bartowski/Delta-Vector_Archaeo-12B-V2-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/Delta-Vector_Archaeo-12B-V2-GGUF
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-10-02 01:51:14 +08:00
commit dfb4ef9a48
29 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
Delta-Vector_Archaeo-12B-V2.imatrix filter=lfs diff=lfs merge=lfs -text

3
Delta-Vector_Archaeo-12B-V2-IQ2_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:fbcb4a1824ca2f2d929f69714738abe7a17f7314837f876b70f9ec6cef5217d3
size 4435027232

3
Delta-Vector_Archaeo-12B-V2-IQ2_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:68c8afb31276722581946b006b21febfde285b171d6f9915836e86451f62372b
size 4138476832

3
Delta-Vector_Archaeo-12B-V2-IQ3_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:020c981f776e0d563075944bebe77c4161a0319ca0957a50777fbdec7a330d30
size 5722236192

3
Delta-Vector_Archaeo-12B-V2-IQ3_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:cf6508cf4eed2f4f478548b2a33ccb40fc904329bcce009ea54ac59ec43fd574
size 5306492192

3
Delta-Vector_Archaeo-12B-V2-IQ3_XXS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:44b1fb6e712da145f1636484c9c1328a138dded8b53ff775d5c3a4b72ee0282d
size 4945388832

3
Delta-Vector_Archaeo-12B-V2-IQ4_NL.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:90317bee8c287331295d0a5287641ef2b4ba248db7d91fd1be73990bdd77267d
size 7097918752

3
Delta-Vector_Archaeo-12B-V2-IQ4_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:39eecb234ef3ec5984f48ffde91d50a72855e812686655e495249051dcd2b01e
size 6742713632

3
Delta-Vector_Archaeo-12B-V2-Q2_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:6d0d7e9ec7fcec989e3d91c2ca43818d780a9d3024d99ea95ad7af2ae1e75c7f
size 4791051552

3
Delta-Vector_Archaeo-12B-V2-Q2_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b966766a8ce47944658377f5ae99a91610134d0b4b7fb4f855c0f3ba73bc8c56
size 5446411552

3
Delta-Vector_Archaeo-12B-V2-Q3_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:aeff377ca72a0ac72d785b52f4b9d973ec1c2dfa6b6a057f85bf22cf60d3de5a
size 6561506592

3
Delta-Vector_Archaeo-12B-V2-Q3_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d22a90c0f96cdf74abdd9750cf28d052f6aed0bde89bc46ccd16609b286d63d2
size 6083093792

3
Delta-Vector_Archaeo-12B-V2-Q3_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:6961405eb5595715efcd2a42a6be7c10cfbcfef67d2f9629149970b8b01dd557
size 5534229792

3
Delta-Vector_Archaeo-12B-V2-Q3_K_XL.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:10ac9c0129f61cf33d0e6e166f6183b9d2df65ddd7829ebc21628a69a3c8bbec
size 7148709152

3
Delta-Vector_Archaeo-12B-V2-Q4_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:711ffe516340b1492fce7c4d2ddd9a13a01c10f358db6edb8ac8ebd8dcd83789
size 7094641952

3
Delta-Vector_Archaeo-12B-V2-Q4_1.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:637d6867b07eaec514b0db8fae78e0ada8596c635934b59899face37e85a559d
size 7795221792

3
Delta-Vector_Archaeo-12B-V2-Q4_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:26964e72abd579f9c276598fd6ea83f7346e067c9beec1a1fe69d408db71b200
size 7975281952

3
Delta-Vector_Archaeo-12B-V2-Q4_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2b0c8cb3a65b36d2fc0abe47c84a4adda91b890d9f984ca31e4a53e08cfffb8c
size 7477208352

3
Delta-Vector_Archaeo-12B-V2-Q4_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:cef439e5661e4ca35affc778b3ecb97c77a1049e19477433a4765435e67dd05d
size 7120200992

3
Delta-Vector_Archaeo-12B-V2-Q5_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:92f4a84d5b4e3f2ba4fda024ac6dab2aa6232a3c3ab3f11b13eb83036dce2bb0
size 9141822752

3
Delta-Vector_Archaeo-12B-V2-Q5_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:8a7cab8f5182708f028b445cf230a0761a4be021618abaac19dfc265b7b7ac0a
size 8727635232

3
Delta-Vector_Archaeo-12B-V2-Q5_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2de916bbb4cd29244d0fedab489c8e5e9d99da0539898180993260ecf2b4506b
size 8518739232

3
Delta-Vector_Archaeo-12B-V2-Q6_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:62f01c95d2554f7fa33af8ba323c9a468b70b1631c2a942d9543843eb33dddab
size 10056213792

3
Delta-Vector_Archaeo-12B-V2-Q6_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9b23dc613950acf33c61553dfbd27180291f98e11c0c3bd5ff2197fdd4763318
size 10381272352

3
Delta-Vector_Archaeo-12B-V2-Q8_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f40706eaaf7229a26f9602b3a5465d21637de27b72608419f89ca4b2f9312d6b
size 13022373152

3
Delta-Vector_Archaeo-12B-V2-bf16.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:97171011c820d5a53da2d5a8165bdb92cebaf26960b0e76b84ce347979403a66
size 24504280064

3
Delta-Vector_Archaeo-12B-V2.imatrix Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9bbc3255f8216e09f570ede14fc04140937f8e1d67495f1310e1a9863db814d2
size 7054418

172
README.md Normal file
View File

@@ -0,0 +1,172 @@
---
quantized_by: bartowski
pipeline_tag: text-generation
base_model: Delta-Vector/Archaeo-12B-V2
tags:
- roleplay
- creative-writing
- merge
- mergekit
base_model_relation: quantized
---
## Llamacpp imatrix Quantizations of Archaeo-12B-V2 by Delta-Vector
Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b5432">b5432</a> for quantization.
Original model: https://huggingface.co/Delta-Vector/Archaeo-12B-V2
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
```
<s><|im_start|>user{prompt}<|im_start|>assistant
```
## Download a file (not the whole branch) from below:
| Filename | Quant type | File Size | Split | Description |
| -------- | ---------- | --------- | ----- | ----------- |
| [Archaeo-12B-V2-bf16.gguf](https://huggingface.co/bartowski/Delta-Vector_Archaeo-12B-V2-GGUF/blob/main/Delta-Vector_Archaeo-12B-V2-bf16.gguf) | bf16 | 24.50GB | false | Full BF16 weights. |
| [Archaeo-12B-V2-Q8_0.gguf](https://huggingface.co/bartowski/Delta-Vector_Archaeo-12B-V2-GGUF/blob/main/Delta-Vector_Archaeo-12B-V2-Q8_0.gguf) | Q8_0 | 13.02GB | false | Extremely high quality, generally unneeded but max available quant. |
| [Archaeo-12B-V2-Q6_K_L.gguf](https://huggingface.co/bartowski/Delta-Vector_Archaeo-12B-V2-GGUF/blob/main/Delta-Vector_Archaeo-12B-V2-Q6_K_L.gguf) | Q6_K_L | 10.38GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. |
| [Archaeo-12B-V2-Q6_K.gguf](https://huggingface.co/bartowski/Delta-Vector_Archaeo-12B-V2-GGUF/blob/main/Delta-Vector_Archaeo-12B-V2-Q6_K.gguf) | Q6_K | 10.06GB | false | Very high quality, near perfect, *recommended*. |
| [Archaeo-12B-V2-Q5_K_L.gguf](https://huggingface.co/bartowski/Delta-Vector_Archaeo-12B-V2-GGUF/blob/main/Delta-Vector_Archaeo-12B-V2-Q5_K_L.gguf) | Q5_K_L | 9.14GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. |
| [Archaeo-12B-V2-Q5_K_M.gguf](https://huggingface.co/bartowski/Delta-Vector_Archaeo-12B-V2-GGUF/blob/main/Delta-Vector_Archaeo-12B-V2-Q5_K_M.gguf) | Q5_K_M | 8.73GB | false | High quality, *recommended*. |
| [Archaeo-12B-V2-Q5_K_S.gguf](https://huggingface.co/bartowski/Delta-Vector_Archaeo-12B-V2-GGUF/blob/main/Delta-Vector_Archaeo-12B-V2-Q5_K_S.gguf) | Q5_K_S | 8.52GB | false | High quality, *recommended*. |
| [Archaeo-12B-V2-Q4_K_L.gguf](https://huggingface.co/bartowski/Delta-Vector_Archaeo-12B-V2-GGUF/blob/main/Delta-Vector_Archaeo-12B-V2-Q4_K_L.gguf) | Q4_K_L | 7.98GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. |
| [Archaeo-12B-V2-Q4_1.gguf](https://huggingface.co/bartowski/Delta-Vector_Archaeo-12B-V2-GGUF/blob/main/Delta-Vector_Archaeo-12B-V2-Q4_1.gguf) | Q4_1 | 7.80GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. |
| [Archaeo-12B-V2-Q4_K_M.gguf](https://huggingface.co/bartowski/Delta-Vector_Archaeo-12B-V2-GGUF/blob/main/Delta-Vector_Archaeo-12B-V2-Q4_K_M.gguf) | Q4_K_M | 7.48GB | false | Good quality, default size for most use cases, *recommended*. |
| [Archaeo-12B-V2-Q3_K_XL.gguf](https://huggingface.co/bartowski/Delta-Vector_Archaeo-12B-V2-GGUF/blob/main/Delta-Vector_Archaeo-12B-V2-Q3_K_XL.gguf) | Q3_K_XL | 7.15GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. |
| [Archaeo-12B-V2-Q4_K_S.gguf](https://huggingface.co/bartowski/Delta-Vector_Archaeo-12B-V2-GGUF/blob/main/Delta-Vector_Archaeo-12B-V2-Q4_K_S.gguf) | Q4_K_S | 7.12GB | false | Slightly lower quality with more space savings, *recommended*. |
| [Archaeo-12B-V2-IQ4_NL.gguf](https://huggingface.co/bartowski/Delta-Vector_Archaeo-12B-V2-GGUF/blob/main/Delta-Vector_Archaeo-12B-V2-IQ4_NL.gguf) | IQ4_NL | 7.10GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. |
| [Archaeo-12B-V2-Q4_0.gguf](https://huggingface.co/bartowski/Delta-Vector_Archaeo-12B-V2-GGUF/blob/main/Delta-Vector_Archaeo-12B-V2-Q4_0.gguf) | Q4_0 | 7.09GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. |
| [Archaeo-12B-V2-IQ4_XS.gguf](https://huggingface.co/bartowski/Delta-Vector_Archaeo-12B-V2-GGUF/blob/main/Delta-Vector_Archaeo-12B-V2-IQ4_XS.gguf) | IQ4_XS | 6.74GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
| [Archaeo-12B-V2-Q3_K_L.gguf](https://huggingface.co/bartowski/Delta-Vector_Archaeo-12B-V2-GGUF/blob/main/Delta-Vector_Archaeo-12B-V2-Q3_K_L.gguf) | Q3_K_L | 6.56GB | false | Lower quality but usable, good for low RAM availability. |
| [Archaeo-12B-V2-Q3_K_M.gguf](https://huggingface.co/bartowski/Delta-Vector_Archaeo-12B-V2-GGUF/blob/main/Delta-Vector_Archaeo-12B-V2-Q3_K_M.gguf) | Q3_K_M | 6.08GB | false | Low quality. |
| [Archaeo-12B-V2-IQ3_M.gguf](https://huggingface.co/bartowski/Delta-Vector_Archaeo-12B-V2-GGUF/blob/main/Delta-Vector_Archaeo-12B-V2-IQ3_M.gguf) | IQ3_M | 5.72GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
| [Archaeo-12B-V2-Q3_K_S.gguf](https://huggingface.co/bartowski/Delta-Vector_Archaeo-12B-V2-GGUF/blob/main/Delta-Vector_Archaeo-12B-V2-Q3_K_S.gguf) | Q3_K_S | 5.53GB | false | Low quality, not recommended. |
| [Archaeo-12B-V2-Q2_K_L.gguf](https://huggingface.co/bartowski/Delta-Vector_Archaeo-12B-V2-GGUF/blob/main/Delta-Vector_Archaeo-12B-V2-Q2_K_L.gguf) | Q2_K_L | 5.45GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. |
| [Archaeo-12B-V2-IQ3_XS.gguf](https://huggingface.co/bartowski/Delta-Vector_Archaeo-12B-V2-GGUF/blob/main/Delta-Vector_Archaeo-12B-V2-IQ3_XS.gguf) | IQ3_XS | 5.31GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
| [Archaeo-12B-V2-IQ3_XXS.gguf](https://huggingface.co/bartowski/Delta-Vector_Archaeo-12B-V2-GGUF/blob/main/Delta-Vector_Archaeo-12B-V2-IQ3_XXS.gguf) | IQ3_XXS | 4.95GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. |
| [Archaeo-12B-V2-Q2_K.gguf](https://huggingface.co/bartowski/Delta-Vector_Archaeo-12B-V2-GGUF/blob/main/Delta-Vector_Archaeo-12B-V2-Q2_K.gguf) | Q2_K | 4.79GB | false | Very low quality but surprisingly usable. |
| [Archaeo-12B-V2-IQ2_M.gguf](https://huggingface.co/bartowski/Delta-Vector_Archaeo-12B-V2-GGUF/blob/main/Delta-Vector_Archaeo-12B-V2-IQ2_M.gguf) | IQ2_M | 4.44GB | false | Relatively low quality, uses SOTA techniques to be surprisingly usable. |
| [Archaeo-12B-V2-IQ2_S.gguf](https://huggingface.co/bartowski/Delta-Vector_Archaeo-12B-V2-GGUF/blob/main/Delta-Vector_Archaeo-12B-V2-IQ2_S.gguf) | IQ2_S | 4.14GB | 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.
## 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/Delta-Vector_Archaeo-12B-V2-GGUF --include "Delta-Vector_Archaeo-12B-V2-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/Delta-Vector_Archaeo-12B-V2-GGUF --include "Delta-Vector_Archaeo-12B-V2-Q8_0/*" --local-dir ./
```
You can either specify a new local-dir (Delta-Vector_Archaeo-12B-V2-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}