bartowski/AGI-0_Art-Skynet-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/AGI-0_Art-Skynet-3B-GGUF
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-08-07 05:33:13 +08:00
commit 35fe3150f8
28 changed files with 311 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
AGI-0_Art-Skynet-3B-f16.gguf filter=lfs diff=lfs merge=lfs -text
AGI-0_Art-Skynet-3B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
AGI-0_Art-Skynet-3B-Q6_K_L.gguf filter=lfs diff=lfs merge=lfs -text
AGI-0_Art-Skynet-3B-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
AGI-0_Art-Skynet-3B-Q5_K_L.gguf filter=lfs diff=lfs merge=lfs -text
AGI-0_Art-Skynet-3B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
AGI-0_Art-Skynet-3B-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
AGI-0_Art-Skynet-3B-Q4_K_L.gguf filter=lfs diff=lfs merge=lfs -text
AGI-0_Art-Skynet-3B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
AGI-0_Art-Skynet-3B-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
AGI-0_Art-Skynet-3B-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text
AGI-0_Art-Skynet-3B-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
AGI-0_Art-Skynet-3B-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text
AGI-0_Art-Skynet-3B-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
AGI-0_Art-Skynet-3B-Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
AGI-0_Art-Skynet-3B-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
AGI-0_Art-Skynet-3B-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
AGI-0_Art-Skynet-3B-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
AGI-0_Art-Skynet-3B-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
AGI-0_Art-Skynet-3B-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
AGI-0_Art-Skynet-3B-Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text
AGI-0_Art-Skynet-3B-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
AGI-0_Art-Skynet-3B-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text
AGI-0_Art-Skynet-3B-f32.gguf filter=lfs diff=lfs merge=lfs -text
AGI-0_Art-Skynet-3B.imatrix filter=lfs diff=lfs merge=lfs -text

3
AGI-0_Art-Skynet-3B-IQ2_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0f6f0940e56df5fd963425da464bfb9a648d7b684885dedd1ec540fca970d5f0
size 1229031776

3
AGI-0_Art-Skynet-3B-IQ3_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a338695cfc652a3411936cfe28b510bfc5792d502d62dceecfa4626f53099587
size 1599668576

3
AGI-0_Art-Skynet-3B-IQ3_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:18797d1c878fa8ec6f41881af65086703c8ab7b7164823f4eb4c4e42ea01839b
size 1476788576

3
AGI-0_Art-Skynet-3B-IQ4_NL.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:498ecc3a592bee43b705461ea2e0af349b7a2ba63d4201aa73513a0df948557d
size 1917190496

3
AGI-0_Art-Skynet-3B-IQ4_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c05b57ff5157e53604c54da6cbd7b3ba7507163e7d932108e6534eb6ff71fb0c
size 1829110112

3
AGI-0_Art-Skynet-3B-Q2_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d468dd4453b69124a98b521355d89cd6046312cf6ec4343306ea2762ab5dc81c
size 1363935584

3
AGI-0_Art-Skynet-3B-Q2_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:75b4208541d232da254ee9de11560849285857fc1c6e8a34b221205d98e57e94
size 1459358048

3
AGI-0_Art-Skynet-3B-Q3_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:620023fbc7e750a37a1c81704a9f63f0a37535478747b3f413618e0074bf477e
size 1815347552

3
AGI-0_Art-Skynet-3B-Q3_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:68e8bbb74d126ada4e01acf730cc0e818db78a72cb08087d8675e999e595c363
size 1687159136

3
AGI-0_Art-Skynet-3B-Q3_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ef99dfa9bc0c58b31f2cac4f75c15ce65b0685adf6a5e113737813f5bd489dad
size 1542848864

3
AGI-0_Art-Skynet-3B-Q3_K_XL.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:503bfbc2a7deb3d3011780137db76ac9ab0902249e39a8eb601f0ad387195809
size 1910770016

3
AGI-0_Art-Skynet-3B-Q4_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:539a4c75f53a61ce28f8a231dbd6a25503b072bb73aa2c88ffccff3bd14dd06e
size 1921909088

3
AGI-0_Art-Skynet-3B-Q4_1.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b7c0473b85ca8ef480bc182d788f256833ae385f65f37234e5bc98620a812757
size 2093351264

3
AGI-0_Art-Skynet-3B-Q4_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0126a23e63abc029c463f287838a8ce54da1e9d8f7afdcbb68e7595f7212121e
size 2114799968

3
AGI-0_Art-Skynet-3B-Q4_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:6063cf3cf90f72cfb6ad7564bca8229806cb9823a055adcbce3dc539c2a75765
size 2019377504

3
AGI-0_Art-Skynet-3B-Q4_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:095f02f786dfd43f61ab3c600558420b64798c3a20a8fa91ee0890930cfff756
size 1928200544

3
AGI-0_Art-Skynet-3B-Q5_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:95a1fec07643424f04babb6b55654c8d10e90d9bc9d5c8cb84480db738a94395
size 2417576288

3
AGI-0_Art-Skynet-3B-Q5_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:bc48f58420e87fd0de3ec66fa12a99e95f46d1d92c00dcbdc58455d434186d7a
size 2322153824

3
AGI-0_Art-Skynet-3B-Q5_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3b9dc1653bdf915343333f3e37dbf2527f09ac5abd75d260d8dd07334d0f39f2
size 2269512032

3
AGI-0_Art-Skynet-3B-Q6_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2decb7930cc193dc286df2f9af17c27e9313808e30677c19f90420e9b84bb6b2
size 2643853664

3
AGI-0_Art-Skynet-3B-Q6_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c1b98b045e13aafbbc9ceb8bb76903b54205f2261fae84ce47fe2fe3fae25265
size 2739276128

3
AGI-0_Art-Skynet-3B-Q8_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:badbbb4e994825c29566c617cef2391294643b08b11f90bdd5c232f1ddec6e2a
size 3421899104

3
AGI-0_Art-Skynet-3B-f16.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d1c6eb159740680bcf8b7dbf05118a87a946ba339a237c84118ba4f4d0414bb8
size 6433687904

3
AGI-0_Art-Skynet-3B-f32.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:03258aab66333ad29b55aa3e66fa8d225c793444631d29d1d22e861a458b8338
size 12858837056

3
AGI-0_Art-Skynet-3B.imatrix Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b3ef2af9f47a19fa7047ecf7574feb6dd614d1ebc6e31218688413e49eedd0eb
size 2988390

175
README.md Normal file
View File

@@ -0,0 +1,175 @@
---
quantized_by: bartowski
pipeline_tag: text-generation
license: llama3.2
base_model: AGI-0/Art-Skynet-3B
---
## Llamacpp imatrix Quantizations of Art-Skynet-3B by AGI-0
Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b4585">b4585</a> for quantization.
Original model: https://huggingface.co/AGI-0/Art-Skynet-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/)
Run them directly with [llama.cpp](https://github.com/ggerganov/llama.cpp), or any other llama.cpp based project
## Prompt format
```
<|begin_of_text|><|start_header_id|>system<|end_header_id|>
Cutting Knowledge Date: December 2023
Today Date: 05 Feb 2025
{system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>
{prompt}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
```
## Download a file (not the whole branch) from below:
| Filename | Quant type | File Size | Split | Description |
| -------- | ---------- | --------- | ----- | ----------- |
| [Art-Skynet-3B-f32.gguf](https://huggingface.co/bartowski/AGI-0_Art-Skynet-3B-GGUF/blob/main/AGI-0_Art-Skynet-3B-f32.gguf) | f32 | 12.86GB | false | Full F32 weights. |
| [Art-Skynet-3B-f16.gguf](https://huggingface.co/bartowski/AGI-0_Art-Skynet-3B-GGUF/blob/main/AGI-0_Art-Skynet-3B-f16.gguf) | f16 | 6.43GB | false | Full F16 weights. |
| [Art-Skynet-3B-Q8_0.gguf](https://huggingface.co/bartowski/AGI-0_Art-Skynet-3B-GGUF/blob/main/AGI-0_Art-Skynet-3B-Q8_0.gguf) | Q8_0 | 3.42GB | false | Extremely high quality, generally unneeded but max available quant. |
| [Art-Skynet-3B-Q6_K_L.gguf](https://huggingface.co/bartowski/AGI-0_Art-Skynet-3B-GGUF/blob/main/AGI-0_Art-Skynet-3B-Q6_K_L.gguf) | Q6_K_L | 2.74GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. |
| [Art-Skynet-3B-Q6_K.gguf](https://huggingface.co/bartowski/AGI-0_Art-Skynet-3B-GGUF/blob/main/AGI-0_Art-Skynet-3B-Q6_K.gguf) | Q6_K | 2.64GB | false | Very high quality, near perfect, *recommended*. |
| [Art-Skynet-3B-Q5_K_L.gguf](https://huggingface.co/bartowski/AGI-0_Art-Skynet-3B-GGUF/blob/main/AGI-0_Art-Skynet-3B-Q5_K_L.gguf) | Q5_K_L | 2.42GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. |
| [Art-Skynet-3B-Q5_K_M.gguf](https://huggingface.co/bartowski/AGI-0_Art-Skynet-3B-GGUF/blob/main/AGI-0_Art-Skynet-3B-Q5_K_M.gguf) | Q5_K_M | 2.32GB | false | High quality, *recommended*. |
| [Art-Skynet-3B-Q5_K_S.gguf](https://huggingface.co/bartowski/AGI-0_Art-Skynet-3B-GGUF/blob/main/AGI-0_Art-Skynet-3B-Q5_K_S.gguf) | Q5_K_S | 2.27GB | false | High quality, *recommended*. |
| [Art-Skynet-3B-Q4_K_L.gguf](https://huggingface.co/bartowski/AGI-0_Art-Skynet-3B-GGUF/blob/main/AGI-0_Art-Skynet-3B-Q4_K_L.gguf) | Q4_K_L | 2.11GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. |
| [Art-Skynet-3B-Q4_1.gguf](https://huggingface.co/bartowski/AGI-0_Art-Skynet-3B-GGUF/blob/main/AGI-0_Art-Skynet-3B-Q4_1.gguf) | Q4_1 | 2.09GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. |
| [Art-Skynet-3B-Q4_K_M.gguf](https://huggingface.co/bartowski/AGI-0_Art-Skynet-3B-GGUF/blob/main/AGI-0_Art-Skynet-3B-Q4_K_M.gguf) | Q4_K_M | 2.02GB | false | Good quality, default size for most use cases, *recommended*. |
| [Art-Skynet-3B-Q4_K_S.gguf](https://huggingface.co/bartowski/AGI-0_Art-Skynet-3B-GGUF/blob/main/AGI-0_Art-Skynet-3B-Q4_K_S.gguf) | Q4_K_S | 1.93GB | false | Slightly lower quality with more space savings, *recommended*. |
| [Art-Skynet-3B-Q4_0.gguf](https://huggingface.co/bartowski/AGI-0_Art-Skynet-3B-GGUF/blob/main/AGI-0_Art-Skynet-3B-Q4_0.gguf) | Q4_0 | 1.92GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. |
| [Art-Skynet-3B-IQ4_NL.gguf](https://huggingface.co/bartowski/AGI-0_Art-Skynet-3B-GGUF/blob/main/AGI-0_Art-Skynet-3B-IQ4_NL.gguf) | IQ4_NL | 1.92GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. |
| [Art-Skynet-3B-Q3_K_XL.gguf](https://huggingface.co/bartowski/AGI-0_Art-Skynet-3B-GGUF/blob/main/AGI-0_Art-Skynet-3B-Q3_K_XL.gguf) | Q3_K_XL | 1.91GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. |
| [Art-Skynet-3B-IQ4_XS.gguf](https://huggingface.co/bartowski/AGI-0_Art-Skynet-3B-GGUF/blob/main/AGI-0_Art-Skynet-3B-IQ4_XS.gguf) | IQ4_XS | 1.83GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
| [Art-Skynet-3B-Q3_K_L.gguf](https://huggingface.co/bartowski/AGI-0_Art-Skynet-3B-GGUF/blob/main/AGI-0_Art-Skynet-3B-Q3_K_L.gguf) | Q3_K_L | 1.82GB | false | Lower quality but usable, good for low RAM availability. |
| [Art-Skynet-3B-Q3_K_M.gguf](https://huggingface.co/bartowski/AGI-0_Art-Skynet-3B-GGUF/blob/main/AGI-0_Art-Skynet-3B-Q3_K_M.gguf) | Q3_K_M | 1.69GB | false | Low quality. |
| [Art-Skynet-3B-IQ3_M.gguf](https://huggingface.co/bartowski/AGI-0_Art-Skynet-3B-GGUF/blob/main/AGI-0_Art-Skynet-3B-IQ3_M.gguf) | IQ3_M | 1.60GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
| [Art-Skynet-3B-Q3_K_S.gguf](https://huggingface.co/bartowski/AGI-0_Art-Skynet-3B-GGUF/blob/main/AGI-0_Art-Skynet-3B-Q3_K_S.gguf) | Q3_K_S | 1.54GB | false | Low quality, not recommended. |
| [Art-Skynet-3B-IQ3_XS.gguf](https://huggingface.co/bartowski/AGI-0_Art-Skynet-3B-GGUF/blob/main/AGI-0_Art-Skynet-3B-IQ3_XS.gguf) | IQ3_XS | 1.48GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
| [Art-Skynet-3B-Q2_K_L.gguf](https://huggingface.co/bartowski/AGI-0_Art-Skynet-3B-GGUF/blob/main/AGI-0_Art-Skynet-3B-Q2_K_L.gguf) | Q2_K_L | 1.46GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. |
| [Art-Skynet-3B-Q2_K.gguf](https://huggingface.co/bartowski/AGI-0_Art-Skynet-3B-GGUF/blob/main/AGI-0_Art-Skynet-3B-Q2_K.gguf) | Q2_K | 1.36GB | false | Very low quality but surprisingly usable. |
| [Art-Skynet-3B-IQ2_M.gguf](https://huggingface.co/bartowski/AGI-0_Art-Skynet-3B-GGUF/blob/main/AGI-0_Art-Skynet-3B-IQ2_M.gguf) | IQ2_M | 1.23GB | 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/AGI-0_Art-Skynet-3B-GGUF --include "AGI-0_Art-Skynet-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/AGI-0_Art-Skynet-3B-GGUF --include "AGI-0_Art-Skynet-3B-Q8_0/*" --local-dir ./
```
You can either specify a new local-dir (AGI-0_Art-Skynet-3B-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 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.
</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

1
configuration.json Normal file
View File

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