bartowski/Locutusque_liberalis-cogitator-llama-3.1-8b-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/Locutusque_liberalis-cogitator-llama-3.1-8b-GGUF
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-10-24 16:28:12 +08:00
commit 648b1d5e20
28 changed files with 287 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

47
.gitattributes vendored Normal file
View File

@@ -0,0 +1,47 @@
*.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

3
Locutusque_liberalis-cogitator-llama-3.1-8b-IQ2_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:58a9093fd42c9ff79d3996e5f41d07028f1939cca5bb7473a7ee1b3619f12f0f
size 2948281792

3
Locutusque_liberalis-cogitator-llama-3.1-8b-IQ3_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:de999814cd8ca2230ec3b137d9b13ac327ec0f7161f63cb2036ed47013e3901e
size 3784824256

3
Locutusque_liberalis-cogitator-llama-3.1-8b-IQ3_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:33cd1a9c5ed85653dbaee7efd1df83a1898efd025bc5f4ae432a5925a02c9e43
size 3518748096

3
Locutusque_liberalis-cogitator-llama-3.1-8b-IQ3_XXS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5f1a29ea4552ad3b33ca20e2af6afefba585fa99899f7172fb6d6cb2c4524a77
size 3274913216

3
Locutusque_liberalis-cogitator-llama-3.1-8b-IQ4_NL.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f9fd8bb2b01cd393c5ab5e6f560f48544f5921141a035b263cb5d7512e42d179
size 4677989824

3
Locutusque_liberalis-cogitator-llama-3.1-8b-IQ4_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:6628e73ddc832766e3a4d18a6de92d43e4e9518dca99d923a2714d069ac509ec
size 4447663552

3
Locutusque_liberalis-cogitator-llama-3.1-8b-Q2_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c9ee24f346c31360bdf659e2a9ed800b16f97b530ada91ae3328247ab2bfc80b
size 3179132352

3
Locutusque_liberalis-cogitator-llama-3.1-8b-Q2_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0ff1462c0b8d54e27229de3b9ac827491f94dca7118092b83d080f3ff352697f
size 3692156352

3
Locutusque_liberalis-cogitator-llama-3.1-8b-Q3_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f7c3b859c27ecc9e122967ac24155bdca726df423b505067d416a5a62c54d67e
size 4321957312

3
Locutusque_liberalis-cogitator-llama-3.1-8b-Q3_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:72894d08f476699292d6089fc27d58e79ed2b6b5d4c8432237184afdc8c9c171
size 4018918848

3
Locutusque_liberalis-cogitator-llama-3.1-8b-Q3_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:49311c418eb2401a43859d9eb443b41947ba2f190f9800f6c669f8ecfa382f6e
size 3664500160

3
Locutusque_liberalis-cogitator-llama-3.1-8b-Q3_K_XL.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:96285743851b46ec742bbe491b32a7d01402741bf0813e42d9b1c44f9b353317
size 4781626816

3
Locutusque_liberalis-cogitator-llama-3.1-8b-Q4_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:10b9e4c7a9d86840ccef53fe73587542b9b6e17539e7638ec3893f309134bffa
size 4675892672

3
Locutusque_liberalis-cogitator-llama-3.1-8b-Q4_1.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c7361fcd7a130308539e949fa7cb0d7671c739839c14e7f9a267734b5d710ee2
size 5130253760

3
Locutusque_liberalis-cogitator-llama-3.1-8b-Q4_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:94db5ed8074f47f2e2c1d3d69f5f204b263c72d78a9b6699529b6a45f134054c
size 5310633408

3
Locutusque_liberalis-cogitator-llama-3.1-8b-Q4_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:986f3f6d0858393800af93cad86048d324c31d06a804c9f393368daf2ee070c5
size 4920735168

3
Locutusque_liberalis-cogitator-llama-3.1-8b-Q4_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:332de4a2925074e0fb0b9d44a548f0267abbe94d7686695625a160c52b6edb75
size 4692669888

3
Locutusque_liberalis-cogitator-llama-3.1-8b-Q5_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0ce4b27020fce0b144450963b41b8c9d39134e393e38bd38a11384bdc728af95
size 6057219520

3
Locutusque_liberalis-cogitator-llama-3.1-8b-Q5_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2008f002836da9fc1c33cb64974c006aaf936f56b5247c5f7b63ad5585118739
size 5732988352

3
Locutusque_liberalis-cogitator-llama-3.1-8b-Q5_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ef6b8440e3173a5297668fd7dfbf6171224cc199cc8eecd782166d91dcbb3114
size 5599294912

3
Locutusque_liberalis-cogitator-llama-3.1-8b-Q6_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:6e69969a7283d9f1559c79f9bc17e24bacb4711a16ec9cff89926da8d722c25f
size 6596007360

3
Locutusque_liberalis-cogitator-llama-3.1-8b-Q6_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f19195d5249f2c0bbc9f1242303d9e1466a47a561dfbb5b376e4612fe8b01a33
size 6850467264

3
Locutusque_liberalis-cogitator-llama-3.1-8b-Q8_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1e36bd546427440805c3447650ff67fc9002af6b6ce7a3f8359dd00cd25efc69
size 8540771776

3
Locutusque_liberalis-cogitator-llama-3.1-8b-bf16.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:af6b0d1668878e979ed0630b5d8caf72baed1b83f2f49a976d622c3c7543b109
size 16068891776

3
Locutusque_liberalis-cogitator-llama-3.1-8b-imatrix.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:bef5a1346faac68d5b62a0ff65535403ba31e829e6583b0555dde8c8d71d8a11
size 5015232

164
README.md Normal file
View File

@@ -0,0 +1,164 @@
---
quantized_by: bartowski
pipeline_tag: text-generation
base_model_relation: quantized
base_model: Locutusque/liberalis-cogitator-llama-3.1-8b
---
## Llamacpp imatrix Quantizations of liberalis-cogitator-llama-3.1-8b by Locutusque
Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b6115">b6115</a> for quantization.
Original model: https://huggingface.co/Locutusque/liberalis-cogitator-llama-3.1-8b
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 prompt format found, check original model page
## Download a file (not the whole branch) from below:
| Filename | Quant type | File Size | Split | Description |
| -------- | ---------- | --------- | ----- | ----------- |
| [liberalis-cogitator-llama-3.1-8b-bf16.gguf](https://huggingface.co/bartowski/Locutusque_liberalis-cogitator-llama-3.1-8b-GGUF/blob/main/Locutusque_liberalis-cogitator-llama-3.1-8b-bf16.gguf) | bf16 | 16.07GB | false | Full BF16 weights. |
| [liberalis-cogitator-llama-3.1-8b-Q8_0.gguf](https://huggingface.co/bartowski/Locutusque_liberalis-cogitator-llama-3.1-8b-GGUF/blob/main/Locutusque_liberalis-cogitator-llama-3.1-8b-Q8_0.gguf) | Q8_0 | 8.54GB | false | Extremely high quality, generally unneeded but max available quant. |
| [liberalis-cogitator-llama-3.1-8b-Q6_K_L.gguf](https://huggingface.co/bartowski/Locutusque_liberalis-cogitator-llama-3.1-8b-GGUF/blob/main/Locutusque_liberalis-cogitator-llama-3.1-8b-Q6_K_L.gguf) | Q6_K_L | 6.85GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. |
| [liberalis-cogitator-llama-3.1-8b-Q6_K.gguf](https://huggingface.co/bartowski/Locutusque_liberalis-cogitator-llama-3.1-8b-GGUF/blob/main/Locutusque_liberalis-cogitator-llama-3.1-8b-Q6_K.gguf) | Q6_K | 6.60GB | false | Very high quality, near perfect, *recommended*. |
| [liberalis-cogitator-llama-3.1-8b-Q5_K_L.gguf](https://huggingface.co/bartowski/Locutusque_liberalis-cogitator-llama-3.1-8b-GGUF/blob/main/Locutusque_liberalis-cogitator-llama-3.1-8b-Q5_K_L.gguf) | Q5_K_L | 6.06GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. |
| [liberalis-cogitator-llama-3.1-8b-Q5_K_M.gguf](https://huggingface.co/bartowski/Locutusque_liberalis-cogitator-llama-3.1-8b-GGUF/blob/main/Locutusque_liberalis-cogitator-llama-3.1-8b-Q5_K_M.gguf) | Q5_K_M | 5.73GB | false | High quality, *recommended*. |
| [liberalis-cogitator-llama-3.1-8b-Q5_K_S.gguf](https://huggingface.co/bartowski/Locutusque_liberalis-cogitator-llama-3.1-8b-GGUF/blob/main/Locutusque_liberalis-cogitator-llama-3.1-8b-Q5_K_S.gguf) | Q5_K_S | 5.60GB | false | High quality, *recommended*. |
| [liberalis-cogitator-llama-3.1-8b-Q4_K_L.gguf](https://huggingface.co/bartowski/Locutusque_liberalis-cogitator-llama-3.1-8b-GGUF/blob/main/Locutusque_liberalis-cogitator-llama-3.1-8b-Q4_K_L.gguf) | Q4_K_L | 5.31GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. |
| [liberalis-cogitator-llama-3.1-8b-Q4_1.gguf](https://huggingface.co/bartowski/Locutusque_liberalis-cogitator-llama-3.1-8b-GGUF/blob/main/Locutusque_liberalis-cogitator-llama-3.1-8b-Q4_1.gguf) | Q4_1 | 5.13GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. |
| [liberalis-cogitator-llama-3.1-8b-Q4_K_M.gguf](https://huggingface.co/bartowski/Locutusque_liberalis-cogitator-llama-3.1-8b-GGUF/blob/main/Locutusque_liberalis-cogitator-llama-3.1-8b-Q4_K_M.gguf) | Q4_K_M | 4.92GB | false | Good quality, default size for most use cases, *recommended*. |
| [liberalis-cogitator-llama-3.1-8b-Q3_K_XL.gguf](https://huggingface.co/bartowski/Locutusque_liberalis-cogitator-llama-3.1-8b-GGUF/blob/main/Locutusque_liberalis-cogitator-llama-3.1-8b-Q3_K_XL.gguf) | Q3_K_XL | 4.78GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. |
| [liberalis-cogitator-llama-3.1-8b-Q4_K_S.gguf](https://huggingface.co/bartowski/Locutusque_liberalis-cogitator-llama-3.1-8b-GGUF/blob/main/Locutusque_liberalis-cogitator-llama-3.1-8b-Q4_K_S.gguf) | Q4_K_S | 4.69GB | false | Slightly lower quality with more space savings, *recommended*. |
| [liberalis-cogitator-llama-3.1-8b-Q4_0.gguf](https://huggingface.co/bartowski/Locutusque_liberalis-cogitator-llama-3.1-8b-GGUF/blob/main/Locutusque_liberalis-cogitator-llama-3.1-8b-Q4_0.gguf) | Q4_0 | 4.68GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. |
| [liberalis-cogitator-llama-3.1-8b-IQ4_NL.gguf](https://huggingface.co/bartowski/Locutusque_liberalis-cogitator-llama-3.1-8b-GGUF/blob/main/Locutusque_liberalis-cogitator-llama-3.1-8b-IQ4_NL.gguf) | IQ4_NL | 4.68GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. |
| [liberalis-cogitator-llama-3.1-8b-IQ4_XS.gguf](https://huggingface.co/bartowski/Locutusque_liberalis-cogitator-llama-3.1-8b-GGUF/blob/main/Locutusque_liberalis-cogitator-llama-3.1-8b-IQ4_XS.gguf) | IQ4_XS | 4.45GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
| [liberalis-cogitator-llama-3.1-8b-Q3_K_L.gguf](https://huggingface.co/bartowski/Locutusque_liberalis-cogitator-llama-3.1-8b-GGUF/blob/main/Locutusque_liberalis-cogitator-llama-3.1-8b-Q3_K_L.gguf) | Q3_K_L | 4.32GB | false | Lower quality but usable, good for low RAM availability. |
| [liberalis-cogitator-llama-3.1-8b-Q3_K_M.gguf](https://huggingface.co/bartowski/Locutusque_liberalis-cogitator-llama-3.1-8b-GGUF/blob/main/Locutusque_liberalis-cogitator-llama-3.1-8b-Q3_K_M.gguf) | Q3_K_M | 4.02GB | false | Low quality. |
| [liberalis-cogitator-llama-3.1-8b-IQ3_M.gguf](https://huggingface.co/bartowski/Locutusque_liberalis-cogitator-llama-3.1-8b-GGUF/blob/main/Locutusque_liberalis-cogitator-llama-3.1-8b-IQ3_M.gguf) | IQ3_M | 3.78GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
| [liberalis-cogitator-llama-3.1-8b-Q2_K_L.gguf](https://huggingface.co/bartowski/Locutusque_liberalis-cogitator-llama-3.1-8b-GGUF/blob/main/Locutusque_liberalis-cogitator-llama-3.1-8b-Q2_K_L.gguf) | Q2_K_L | 3.69GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. |
| [liberalis-cogitator-llama-3.1-8b-Q3_K_S.gguf](https://huggingface.co/bartowski/Locutusque_liberalis-cogitator-llama-3.1-8b-GGUF/blob/main/Locutusque_liberalis-cogitator-llama-3.1-8b-Q3_K_S.gguf) | Q3_K_S | 3.66GB | false | Low quality, not recommended. |
| [liberalis-cogitator-llama-3.1-8b-IQ3_XS.gguf](https://huggingface.co/bartowski/Locutusque_liberalis-cogitator-llama-3.1-8b-GGUF/blob/main/Locutusque_liberalis-cogitator-llama-3.1-8b-IQ3_XS.gguf) | IQ3_XS | 3.52GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
| [liberalis-cogitator-llama-3.1-8b-IQ3_XXS.gguf](https://huggingface.co/bartowski/Locutusque_liberalis-cogitator-llama-3.1-8b-GGUF/blob/main/Locutusque_liberalis-cogitator-llama-3.1-8b-IQ3_XXS.gguf) | IQ3_XXS | 3.27GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. |
| [liberalis-cogitator-llama-3.1-8b-Q2_K.gguf](https://huggingface.co/bartowski/Locutusque_liberalis-cogitator-llama-3.1-8b-GGUF/blob/main/Locutusque_liberalis-cogitator-llama-3.1-8b-Q2_K.gguf) | Q2_K | 3.18GB | false | Very low quality but surprisingly usable. |
| [liberalis-cogitator-llama-3.1-8b-IQ2_M.gguf](https://huggingface.co/bartowski/Locutusque_liberalis-cogitator-llama-3.1-8b-GGUF/blob/main/Locutusque_liberalis-cogitator-llama-3.1-8b-IQ2_M.gguf) | IQ2_M | 2.95GB | 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/Locutusque_liberalis-cogitator-llama-3.1-8b-GGUF --include "Locutusque_liberalis-cogitator-llama-3.1-8b-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/Locutusque_liberalis-cogitator-llama-3.1-8b-GGUF --include "Locutusque_liberalis-cogitator-llama-3.1-8b-Q8_0/*" --local-dir ./
```
You can either specify a new local-dir (Locutusque_liberalis-cogitator-llama-3.1-8b-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}