bartowski/LatitudeGames_Wayfarer-2-12B-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/LatitudeGames_Wayfarer-2-12B-GGUF
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-09-01 00:27:14 +08:00
commit f6efed65b7
29 changed files with 291 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
LatitudeGames_Wayfarer-2-12B-IQ2_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:33ecfe79d1ff7b7ddf2daadab59290f526bcfadb43fea1f22cb90e3dda3f654b
size 4435034880

3
LatitudeGames_Wayfarer-2-12B-IQ2_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5ad663871f2363316610587b4cd9264f4747a6e1fdaea95d86dde51a8ec19a84
size 4138484480

3
LatitudeGames_Wayfarer-2-12B-IQ3_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:8c3eb044a0063fec6f07ec44736e293abe51aea6bf042fe5bf1170ea11307584
size 5722245216

3
LatitudeGames_Wayfarer-2-12B-IQ3_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c10f45b3737bf9fa400e0c8bb4343446135a532fe5493e087e901f93533e2822
size 5306501216

3
LatitudeGames_Wayfarer-2-12B-IQ3_XXS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:51c0daaf8ed77e90d32fe4418dca6881e61c8d1f12b403f8fe13ac0500fee043
size 4945396480

3
LatitudeGames_Wayfarer-2-12B-IQ4_NL.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3dc3a8335ec467544710c92c08b6db095498ae7858b2344ff128a7f6d5df3800
size 7097929120

3
LatitudeGames_Wayfarer-2-12B-IQ4_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2227af939b938774b267e9677c898a60c33224e7ba6f85236dc386878c9e548b
size 6742723680

3
LatitudeGames_Wayfarer-2-12B-Q2_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:754986145abfc465e7ce60e714868110c0a04e52a0a165b1bd2da684cf7e15b6
size 4791059520

3
LatitudeGames_Wayfarer-2-12B-Q2_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f1bfaaac890332d75bf5327499fc8412d2e1fe5cda48e2d9448d5e4ee01d8e4b
size 5446429504

3
LatitudeGames_Wayfarer-2-12B-Q3_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9bf06d4255999f647dfd8d18e6aa2fbeda6008572d1b798d861b205539e99d66
size 6561515616

3
LatitudeGames_Wayfarer-2-12B-Q3_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:36120023054d24b7359c8a23d89f3b39ef76fc49e4c7d26d72873d6ea4cfc03c
size 6083102816

3
LatitudeGames_Wayfarer-2-12B-Q3_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ff81184de108a9360106729baefccc2ed34aa2cde6c309c50b044b6d8dff6a71
size 5534238816

3
LatitudeGames_Wayfarer-2-12B-Q3_K_XL.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:25c641b07116a2a78147bc725f0e0cf25a7b02be23049462882251c3d119e3ef
size 7148727104

3
LatitudeGames_Wayfarer-2-12B-Q4_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:476af84bfc44590eade999eb3658323aea2658930156f63e489f15e18e629311
size 7094652320

3
LatitudeGames_Wayfarer-2-12B-Q4_1.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3ecf314222b6caf98f2c3de72acf34e5615beb92df61e19d195a375bfd4d4fee
size 7795232800

3
LatitudeGames_Wayfarer-2-12B-Q4_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2b3118aa5a97e6b40a35336f264cf29d846b310d7c5886515727f3b3bab79ed1
size 7975299904

3
LatitudeGames_Wayfarer-2-12B-Q4_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ddec1e6fa3b98afcbd44caa479f1a2afb26bee88381f89b5b4b8e7ed6f60db03
size 7477218720

3
LatitudeGames_Wayfarer-2-12B-Q4_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ee17a706748fd108f3abad9abb37ff361e46aef6fac0f098467f70ea5a17aec4
size 7120211360

3
LatitudeGames_Wayfarer-2-12B-Q5_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e04dbe2b515bae44d91d39af8eadc796d5d07e4b3638c76ec015a3fd56136394
size 9141840704

3
LatitudeGames_Wayfarer-2-12B-Q5_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:689ce5f5e2f0449e68441614b64da0c7bbe19c9c4cb26c0927765a27766df03c
size 8727646880

3
LatitudeGames_Wayfarer-2-12B-Q5_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:116ee968ede409e396d2f71ef7f8bc5ee295b143fcfe630bfc7c6bf3ff51b0ec
size 8518750880

3
LatitudeGames_Wayfarer-2-12B-Q6_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e9ee848f02081301051461c9d79ed240c02808a19ce12beea46bf1fe733ad5ac
size 10056226816

3
LatitudeGames_Wayfarer-2-12B-Q6_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:dc1adc53bc66f223ad5f65a737316fbd3c87b48874fb693af8c0233940af590e
size 10381290304

3
LatitudeGames_Wayfarer-2-12B-Q8_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:8ae9b1c4090fa8d1be79f6867fc533cdf372425be714d2c38208500fc1b6abcf
size 13022391104

3
LatitudeGames_Wayfarer-2-12B-bf16.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:08cec90d4390ed6de924da186b119d04dd9f30a6115f76683a3d82eb94324138
size 24504317216

3
LatitudeGames_Wayfarer-2-12B-imatrix.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:598b0345a934aed4ff2a6965393749c78417c2b8af87b18c1af71f1ec352492f
size 7088224

165
README.md Normal file
View File

@@ -0,0 +1,165 @@
---
quantized_by: bartowski
pipeline_tag: text-generation
base_model: LatitudeGames/Wayfarer-2-12B
base_model_relation: quantized
---
## Llamacpp imatrix Quantizations of Wayfarer-2-12B by LatitudeGames
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/LatitudeGames/Wayfarer-2-12B
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 |
| -------- | ---------- | --------- | ----- | ----------- |
| [Wayfarer-2-12B-bf16.gguf](https://huggingface.co/bartowski/LatitudeGames_Wayfarer-2-12B-GGUF/blob/main/LatitudeGames_Wayfarer-2-12B-bf16.gguf) | bf16 | 24.50GB | false | Full BF16 weights. |
| [Wayfarer-2-12B-Q8_0.gguf](https://huggingface.co/bartowski/LatitudeGames_Wayfarer-2-12B-GGUF/blob/main/LatitudeGames_Wayfarer-2-12B-Q8_0.gguf) | Q8_0 | 13.02GB | false | Extremely high quality, generally unneeded but max available quant. |
| [Wayfarer-2-12B-Q6_K_L.gguf](https://huggingface.co/bartowski/LatitudeGames_Wayfarer-2-12B-GGUF/blob/main/LatitudeGames_Wayfarer-2-12B-Q6_K_L.gguf) | Q6_K_L | 10.38GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. |
| [Wayfarer-2-12B-Q6_K.gguf](https://huggingface.co/bartowski/LatitudeGames_Wayfarer-2-12B-GGUF/blob/main/LatitudeGames_Wayfarer-2-12B-Q6_K.gguf) | Q6_K | 10.06GB | false | Very high quality, near perfect, *recommended*. |
| [Wayfarer-2-12B-Q5_K_L.gguf](https://huggingface.co/bartowski/LatitudeGames_Wayfarer-2-12B-GGUF/blob/main/LatitudeGames_Wayfarer-2-12B-Q5_K_L.gguf) | Q5_K_L | 9.14GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. |
| [Wayfarer-2-12B-Q5_K_M.gguf](https://huggingface.co/bartowski/LatitudeGames_Wayfarer-2-12B-GGUF/blob/main/LatitudeGames_Wayfarer-2-12B-Q5_K_M.gguf) | Q5_K_M | 8.73GB | false | High quality, *recommended*. |
| [Wayfarer-2-12B-Q5_K_S.gguf](https://huggingface.co/bartowski/LatitudeGames_Wayfarer-2-12B-GGUF/blob/main/LatitudeGames_Wayfarer-2-12B-Q5_K_S.gguf) | Q5_K_S | 8.52GB | false | High quality, *recommended*. |
| [Wayfarer-2-12B-Q4_K_L.gguf](https://huggingface.co/bartowski/LatitudeGames_Wayfarer-2-12B-GGUF/blob/main/LatitudeGames_Wayfarer-2-12B-Q4_K_L.gguf) | Q4_K_L | 7.98GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. |
| [Wayfarer-2-12B-Q4_1.gguf](https://huggingface.co/bartowski/LatitudeGames_Wayfarer-2-12B-GGUF/blob/main/LatitudeGames_Wayfarer-2-12B-Q4_1.gguf) | Q4_1 | 7.80GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. |
| [Wayfarer-2-12B-Q4_K_M.gguf](https://huggingface.co/bartowski/LatitudeGames_Wayfarer-2-12B-GGUF/blob/main/LatitudeGames_Wayfarer-2-12B-Q4_K_M.gguf) | Q4_K_M | 7.48GB | false | Good quality, default size for most use cases, *recommended*. |
| [Wayfarer-2-12B-Q3_K_XL.gguf](https://huggingface.co/bartowski/LatitudeGames_Wayfarer-2-12B-GGUF/blob/main/LatitudeGames_Wayfarer-2-12B-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. |
| [Wayfarer-2-12B-Q4_K_S.gguf](https://huggingface.co/bartowski/LatitudeGames_Wayfarer-2-12B-GGUF/blob/main/LatitudeGames_Wayfarer-2-12B-Q4_K_S.gguf) | Q4_K_S | 7.12GB | false | Slightly lower quality with more space savings, *recommended*. |
| [Wayfarer-2-12B-IQ4_NL.gguf](https://huggingface.co/bartowski/LatitudeGames_Wayfarer-2-12B-GGUF/blob/main/LatitudeGames_Wayfarer-2-12B-IQ4_NL.gguf) | IQ4_NL | 7.10GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. |
| [Wayfarer-2-12B-Q4_0.gguf](https://huggingface.co/bartowski/LatitudeGames_Wayfarer-2-12B-GGUF/blob/main/LatitudeGames_Wayfarer-2-12B-Q4_0.gguf) | Q4_0 | 7.09GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. |
| [Wayfarer-2-12B-IQ4_XS.gguf](https://huggingface.co/bartowski/LatitudeGames_Wayfarer-2-12B-GGUF/blob/main/LatitudeGames_Wayfarer-2-12B-IQ4_XS.gguf) | IQ4_XS | 6.74GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
| [Wayfarer-2-12B-Q3_K_L.gguf](https://huggingface.co/bartowski/LatitudeGames_Wayfarer-2-12B-GGUF/blob/main/LatitudeGames_Wayfarer-2-12B-Q3_K_L.gguf) | Q3_K_L | 6.56GB | false | Lower quality but usable, good for low RAM availability. |
| [Wayfarer-2-12B-Q3_K_M.gguf](https://huggingface.co/bartowski/LatitudeGames_Wayfarer-2-12B-GGUF/blob/main/LatitudeGames_Wayfarer-2-12B-Q3_K_M.gguf) | Q3_K_M | 6.08GB | false | Low quality. |
| [Wayfarer-2-12B-IQ3_M.gguf](https://huggingface.co/bartowski/LatitudeGames_Wayfarer-2-12B-GGUF/blob/main/LatitudeGames_Wayfarer-2-12B-IQ3_M.gguf) | IQ3_M | 5.72GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
| [Wayfarer-2-12B-Q3_K_S.gguf](https://huggingface.co/bartowski/LatitudeGames_Wayfarer-2-12B-GGUF/blob/main/LatitudeGames_Wayfarer-2-12B-Q3_K_S.gguf) | Q3_K_S | 5.53GB | false | Low quality, not recommended. |
| [Wayfarer-2-12B-Q2_K_L.gguf](https://huggingface.co/bartowski/LatitudeGames_Wayfarer-2-12B-GGUF/blob/main/LatitudeGames_Wayfarer-2-12B-Q2_K_L.gguf) | Q2_K_L | 5.45GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. |
| [Wayfarer-2-12B-IQ3_XS.gguf](https://huggingface.co/bartowski/LatitudeGames_Wayfarer-2-12B-GGUF/blob/main/LatitudeGames_Wayfarer-2-12B-IQ3_XS.gguf) | IQ3_XS | 5.31GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
| [Wayfarer-2-12B-IQ3_XXS.gguf](https://huggingface.co/bartowski/LatitudeGames_Wayfarer-2-12B-GGUF/blob/main/LatitudeGames_Wayfarer-2-12B-IQ3_XXS.gguf) | IQ3_XXS | 4.95GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. |
| [Wayfarer-2-12B-Q2_K.gguf](https://huggingface.co/bartowski/LatitudeGames_Wayfarer-2-12B-GGUF/blob/main/LatitudeGames_Wayfarer-2-12B-Q2_K.gguf) | Q2_K | 4.79GB | false | Very low quality but surprisingly usable. |
| [Wayfarer-2-12B-IQ2_M.gguf](https://huggingface.co/bartowski/LatitudeGames_Wayfarer-2-12B-GGUF/blob/main/LatitudeGames_Wayfarer-2-12B-IQ2_M.gguf) | IQ2_M | 4.44GB | false | Relatively low quality, uses SOTA techniques to be surprisingly usable. |
| [Wayfarer-2-12B-IQ2_S.gguf](https://huggingface.co/bartowski/LatitudeGames_Wayfarer-2-12B-GGUF/blob/main/LatitudeGames_Wayfarer-2-12B-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/LatitudeGames_Wayfarer-2-12B-GGUF --include "LatitudeGames_Wayfarer-2-12B-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/LatitudeGames_Wayfarer-2-12B-GGUF --include "LatitudeGames_Wayfarer-2-12B-Q8_0/*" --local-dir ./
```
You can either specify a new local-dir (LatitudeGames_Wayfarer-2-12B-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}