bartowski/AGI-0_Art-0-8B-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/AGI-0_Art-0-8B-GGUF
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-08-19 00:25:16 +08:00
commit 67d0f3a1c3
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
AGI-0_Art-0-8B-IQ2_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1fde84507ae7a1f4b22afa5ad8fbd300c65a569ad34a81bc1946246babffbf0e
size 3051914336

3
AGI-0_Art-0-8B-IQ3_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:46ffaa1e5b1cede2524e3105fbc5e57ec4ed1620e40c0fe2aa65a4e267027509
size 3896620128

3
AGI-0_Art-0-8B-IQ3_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2d8249ed203e596e7dede557bfdfc869e041149207a7d453f9aa3895c1d4e450
size 3626873952

3
AGI-0_Art-0-8B-IQ3_XXS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:add58bf277dea86cd4604147980c5df162212626f64bf5a50cf42b787a9fb89e
size 3369632864

3
AGI-0_Art-0-8B-IQ4_NL.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1869d17f91b8534f28d801f2f74b71d00ab077e24bebc930c26a0aeea8aeef32
size 4793623648

3
AGI-0_Art-0-8B-IQ4_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:49f6d552f8dea3193cc522790edf0fcfb68543dee17d5c251abf9ed28824ca0e
size 4561839200

3
AGI-0_Art-0-8B-Q2_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:442250b7fb810255bc81c722bae76302ce2395074c25da51b1e38ba9f8072070
size 3281732704

3
AGI-0_Art-0-8B-Q2_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:74fc25439c983dee0c2ba8777fcab6d6e9242def99001528a68126abde0145b0
size 3889476704

3
AGI-0_Art-0-8B-Q3_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ff92629fcaf4fa51f7568a150df05f7c4ce91b93d029517a6bfe80e85cee5cb3
size 4431393888

3
AGI-0_Art-0-8B-Q3_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3d8a1eaafa0b086eec02caa02bf2340a8491ad7ea26f6376a5f19ea2a37e9ca0
size 4124161120

3
AGI-0_Art-0-8B-Q3_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:bce108f1771cf5b34a91fe6ce1ded055827e3f76d53b72eb0250845188656ffd
size 3769611360

3
AGI-0_Art-0-8B-Q3_K_XL.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0b07319b58e23dda70db7aff8aa49b41a794e6a93184b6c0b694d800fdc05219
size 4975932512

3
AGI-0_Art-0-8B-Q4_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f8fe3242e497914ce9a8e9959048e197b3c4124fbc4dcf210f017d9e18332ad4
size 4787332192

3
AGI-0_Art-0-8B-Q4_1.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3ab4f41879a9a4dd26173a96fbb8a59ea32cb91f090a75b168f760bddb9d50ad
size 5247755360

3
AGI-0_Art-0-8B-Q4_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1de8c586675c66b96e36834b26c6942f2243325ebd47b12b37e550844f46da49
size 5489669216

3
AGI-0_Art-0-8B-Q4_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5564844350b0c5370c97583f6a8e5b29f642e9b03236a1e427ab42b64cad4efa
size 5027783776

3
AGI-0_Art-0-8B-Q4_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:33bacec1b863d9effdaa1f9e8732d563ac3558e565786ecc1ef775916b387f1c
size 4802012256

3
AGI-0_Art-0-8B-Q5_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e8b1ea7c9a7f0c8a39b31bba36dd89f8333a9bc56c8dd1f569aac3ee3b0c0810
size 6235206752

3
AGI-0_Art-0-8B-Q5_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5c9e3ab98bda2ff735b82dd53350d899aa8a541d6afa35dcea118fad158a8b21
size 5851112544

3
AGI-0_Art-0-8B-Q5_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:bb8a20148cf885b7cfc704c00dea66507d71ccdb7ce28646286a5662488d1bc3
size 5720761440

3
AGI-0_Art-0-8B-Q6_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e4ca2f864809b375f84850db3978c1fbd0861b28da5cc6002abca285149705a4
size 6725899360

3
AGI-0_Art-0-8B-Q6_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0acb72f3eff05a4308afe7a5e834ac5ad3beeb1c0e289e1ff882c9aa6fc53a50
size 7027340384

3
AGI-0_Art-0-8B-Q8_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:191b627acfbb4239991624a70568822db82ec1c985b758100b232211a0760b23
size 8709518432

3
AGI-0_Art-0-8B-bf16.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:6f615b46b3926b5b886448452a6e6ef45bfd9ec7b8fc84b689142c97228e7262
size 16388043616

3
AGI-0_Art-0-8B-imatrix.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9baae88c411f930ea0dea2368da1c63220fbebe8b52f44820e79cb24cd927f08
size 5347200

164
README.md Normal file
View File

@@ -0,0 +1,164 @@
---
quantized_by: bartowski
pipeline_tag: text-generation
base_model_relation: quantized
base_model: AGI-0/Art-0-8B
---
## Llamacpp imatrix Quantizations of Art-0-8B by AGI-0
Using <a href="https://github.com/ggml-org/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggml-org/llama.cpp/releases/tag/b6317">b6317</a> for quantization.
Original model: https://huggingface.co/AGI-0/Art-0-8B
All quants made using imatrix option with dataset from [here](https://gist.github.com/bartowski1182/eb213dccb3571f863da82e99418f81e8) combined with a subset of combined_all_small.parquet from Ed Addario [here](https://huggingface.co/datasets/eaddario/imatrix-calibration/blob/main/combined_all_small.parquet)
Run them in [LM Studio](https://lmstudio.ai/)
Run them directly with [llama.cpp](https://github.com/ggml-org/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 |
| -------- | ---------- | --------- | ----- | ----------- |
| [Art-0-8B-bf16.gguf](https://huggingface.co/bartowski/AGI-0_Art-0-8B-GGUF/blob/main/AGI-0_Art-0-8B-bf16.gguf) | bf16 | 16.39GB | false | Full BF16 weights. |
| [Art-0-8B-Q8_0.gguf](https://huggingface.co/bartowski/AGI-0_Art-0-8B-GGUF/blob/main/AGI-0_Art-0-8B-Q8_0.gguf) | Q8_0 | 8.71GB | false | Extremely high quality, generally unneeded but max available quant. |
| [Art-0-8B-Q6_K_L.gguf](https://huggingface.co/bartowski/AGI-0_Art-0-8B-GGUF/blob/main/AGI-0_Art-0-8B-Q6_K_L.gguf) | Q6_K_L | 7.03GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. |
| [Art-0-8B-Q6_K.gguf](https://huggingface.co/bartowski/AGI-0_Art-0-8B-GGUF/blob/main/AGI-0_Art-0-8B-Q6_K.gguf) | Q6_K | 6.73GB | false | Very high quality, near perfect, *recommended*. |
| [Art-0-8B-Q5_K_L.gguf](https://huggingface.co/bartowski/AGI-0_Art-0-8B-GGUF/blob/main/AGI-0_Art-0-8B-Q5_K_L.gguf) | Q5_K_L | 6.24GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. |
| [Art-0-8B-Q5_K_M.gguf](https://huggingface.co/bartowski/AGI-0_Art-0-8B-GGUF/blob/main/AGI-0_Art-0-8B-Q5_K_M.gguf) | Q5_K_M | 5.85GB | false | High quality, *recommended*. |
| [Art-0-8B-Q5_K_S.gguf](https://huggingface.co/bartowski/AGI-0_Art-0-8B-GGUF/blob/main/AGI-0_Art-0-8B-Q5_K_S.gguf) | Q5_K_S | 5.72GB | false | High quality, *recommended*. |
| [Art-0-8B-Q4_K_L.gguf](https://huggingface.co/bartowski/AGI-0_Art-0-8B-GGUF/blob/main/AGI-0_Art-0-8B-Q4_K_L.gguf) | Q4_K_L | 5.49GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. |
| [Art-0-8B-Q4_1.gguf](https://huggingface.co/bartowski/AGI-0_Art-0-8B-GGUF/blob/main/AGI-0_Art-0-8B-Q4_1.gguf) | Q4_1 | 5.25GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. |
| [Art-0-8B-Q4_K_M.gguf](https://huggingface.co/bartowski/AGI-0_Art-0-8B-GGUF/blob/main/AGI-0_Art-0-8B-Q4_K_M.gguf) | Q4_K_M | 5.03GB | false | Good quality, default size for most use cases, *recommended*. |
| [Art-0-8B-Q3_K_XL.gguf](https://huggingface.co/bartowski/AGI-0_Art-0-8B-GGUF/blob/main/AGI-0_Art-0-8B-Q3_K_XL.gguf) | Q3_K_XL | 4.98GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. |
| [Art-0-8B-Q4_K_S.gguf](https://huggingface.co/bartowski/AGI-0_Art-0-8B-GGUF/blob/main/AGI-0_Art-0-8B-Q4_K_S.gguf) | Q4_K_S | 4.80GB | false | Slightly lower quality with more space savings, *recommended*. |
| [Art-0-8B-Q4_0.gguf](https://huggingface.co/bartowski/AGI-0_Art-0-8B-GGUF/blob/main/AGI-0_Art-0-8B-Q4_0.gguf) | Q4_0 | 4.79GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. |
| [Art-0-8B-IQ4_NL.gguf](https://huggingface.co/bartowski/AGI-0_Art-0-8B-GGUF/blob/main/AGI-0_Art-0-8B-IQ4_NL.gguf) | IQ4_NL | 4.79GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. |
| [Art-0-8B-IQ4_XS.gguf](https://huggingface.co/bartowski/AGI-0_Art-0-8B-GGUF/blob/main/AGI-0_Art-0-8B-IQ4_XS.gguf) | IQ4_XS | 4.56GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
| [Art-0-8B-Q3_K_L.gguf](https://huggingface.co/bartowski/AGI-0_Art-0-8B-GGUF/blob/main/AGI-0_Art-0-8B-Q3_K_L.gguf) | Q3_K_L | 4.43GB | false | Lower quality but usable, good for low RAM availability. |
| [Art-0-8B-Q3_K_M.gguf](https://huggingface.co/bartowski/AGI-0_Art-0-8B-GGUF/blob/main/AGI-0_Art-0-8B-Q3_K_M.gguf) | Q3_K_M | 4.12GB | false | Low quality. |
| [Art-0-8B-IQ3_M.gguf](https://huggingface.co/bartowski/AGI-0_Art-0-8B-GGUF/blob/main/AGI-0_Art-0-8B-IQ3_M.gguf) | IQ3_M | 3.90GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
| [Art-0-8B-Q2_K_L.gguf](https://huggingface.co/bartowski/AGI-0_Art-0-8B-GGUF/blob/main/AGI-0_Art-0-8B-Q2_K_L.gguf) | Q2_K_L | 3.89GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. |
| [Art-0-8B-Q3_K_S.gguf](https://huggingface.co/bartowski/AGI-0_Art-0-8B-GGUF/blob/main/AGI-0_Art-0-8B-Q3_K_S.gguf) | Q3_K_S | 3.77GB | false | Low quality, not recommended. |
| [Art-0-8B-IQ3_XS.gguf](https://huggingface.co/bartowski/AGI-0_Art-0-8B-GGUF/blob/main/AGI-0_Art-0-8B-IQ3_XS.gguf) | IQ3_XS | 3.63GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
| [Art-0-8B-IQ3_XXS.gguf](https://huggingface.co/bartowski/AGI-0_Art-0-8B-GGUF/blob/main/AGI-0_Art-0-8B-IQ3_XXS.gguf) | IQ3_XXS | 3.37GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. |
| [Art-0-8B-Q2_K.gguf](https://huggingface.co/bartowski/AGI-0_Art-0-8B-GGUF/blob/main/AGI-0_Art-0-8B-Q2_K.gguf) | Q2_K | 3.28GB | false | Very low quality but surprisingly usable. |
| [Art-0-8B-IQ2_M.gguf](https://huggingface.co/bartowski/AGI-0_Art-0-8B-GGUF/blob/main/AGI-0_Art-0-8B-IQ2_M.gguf) | IQ2_M | 3.05GB | 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-0-8B-GGUF --include "AGI-0_Art-0-8B-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/AGI-0_Art-0-8B-GGUF --include "AGI-0_Art-0-8B-Q8_0/*" --local-dir ./
```
You can either specify a new local-dir (AGI-0_Art-0-8B-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/ggml-org/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/ggml-org/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/ggml-org/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/ggml-org/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}