bartowski/Qwen2.5-14B_Uncencored-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/Qwen2.5-14B_Uncencored-GGUF
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-07-18 03:29:07 +08:00
commit 2d4b31d45f
29 changed files with 270 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

61
.gitattributes vendored Normal file
View File

@@ -0,0 +1,61 @@
*.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
Qwen2.5-14B_Uncencored-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
Qwen2.5-14B_Uncencored-Q6_K_L.gguf filter=lfs diff=lfs merge=lfs -text
Qwen2.5-14B_Uncencored-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
Qwen2.5-14B_Uncencored-Q5_K_L.gguf filter=lfs diff=lfs merge=lfs -text
Qwen2.5-14B_Uncencored-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
Qwen2.5-14B_Uncencored-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
Qwen2.5-14B_Uncencored-Q4_K_L.gguf filter=lfs diff=lfs merge=lfs -text
Qwen2.5-14B_Uncencored-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
Qwen2.5-14B_Uncencored-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
Qwen2.5-14B_Uncencored-Q4_0_8_8.gguf filter=lfs diff=lfs merge=lfs -text
Qwen2.5-14B_Uncencored-Q4_0_4_8.gguf filter=lfs diff=lfs merge=lfs -text
Qwen2.5-14B_Uncencored-Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text
Qwen2.5-14B_Uncencored-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
Qwen2.5-14B_Uncencored-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
Qwen2.5-14B_Uncencored-Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
Qwen2.5-14B_Uncencored-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
Qwen2.5-14B_Uncencored-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
Qwen2.5-14B_Uncencored-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
Qwen2.5-14B_Uncencored-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
Qwen2.5-14B_Uncencored-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
Qwen2.5-14B_Uncencored-Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text
Qwen2.5-14B_Uncencored-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
Qwen2.5-14B_Uncencored-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text
Qwen2.5-14B_Uncencored-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text
Qwen2.5-14B_Uncencored-f16.gguf filter=lfs diff=lfs merge=lfs -text
Qwen2.5-14B_Uncencored.imatrix filter=lfs diff=lfs merge=lfs -text

3
Qwen2.5-14B_Uncencored-IQ2_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:6b20dd766a87483b9fc753b1ad489ff58d9e33359765baeea1e58940766c826a
size 5356146400

3
Qwen2.5-14B_Uncencored-IQ2_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:95605fb02b08be0ebf3a62e260a3e4ccb0b03f03e66c64e07ef509f44a906cb3
size 5003726560

3
Qwen2.5-14B_Uncencored-IQ3_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:08467d80ea47fda4f452efa5defd006ca6c1aff5c37d5b58d1f388bb8f9bf784
size 6916538080

3
Qwen2.5-14B_Uncencored-IQ3_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:40166ff0dad2264c3b2bde17d0b1e0624578a2cf613206f082c3ccd09cf768e3
size 6383361760

3
Qwen2.5-14B_Uncencored-IQ4_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:bfb6df9fb673a2e4bc3b2f2ca646f49a3250e599a636764c5138b89ef4171d51
size 8119840480

3
Qwen2.5-14B_Uncencored-Q2_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1d2b2fda200cb92e81611c72b2c2d8ee370d82ba674d6575ee13b4ca9ba87ffb
size 5770497760

3
Qwen2.5-14B_Uncencored-Q2_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:54d4d71645f1a541741a849767292ac371f1c651485cae5307f27ed7455d4047
size 6530817760

3
Qwen2.5-14B_Uncencored-Q3_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:4e718f956c742f488a233aa95a29201176b5a01199319ed1ac4731d7ba6449bd
size 7924768480

3
Qwen2.5-14B_Uncencored-Q3_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9118a7f77458f7b324aaa82ebe50a2e23badde11d346670334aae98e1a0c1d3e
size 7339204320

3
Qwen2.5-14B_Uncencored-Q3_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0f7f0117ecc0d95ea612481b605322cb9d9cfc43e60800200e7ee61a97e84bcf
size 6659596000

3
Qwen2.5-14B_Uncencored-Q3_K_XL.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:52dddb80692513cc1df8b078bf7ce07bf6af4b07737fec4eb93927d88b553087
size 8606015200

3
Qwen2.5-14B_Uncencored-Q4_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e557101ca79a4395f0e4ba3bd6eef52efb84653f60b5ccf42b7fb268d4361b23
size 8544268000

3
Qwen2.5-14B_Uncencored-Q4_0_4_4.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e85571508960710a7885f0d0a72666d6ac4f503ed2afca10d54a4158e24e49f8
size 8517725920

3
Qwen2.5-14B_Uncencored-Q4_0_4_8.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:428393f523aa1b4887e3d89ed4ce2d1fab37a965f3a3a8ab619faaaf6d285d9d
size 8517725920

3
Qwen2.5-14B_Uncencored-Q4_0_8_8.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:55931449cccc4b6aea4ba6c32741c602a74cdaeeaf7439237bf82083bd8d42cb
size 8517725920

3
Qwen2.5-14B_Uncencored-Q4_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:46c43b000481f7e0a80685f827ad3f4d8e8b95eece6286084cbaf4703ef8291d
size 9565953760

3
Qwen2.5-14B_Uncencored-Q4_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:066b9341b67e0fd0956de3576a3b7988574a5b9a0028aef2b9c8edeadd6dbbd1
size 8988110560

3
Qwen2.5-14B_Uncencored-Q4_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:23b6458478cf441b065174de9eb9b47a6cadd00c9185cea386ca331831117605
size 8573431520

3
Qwen2.5-14B_Uncencored-Q5_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f2dbe95d84139936788652738629726182df0096effe036b07c5227ebf0a1636
size 10989395680

3
Qwen2.5-14B_Uncencored-Q5_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f6a930e3672d5900d5f80d82f8a32d6a211e1ee15259bc87bba754bdc9a64544
size 10508873440

3
Qwen2.5-14B_Uncencored-Q5_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d994e3690946c5f1ad137bfd75f8c4541a5ef4258b9866a558a5aac870edbb46
size 10266554080

3
Qwen2.5-14B_Uncencored-Q6_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ec795c1070b072567bc6415356cccb04d95b0b049be07a62f60f5f23ef489946
size 12124684000

3
Qwen2.5-14B_Uncencored-Q6_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:dbeaf1f7ee9be3482b7e33af869c92f712a173b369221eeb60e163744d885239
size 12501802720

3
Qwen2.5-14B_Uncencored-Q8_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:11e23437b3ef117af39a92a2d96709db8ca049d89748db183d72e6d27366a130
size 15701597920

3
Qwen2.5-14B_Uncencored-f16.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3d50552a6cb85a3a86bf19e1224978b4ba30b45851b3519ed2a4b8291e7c83d8
size 29547716032

3
Qwen2.5-14B_Uncencored.imatrix Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d41c36476d8b622782c379b73d1fabc8cb4ffe46cc9fa35a21cb9872dc034b66
size 8563610

130
README.md Normal file
View File

@@ -0,0 +1,130 @@
---
base_model: SicariusSicariiStuff/Qwen2.5-14B_Uncencored
language:
- en
license: apache-2.0
pipeline_tag: text-generation
quantized_by: bartowski
tags:
- not-for-all-audiences
---
## Llamacpp imatrix Quantizations of Qwen2.5-14B_Uncencored
Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b3772">b3772</a> for quantization.
Original model: https://huggingface.co/SicariusSicariiStuff/Qwen2.5-14B_Uncencored
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 |
| -------- | ---------- | --------- | ----- | ----------- |
| [Qwen2.5-14B_Uncencored-f16.gguf](https://huggingface.co/bartowski/Qwen2.5-14B_Uncencored-GGUF/blob/main/Qwen2.5-14B_Uncencored-f16.gguf) | f16 | 29.55GB | false | Full F16 weights. |
| [Qwen2.5-14B_Uncencored-Q8_0.gguf](https://huggingface.co/bartowski/Qwen2.5-14B_Uncencored-GGUF/blob/main/Qwen2.5-14B_Uncencored-Q8_0.gguf) | Q8_0 | 15.70GB | false | Extremely high quality, generally unneeded but max available quant. |
| [Qwen2.5-14B_Uncencored-Q6_K_L.gguf](https://huggingface.co/bartowski/Qwen2.5-14B_Uncencored-GGUF/blob/main/Qwen2.5-14B_Uncencored-Q6_K_L.gguf) | Q6_K_L | 12.50GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. |
| [Qwen2.5-14B_Uncencored-Q6_K.gguf](https://huggingface.co/bartowski/Qwen2.5-14B_Uncencored-GGUF/blob/main/Qwen2.5-14B_Uncencored-Q6_K.gguf) | Q6_K | 12.12GB | false | Very high quality, near perfect, *recommended*. |
| [Qwen2.5-14B_Uncencored-Q5_K_L.gguf](https://huggingface.co/bartowski/Qwen2.5-14B_Uncencored-GGUF/blob/main/Qwen2.5-14B_Uncencored-Q5_K_L.gguf) | Q5_K_L | 10.99GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. |
| [Qwen2.5-14B_Uncencored-Q5_K_M.gguf](https://huggingface.co/bartowski/Qwen2.5-14B_Uncencored-GGUF/blob/main/Qwen2.5-14B_Uncencored-Q5_K_M.gguf) | Q5_K_M | 10.51GB | false | High quality, *recommended*. |
| [Qwen2.5-14B_Uncencored-Q5_K_S.gguf](https://huggingface.co/bartowski/Qwen2.5-14B_Uncencored-GGUF/blob/main/Qwen2.5-14B_Uncencored-Q5_K_S.gguf) | Q5_K_S | 10.27GB | false | High quality, *recommended*. |
| [Qwen2.5-14B_Uncencored-Q4_K_L.gguf](https://huggingface.co/bartowski/Qwen2.5-14B_Uncencored-GGUF/blob/main/Qwen2.5-14B_Uncencored-Q4_K_L.gguf) | Q4_K_L | 9.57GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. |
| [Qwen2.5-14B_Uncencored-Q4_K_M.gguf](https://huggingface.co/bartowski/Qwen2.5-14B_Uncencored-GGUF/blob/main/Qwen2.5-14B_Uncencored-Q4_K_M.gguf) | Q4_K_M | 8.99GB | false | Good quality, default size for must use cases, *recommended*. |
| [Qwen2.5-14B_Uncencored-Q3_K_XL.gguf](https://huggingface.co/bartowski/Qwen2.5-14B_Uncencored-GGUF/blob/main/Qwen2.5-14B_Uncencored-Q3_K_XL.gguf) | Q3_K_XL | 8.61GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. |
| [Qwen2.5-14B_Uncencored-Q4_K_S.gguf](https://huggingface.co/bartowski/Qwen2.5-14B_Uncencored-GGUF/blob/main/Qwen2.5-14B_Uncencored-Q4_K_S.gguf) | Q4_K_S | 8.57GB | false | Slightly lower quality with more space savings, *recommended*. |
| [Qwen2.5-14B_Uncencored-Q4_0.gguf](https://huggingface.co/bartowski/Qwen2.5-14B_Uncencored-GGUF/blob/main/Qwen2.5-14B_Uncencored-Q4_0.gguf) | Q4_0 | 8.54GB | false | Legacy format, generally not worth using over similarly sized formats |
| [Qwen2.5-14B_Uncencored-Q4_0_8_8.gguf](https://huggingface.co/bartowski/Qwen2.5-14B_Uncencored-GGUF/blob/main/Qwen2.5-14B_Uncencored-Q4_0_8_8.gguf) | Q4_0_8_8 | 8.52GB | false | Optimized for ARM inference. Requires 'sve' support (see link below). |
| [Qwen2.5-14B_Uncencored-Q4_0_4_8.gguf](https://huggingface.co/bartowski/Qwen2.5-14B_Uncencored-GGUF/blob/main/Qwen2.5-14B_Uncencored-Q4_0_4_8.gguf) | Q4_0_4_8 | 8.52GB | false | Optimized for ARM inference. Requires 'i8mm' support (see link below). |
| [Qwen2.5-14B_Uncencored-Q4_0_4_4.gguf](https://huggingface.co/bartowski/Qwen2.5-14B_Uncencored-GGUF/blob/main/Qwen2.5-14B_Uncencored-Q4_0_4_4.gguf) | Q4_0_4_4 | 8.52GB | false | Optimized for ARM inference. Should work well on all ARM chips, pick this if you're unsure. |
| [Qwen2.5-14B_Uncencored-IQ4_XS.gguf](https://huggingface.co/bartowski/Qwen2.5-14B_Uncencored-GGUF/blob/main/Qwen2.5-14B_Uncencored-IQ4_XS.gguf) | IQ4_XS | 8.12GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
| [Qwen2.5-14B_Uncencored-Q3_K_L.gguf](https://huggingface.co/bartowski/Qwen2.5-14B_Uncencored-GGUF/blob/main/Qwen2.5-14B_Uncencored-Q3_K_L.gguf) | Q3_K_L | 7.92GB | false | Lower quality but usable, good for low RAM availability. |
| [Qwen2.5-14B_Uncencored-Q3_K_M.gguf](https://huggingface.co/bartowski/Qwen2.5-14B_Uncencored-GGUF/blob/main/Qwen2.5-14B_Uncencored-Q3_K_M.gguf) | Q3_K_M | 7.34GB | false | Low quality. |
| [Qwen2.5-14B_Uncencored-IQ3_M.gguf](https://huggingface.co/bartowski/Qwen2.5-14B_Uncencored-GGUF/blob/main/Qwen2.5-14B_Uncencored-IQ3_M.gguf) | IQ3_M | 6.92GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
| [Qwen2.5-14B_Uncencored-Q3_K_S.gguf](https://huggingface.co/bartowski/Qwen2.5-14B_Uncencored-GGUF/blob/main/Qwen2.5-14B_Uncencored-Q3_K_S.gguf) | Q3_K_S | 6.66GB | false | Low quality, not recommended. |
| [Qwen2.5-14B_Uncencored-Q2_K_L.gguf](https://huggingface.co/bartowski/Qwen2.5-14B_Uncencored-GGUF/blob/main/Qwen2.5-14B_Uncencored-Q2_K_L.gguf) | Q2_K_L | 6.53GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. |
| [Qwen2.5-14B_Uncencored-IQ3_XS.gguf](https://huggingface.co/bartowski/Qwen2.5-14B_Uncencored-GGUF/blob/main/Qwen2.5-14B_Uncencored-IQ3_XS.gguf) | IQ3_XS | 6.38GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
| [Qwen2.5-14B_Uncencored-Q2_K.gguf](https://huggingface.co/bartowski/Qwen2.5-14B_Uncencored-GGUF/blob/main/Qwen2.5-14B_Uncencored-Q2_K.gguf) | Q2_K | 5.77GB | false | Very low quality but surprisingly usable. |
| [Qwen2.5-14B_Uncencored-IQ2_M.gguf](https://huggingface.co/bartowski/Qwen2.5-14B_Uncencored-GGUF/blob/main/Qwen2.5-14B_Uncencored-IQ2_M.gguf) | IQ2_M | 5.36GB | false | Relatively low quality, uses SOTA techniques to be surprisingly usable. |
| [Qwen2.5-14B_Uncencored-IQ2_S.gguf](https://huggingface.co/bartowski/Qwen2.5-14B_Uncencored-GGUF/blob/main/Qwen2.5-14B_Uncencored-IQ2_S.gguf) | IQ2_S | 5.00GB | false | Low quality, uses SOTA techniques to be 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/Qwen2.5-14B_Uncencored-GGUF --include "Qwen2.5-14B_Uncencored-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/Qwen2.5-14B_Uncencored-GGUF --include "Qwen2.5-14B_Uncencored-Q8_0/*" --local-dir ./
```
You can either specify a new local-dir (Qwen2.5-14B_Uncencored-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}