bartowski/LGAI-EXAONE_EXAONE-4.0-1.2B-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/LGAI-EXAONE_EXAONE-4.0-1.2B-GGUF
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-07-27 18:56:06 +08:00
commit 67367d2a5f
28 changed files with 300 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

49
.gitattributes vendored Normal file
View File

@@ -0,0 +1,49 @@
*.7z filter=lfs diff=lfs merge=lfs -text
*.arrow filter=lfs diff=lfs merge=lfs -text
*.bin filter=lfs diff=lfs merge=lfs -text
*.bin.* filter=lfs diff=lfs merge=lfs -text
*.bz2 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
*.model filter=lfs diff=lfs merge=lfs -text
*.msgpack 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
*.pt filter=lfs diff=lfs merge=lfs -text
*.pth filter=lfs diff=lfs merge=lfs -text
*.rar filter=lfs diff=lfs merge=lfs -text
saved_model/**/* 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
*.xz filter=lfs diff=lfs merge=lfs -text
*.zip filter=lfs diff=lfs merge=lfs -text
*.zstandard filter=lfs diff=lfs merge=lfs -text
*.tfevents* filter=lfs diff=lfs merge=lfs -text
*.db* filter=lfs diff=lfs merge=lfs -text
*.ark* filter=lfs diff=lfs merge=lfs -text
**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
*.safetensors filter=lfs diff=lfs merge=lfs -text
*.ckpt filter=lfs diff=lfs merge=lfs -text
*.gguf* filter=lfs diff=lfs merge=lfs -text
*.ggml filter=lfs diff=lfs merge=lfs -text
*.llamafile* filter=lfs diff=lfs merge=lfs -text
*.pt2 filter=lfs diff=lfs merge=lfs -text
*.mlmodel filter=lfs diff=lfs merge=lfs -text
*.npy filter=lfs diff=lfs merge=lfs -text
*.npz filter=lfs diff=lfs merge=lfs -text
*.pickle filter=lfs diff=lfs merge=lfs -text
*.pkl filter=lfs diff=lfs merge=lfs -text
*.tar filter=lfs diff=lfs merge=lfs -text
*.wasm filter=lfs diff=lfs merge=lfs -text
*.zst filter=lfs diff=lfs merge=lfs -text
*tfevents* filter=lfs diff=lfs merge=lfs -text
LGAI-EXAONE_EXAONE-4.0-1.2B.imatrix filter=lfs diff=lfs merge=lfs -text

3
LGAI-EXAONE_EXAONE-4.0-1.2B-IQ2_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:74f6bfd9f15d028da6f9406492dc02833655aa3338b3d7b6abf24396897e6159
size 515625760

3
LGAI-EXAONE_EXAONE-4.0-1.2B-IQ3_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9a96ecb3a26c02aa502f370bedfad63c67aa0773f3b7045e58a90b3779b2fedb
size 660558624

3
LGAI-EXAONE_EXAONE-4.0-1.2B-IQ3_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:fa0a4ec237a20c365d8bffff14af5da6e691be24cdec95281ca64ccd5cbaf9c5
size 615043872

3
LGAI-EXAONE_EXAONE-4.0-1.2B-IQ3_XXS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:8ea4b9902274b0c82f86c1aed29f42fd2a9cec906b1bfe3979feb093c667fed7
size 560059168

3
LGAI-EXAONE_EXAONE-4.0-1.2B-IQ4_NL.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1a459af1f089b72a16751d5a8b28f2ea05087bcad2df3154cc139d409f05a48d
size 782308128

3
LGAI-EXAONE_EXAONE-4.0-1.2B-IQ4_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b83bfcee00cdc6937ef9bb8123429e1d3229e507fb3cf934e32777f6f0f62297
size 749867808

3
LGAI-EXAONE_EXAONE-4.0-1.2B-Q2_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5f954d42df519a9205283958f4ba7e870c185fa3545ea5e93a5966de5e1e4de5
size 573412128

3
LGAI-EXAONE_EXAONE-4.0-1.2B-Q2_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:4e48eda140d178bc60709b128f5ffaecabf133423fdd9d73528afdfd102d10d6
size 624202528

3
LGAI-EXAONE_EXAONE-4.0-1.2B-Q3_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1d60c0840b6a52281a67a581dc998b18d64f0206aed1f1d6d7922562c4232de9
size 741757728

3
LGAI-EXAONE_EXAONE-4.0-1.2B-Q3_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f13e843ba002d1aa0f1488b3251bc2def3a60f81deda923bbb7e8d368e9b8c26
size 691950368

3
LGAI-EXAONE_EXAONE-4.0-1.2B-Q3_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0053eedf928770faac3c3f1521b6c67977aa7f54ccaa8ebbde50670f3b8d7cec
size 636326688

3
LGAI-EXAONE_EXAONE-4.0-1.2B-Q3_K_XL.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:7720a3521af22aaf36e23f2492a3f6ac4bac7582aea9e77b6563d2ffbc6dfc5c
size 792548128

3
LGAI-EXAONE_EXAONE-4.0-1.2B-Q4_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b7d2de07e27b666b06bbdd2edf7d00db7747969bfae16a0a90a8cd5ef16426c8
size 779948832

3
LGAI-EXAONE_EXAONE-4.0-1.2B-Q4_1.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:4a5f2c170807b553b04f72036116753b885a84d15162525d023df62268db4f41
size 845222688

3
LGAI-EXAONE_EXAONE-4.0-1.2B-Q4_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:47ea82daab19e60176d9ce783be6614adcc823923f11959d2fca12d06a5596eb
size 863228704

3
LGAI-EXAONE_EXAONE-4.0-1.2B-Q4_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:4b3fe462894e52ac923540e208840cf949a3b4f50d41e2d5dde7916f386dfeba
size 812438304

3
LGAI-EXAONE_EXAONE-4.0-1.2B-Q4_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:09fcc98df95ddaeb36a4b679f216d23e90485c3d319d5969768d6d4cd46a8f14
size 782045984

3
LGAI-EXAONE_EXAONE-4.0-1.2B-Q5_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:8c0e25b2cef8bb526a21cf2fd5648413e8aa517e053fe90f57abe98d558060b7
size 980407072

3
LGAI-EXAONE_EXAONE-4.0-1.2B-Q5_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:811db92193714df6caf6325d4ddb67016f166d6e16bc8c747dd4fe532aec8a16
size 929616672

3
LGAI-EXAONE_EXAONE-4.0-1.2B-Q5_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3126e722eb785e1a8983edcbda62df649a4984abff97e06f9646aadc3c3df480
size 912069408

3
LGAI-EXAONE_EXAONE-4.0-1.2B-Q6_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:7c2ab092b617cd51977537177854be25af8248d61a0030a94e00034ab38c2920
size 1054118688

3
LGAI-EXAONE_EXAONE-4.0-1.2B-Q6_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5568cef2b46422615cb09ee75d534c3ea4ae10607c1ba08e7d9ae8ba5681a11d
size 1104909088

3
LGAI-EXAONE_EXAONE-4.0-1.2B-Q8_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:7959864702ef5a4476b5dc19186815af10ac9126142dcb92daaac8c0762459f4
size 1363940128

3
LGAI-EXAONE_EXAONE-4.0-1.2B-bf16.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:7f52b33d5568b2274161b76dba4d3db90aebc5ca67b89cb451fb30171b75feb2
size 2563248672

3
LGAI-EXAONE_EXAONE-4.0-1.2B.imatrix Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a333f8af22636837854f71b1480a128f402daa886bf9a59d6fc11a114bd7dbfb
size 1973048

175
README.md Normal file
View File

@@ -0,0 +1,175 @@
---
quantized_by: bartowski
pipeline_tag: text-generation
base_model: LGAI-EXAONE/EXAONE-4.0-1.2B
base_model_relation: quantized
---
## Llamacpp imatrix Quantizations of EXAONE-4.0-1.2B by LGAI-EXAONE
Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b5934">b5934</a> for quantization.
Original model: https://huggingface.co/LGAI-EXAONE/EXAONE-4.0-1.2B
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
No chat template specified so default is used. This may be incorrect, check original model card for details.
```
[|system|]
{system_prompt}[|endofturn|]
[|user|]
{prompt}[|endofturn|]
[|assistant|]
<think>
</think>
```
## Download a file (not the whole branch) from below:
| Filename | Quant type | File Size | Split | Description |
| -------- | ---------- | --------- | ----- | ----------- |
| [EXAONE-4.0-1.2B-bf16.gguf](https://huggingface.co/bartowski/LGAI-EXAONE_EXAONE-4.0-1.2B-GGUF/blob/main/LGAI-EXAONE_EXAONE-4.0-1.2B-bf16.gguf) | bf16 | 2.56GB | false | Full BF16 weights. |
| [EXAONE-4.0-1.2B-Q8_0.gguf](https://huggingface.co/bartowski/LGAI-EXAONE_EXAONE-4.0-1.2B-GGUF/blob/main/LGAI-EXAONE_EXAONE-4.0-1.2B-Q8_0.gguf) | Q8_0 | 1.36GB | false | Extremely high quality, generally unneeded but max available quant. |
| [EXAONE-4.0-1.2B-Q6_K_L.gguf](https://huggingface.co/bartowski/LGAI-EXAONE_EXAONE-4.0-1.2B-GGUF/blob/main/LGAI-EXAONE_EXAONE-4.0-1.2B-Q6_K_L.gguf) | Q6_K_L | 1.10GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. |
| [EXAONE-4.0-1.2B-Q6_K.gguf](https://huggingface.co/bartowski/LGAI-EXAONE_EXAONE-4.0-1.2B-GGUF/blob/main/LGAI-EXAONE_EXAONE-4.0-1.2B-Q6_K.gguf) | Q6_K | 1.05GB | false | Very high quality, near perfect, *recommended*. |
| [EXAONE-4.0-1.2B-Q5_K_L.gguf](https://huggingface.co/bartowski/LGAI-EXAONE_EXAONE-4.0-1.2B-GGUF/blob/main/LGAI-EXAONE_EXAONE-4.0-1.2B-Q5_K_L.gguf) | Q5_K_L | 0.98GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. |
| [EXAONE-4.0-1.2B-Q5_K_M.gguf](https://huggingface.co/bartowski/LGAI-EXAONE_EXAONE-4.0-1.2B-GGUF/blob/main/LGAI-EXAONE_EXAONE-4.0-1.2B-Q5_K_M.gguf) | Q5_K_M | 0.93GB | false | High quality, *recommended*. |
| [EXAONE-4.0-1.2B-Q5_K_S.gguf](https://huggingface.co/bartowski/LGAI-EXAONE_EXAONE-4.0-1.2B-GGUF/blob/main/LGAI-EXAONE_EXAONE-4.0-1.2B-Q5_K_S.gguf) | Q5_K_S | 0.91GB | false | High quality, *recommended*. |
| [EXAONE-4.0-1.2B-Q4_K_L.gguf](https://huggingface.co/bartowski/LGAI-EXAONE_EXAONE-4.0-1.2B-GGUF/blob/main/LGAI-EXAONE_EXAONE-4.0-1.2B-Q4_K_L.gguf) | Q4_K_L | 0.86GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. |
| [EXAONE-4.0-1.2B-Q4_1.gguf](https://huggingface.co/bartowski/LGAI-EXAONE_EXAONE-4.0-1.2B-GGUF/blob/main/LGAI-EXAONE_EXAONE-4.0-1.2B-Q4_1.gguf) | Q4_1 | 0.85GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. |
| [EXAONE-4.0-1.2B-Q4_K_M.gguf](https://huggingface.co/bartowski/LGAI-EXAONE_EXAONE-4.0-1.2B-GGUF/blob/main/LGAI-EXAONE_EXAONE-4.0-1.2B-Q4_K_M.gguf) | Q4_K_M | 0.81GB | false | Good quality, default size for most use cases, *recommended*. |
| [EXAONE-4.0-1.2B-Q3_K_XL.gguf](https://huggingface.co/bartowski/LGAI-EXAONE_EXAONE-4.0-1.2B-GGUF/blob/main/LGAI-EXAONE_EXAONE-4.0-1.2B-Q3_K_XL.gguf) | Q3_K_XL | 0.79GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. |
| [EXAONE-4.0-1.2B-Q4_K_S.gguf](https://huggingface.co/bartowski/LGAI-EXAONE_EXAONE-4.0-1.2B-GGUF/blob/main/LGAI-EXAONE_EXAONE-4.0-1.2B-Q4_K_S.gguf) | Q4_K_S | 0.78GB | false | Slightly lower quality with more space savings, *recommended*. |
| [EXAONE-4.0-1.2B-Q4_0.gguf](https://huggingface.co/bartowski/LGAI-EXAONE_EXAONE-4.0-1.2B-GGUF/blob/main/LGAI-EXAONE_EXAONE-4.0-1.2B-Q4_0.gguf) | Q4_0 | 0.78GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. |
| [EXAONE-4.0-1.2B-IQ4_NL.gguf](https://huggingface.co/bartowski/LGAI-EXAONE_EXAONE-4.0-1.2B-GGUF/blob/main/LGAI-EXAONE_EXAONE-4.0-1.2B-IQ4_NL.gguf) | IQ4_NL | 0.78GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. |
| [EXAONE-4.0-1.2B-IQ4_XS.gguf](https://huggingface.co/bartowski/LGAI-EXAONE_EXAONE-4.0-1.2B-GGUF/blob/main/LGAI-EXAONE_EXAONE-4.0-1.2B-IQ4_XS.gguf) | IQ4_XS | 0.75GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
| [EXAONE-4.0-1.2B-Q3_K_L.gguf](https://huggingface.co/bartowski/LGAI-EXAONE_EXAONE-4.0-1.2B-GGUF/blob/main/LGAI-EXAONE_EXAONE-4.0-1.2B-Q3_K_L.gguf) | Q3_K_L | 0.74GB | false | Lower quality but usable, good for low RAM availability. |
| [EXAONE-4.0-1.2B-Q3_K_M.gguf](https://huggingface.co/bartowski/LGAI-EXAONE_EXAONE-4.0-1.2B-GGUF/blob/main/LGAI-EXAONE_EXAONE-4.0-1.2B-Q3_K_M.gguf) | Q3_K_M | 0.69GB | false | Low quality. |
| [EXAONE-4.0-1.2B-IQ3_M.gguf](https://huggingface.co/bartowski/LGAI-EXAONE_EXAONE-4.0-1.2B-GGUF/blob/main/LGAI-EXAONE_EXAONE-4.0-1.2B-IQ3_M.gguf) | IQ3_M | 0.66GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
| [EXAONE-4.0-1.2B-Q3_K_S.gguf](https://huggingface.co/bartowski/LGAI-EXAONE_EXAONE-4.0-1.2B-GGUF/blob/main/LGAI-EXAONE_EXAONE-4.0-1.2B-Q3_K_S.gguf) | Q3_K_S | 0.64GB | false | Low quality, not recommended. |
| [EXAONE-4.0-1.2B-IQ3_XS.gguf](https://huggingface.co/bartowski/LGAI-EXAONE_EXAONE-4.0-1.2B-GGUF/blob/main/LGAI-EXAONE_EXAONE-4.0-1.2B-IQ3_XS.gguf) | IQ3_XS | 0.62GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
| [EXAONE-4.0-1.2B-Q2_K_L.gguf](https://huggingface.co/bartowski/LGAI-EXAONE_EXAONE-4.0-1.2B-GGUF/blob/main/LGAI-EXAONE_EXAONE-4.0-1.2B-Q2_K_L.gguf) | Q2_K_L | 0.62GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. |
| [EXAONE-4.0-1.2B-Q2_K.gguf](https://huggingface.co/bartowski/LGAI-EXAONE_EXAONE-4.0-1.2B-GGUF/blob/main/LGAI-EXAONE_EXAONE-4.0-1.2B-Q2_K.gguf) | Q2_K | 0.57GB | false | Very low quality but surprisingly usable. |
| [EXAONE-4.0-1.2B-IQ3_XXS.gguf](https://huggingface.co/bartowski/LGAI-EXAONE_EXAONE-4.0-1.2B-GGUF/blob/main/LGAI-EXAONE_EXAONE-4.0-1.2B-IQ3_XXS.gguf) | IQ3_XXS | 0.56GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. |
| [EXAONE-4.0-1.2B-IQ2_M.gguf](https://huggingface.co/bartowski/LGAI-EXAONE_EXAONE-4.0-1.2B-GGUF/blob/main/LGAI-EXAONE_EXAONE-4.0-1.2B-IQ2_M.gguf) | IQ2_M | 0.52GB | 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/LGAI-EXAONE_EXAONE-4.0-1.2B-GGUF --include "LGAI-EXAONE_EXAONE-4.0-1.2B-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/LGAI-EXAONE_EXAONE-4.0-1.2B-GGUF --include "LGAI-EXAONE_EXAONE-4.0-1.2B-Q8_0/*" --local-dir ./
```
You can either specify a new local-dir (LGAI-EXAONE_EXAONE-4.0-1.2B-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

1
configuration.json Normal file
View File

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