v1-Q4_1.gguf](https://huggingface.co/bartowski/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-GGUF/blob/main/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q4_1.gguf) | Q4_1 | 5.25GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. |
|
||||||
|
| [Josiefied-Qwen3-8B-abliterated-v1-Q4_K_M.gguf](https://huggingface.co/bartowski/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-GGUF/blob/main/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q4_K_M.gguf) | Q4_K_M | 5.03GB | false | Good quality, default size for most use cases, *recommended*. |
|
||||||
|
| [Josiefied-Qwen3-8B-abliterated-v1-Q3_K_XL.gguf](https://huggingface.co/bartowski/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-GGUF/blob/main/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q3_K_XL.gguf) | Q3_K_XL | 4.98GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. |
|
||||||
|
| [Josiefied-Qwen3-8B-abliterated-v1-Q4_K_S.gguf](https://huggingface.co/bartowski/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-GGUF/blob/main/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q4_K_S.gguf) | Q4_K_S | 4.80GB | false | Slightly lower quality with more space savings, *recommended*. |
|
||||||
|
| [Josiefied-Qwen3-8B-abliterated-v1-Q4_0.gguf](https://huggingface.co/bartowski/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-GGUF/blob/main/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q4_0.gguf) | Q4_0 | 4.79GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. |
|
||||||
|
| [Josiefied-Qwen3-8B-abliterated-v1-IQ4_NL.gguf](https://huggingface.co/bartowski/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-GGUF/blob/main/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-IQ4_NL.gguf) | IQ4_NL | 4.79GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. |
|
||||||
|
| [Josiefied-Qwen3-8B-abliterated-v1-IQ4_XS.gguf](https://huggingface.co/bartowski/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-GGUF/blob/main/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-IQ4_XS.gguf) | IQ4_XS | 4.56GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
|
||||||
|
| [Josiefied-Qwen3-8B-abliterated-v1-Q3_K_L.gguf](https://huggingface.co/bartowski/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-GGUF/blob/main/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q3_K_L.gguf) | Q3_K_L | 4.43GB | false | Lower quality but usable, good for low RAM availability. |
|
||||||
|
| [Josiefied-Qwen3-8B-abliterated-v1-Q3_K_M.gguf](https://huggingface.co/bartowski/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-GGUF/blob/main/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q3_K_M.gguf) | Q3_K_M | 4.12GB | false | Low quality. |
|
||||||
|
| [Josiefied-Qwen3-8B-abliterated-v1-IQ3_M.gguf](https://huggingface.co/bartowski/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-GGUF/blob/main/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-IQ3_M.gguf) | IQ3_M | 3.90GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
|
||||||
|
| [Josiefied-Qwen3-8B-abliterated-v1-Q2_K_L.gguf](https://huggingface.co/bartowski/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-GGUF/blob/main/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q2_K_L.gguf) | Q2_K_L | 3.89GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. |
|
||||||
|
| [Josiefied-Qwen3-8B-abliterated-v1-Q3_K_S.gguf](https://huggingface.co/bartowski/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-GGUF/blob/main/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q3_K_S.gguf) | Q3_K_S | 3.77GB | false | Low quality, not recommended. |
|
||||||
|
| [Josiefied-Qwen3-8B-abliterated-v1-IQ3_XS.gguf](https://huggingface.co/bartowski/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-GGUF/blob/main/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-IQ3_XS.gguf) | IQ3_XS | 3.63GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
|
||||||
|
| [Josiefied-Qwen3-8B-abliterated-v1-IQ3_XXS.gguf](https://huggingface.co/bartowski/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-GGUF/blob/main/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-IQ3_XXS.gguf) | IQ3_XXS | 3.37GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. |
|
||||||
|
| [Josiefied-Qwen3-8B-abliterated-v1-Q2_K.gguf](https://huggingface.co/bartowski/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-GGUF/blob/main/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q2_K.gguf) | Q2_K | 3.28GB | false | Very low quality but surprisingly usable. |
|
||||||
|
| [Josiefied-Qwen3-8B-abliterated-v1-IQ2_M.gguf](https://huggingface.co/bartowski/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-GGUF/blob/main/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-IQ2_M.gguf) | IQ2_M | 3.05GB | 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.
|
||||||
|
|
||||||
|
## Downloading using huggingface-cli
|
||||||
|
|
||||||
|
<details>
|
||||||
|
<summary>Click to view download instructions</summary>
|
||||||
|
|
||||||
|
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/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-GGUF --include "Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-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/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-GGUF --include "Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q8_0/*" --local-dir ./
|
||||||
|
```
|
||||||
|
|
||||||
|
You can either specify a new local-dir (Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-Q8_0) or download them all in place (./)
|
||||||
|
|
||||||
|
</details>
|
||||||
|
|
||||||
|
## ARM/AVX information
|
||||||
|
|
||||||
|
Previously, you would download Q4_0_4_4/4_8/8_8, and these would have their weights interleaved in memory in order to improve performance on ARM and AVX machines by loading up more data in one pass.
|
||||||
|
|
||||||
|
Now, however, there is something called "online repacking" for weights. details in [this PR](https://github.com/ggerganov/llama.cpp/pull/9921). If you use Q4_0 and your hardware would benefit from repacking weights, it will do it automatically on the fly.
|
||||||
|
|
||||||
|
As of llama.cpp build [b4282](https://github.com/ggerganov/llama.cpp/releases/tag/b4282) you will not be able to run the Q4_0_X_X files and will instead need to use Q4_0.
|
||||||
|
|
||||||
|
Additionally, if you want to get slightly better quality for , you can use IQ4_NL thanks to [this PR](https://github.com/ggerganov/llama.cpp/pull/10541) which will also repack the weights for ARM, though only the 4_4 for now. The loading time may be slower but it will result in an overall speed incrase.
|
||||||
|
|
||||||
|
<details>
|
||||||
|
<summary>Click to view Q4_0_X_X information (deprecated</summary>
|
||||||
|
|
||||||
|
I'm keeping this section to show the potential theoretical uplift in performance from using the Q4_0 with online repacking.
|
||||||
|
|
||||||
|
<details>
|
||||||
|
<summary>Click to view benchmarks on an AVX2 system (EPYC7702)</summary>
|
||||||
|
|
||||||
|
| model | size | params | backend | threads | test | t/s | % (vs Q4_0) |
|
||||||
|
| ------------------------------ | ---------: | ---------: | ---------- | ------: | ------------: | -------------------: |-------------: |
|
||||||
|
| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | pp512 | 204.03 ± 1.03 | 100% |
|
||||||
|
| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | pp1024 | 282.92 ± 0.19 | 100% |
|
||||||
|
| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | pp2048 | 259.49 ± 0.44 | 100% |
|
||||||
|
| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | tg128 | 39.12 ± 0.27 | 100% |
|
||||||
|
| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | tg256 | 39.31 ± 0.69 | 100% |
|
||||||
|
| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | tg512 | 40.52 ± 0.03 | 100% |
|
||||||
|
| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | pp512 | 301.02 ± 1.74 | 147% |
|
||||||
|
| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | pp1024 | 287.23 ± 0.20 | 101% |
|
||||||
|
| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | pp2048 | 262.77 ± 1.81 | 101% |
|
||||||
|
| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | tg128 | 18.80 ± 0.99 | 48% |
|
||||||
|
| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | tg256 | 24.46 ± 3.04 | 83% |
|
||||||
|
| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | tg512 | 36.32 ± 3.59 | 90% |
|
||||||
|
| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | pp512 | 271.71 ± 3.53 | 133% |
|
||||||
|
| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | pp1024 | 279.86 ± 45.63 | 100% |
|
||||||
|
| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | pp2048 | 320.77 ± 5.00 | 124% |
|
||||||
|
| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | tg128 | 43.51 ± 0.05 | 111% |
|
||||||
|
| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | tg256 | 43.35 ± 0.09 | 110% |
|
||||||
|
| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | tg512 | 42.60 ± 0.31 | 105% |
|
||||||
|
|
||||||
|
Q4_0_8_8 offers a nice bump to prompt processing and a small bump to text generation
|
||||||
|
|
||||||
|
</details>
|
||||||
|
|
||||||
|
</details>
|
||||||
|
|
||||||
|
## Which file should I choose?
|
||||||
|
|
||||||
|
<details>
|
||||||
|
<summary>Click here for details</summary>
|
||||||
|
|
||||||
|
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, but will be slower than their K-quant equivalent, so speed vs performance is a tradeoff you'll have to decide.
|
||||||
|
|
||||||
|
</details>
|
||||||
|
|
||||||
|
## 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.
|
||||||
|
|
||||||
|
Thank you to LM Studio for sponsoring my work.
|
||||||
|
|
||||||
|
Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski
|
||||||
Reference in New Issue
Block a user