初始化项目,由ModelHub XC社区提供模型

Model: bartowski/LiquidAI_LFM2-1.2B-Tool-GGUF
Source: Original Platform
This commit is contained in:
ModelHub XC committed 2026-11-06 02:59:12 +08:00
commit 087f31bfc5
28 files changed
+313

No files matched your search

+73
View File
@@ -0,0 +1,73 @@
*.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
*.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
LiquidAI_LFM2-1.2B-Tool-Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
LiquidAI_LFM2-1.2B-Tool-Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text
LiquidAI_LFM2-1.2B-Tool-bf16.gguf filter=lfs diff=lfs merge=lfs -text
LiquidAI_LFM2-1.2B-Tool-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
LiquidAI_LFM2-1.2B-Tool-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text
LiquidAI_LFM2-1.2B-Tool-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
LiquidAI_LFM2-1.2B-Tool-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
LiquidAI_LFM2-1.2B-Tool-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
LiquidAI_LFM2-1.2B-Tool-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
LiquidAI_LFM2-1.2B-Tool-Q4_K_L.gguf filter=lfs diff=lfs merge=lfs -text
LiquidAI_LFM2-1.2B-Tool-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
LiquidAI_LFM2-1.2B-Tool-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text
LiquidAI_LFM2-1.2B-Tool-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
LiquidAI_LFM2-1.2B-Tool-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
LiquidAI_LFM2-1.2B-Tool-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text
LiquidAI_LFM2-1.2B-Tool-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
LiquidAI_LFM2-1.2B-Tool-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
LiquidAI_LFM2-1.2B-Tool-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
LiquidAI_LFM2-1.2B-Tool-imatrix.gguf filter=lfs diff=lfs merge=lfs -text
LiquidAI_LFM2-1.2B-Tool-Q5_K_L.gguf filter=lfs diff=lfs merge=lfs -text
LiquidAI_LFM2-1.2B-Tool-Q6_K_L.gguf filter=lfs diff=lfs merge=lfs -text
LiquidAI_LFM2-1.2B-Tool-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
LiquidAI_LFM2-1.2B-Tool-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text
LiquidAI_LFM2-1.2B-Tool-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
LiquidAI_LFM2-1.2B-Tool-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+3
View File
@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f00daa7bc09b14fb20888a90ecd9529ce4d052e48774166a6f1090b68ed3152d
size 434131488
+3
View File
@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:24a9765633954adff608b116bcbae28a178ba445a1af2225aea21d2e7ab10070
size 566792736
+3
View File
@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:8d2141f72e721bda4332d3720a3fb85ab2128963c3bcfadf82a08c5cc29af5ec
size 537809440
+3
View File
@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:6a60979bb891a005148ad337b7415983261de6a74768d4dc47769f043430585d
size 490983968
+3
View File
@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:beb3a7efe14806aab69ae3d0e1873238c7cdf23f9b5e3977793c0fa5f1f19c6d
size 695751200
+3
View File
@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:4302b7ba57de40c7b1160b6cbe13ead2b72034e710728c23d99cabb4460f8e9b
size 663376416
+3
View File
@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:de01275b7965c39957724b52544749722f940321d5769c765a80b28b7e577a8b
size 483398176
+3
View File
@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:41e3240f6d097c4d20e636c79451a7e45b457b2df1d7d7950e344277ef1ae7ce
size 515904032
+3
View File
@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2133dcb23deaef2a825ca36e304ad86f0901f4d10461fd7547f52dbeaa0e40fe
size 635474464
+3
View File
@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5c95a5d42b1cb9ad039d387cae512fce7e69f55c779494b429d05cbbef1d094c
size 600347168
+3
View File
@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:dd883f80bce3f9d6d1088aef9ef5bfcfa0360b52ed274ae7861c8e203e3c5079
size 558158368
+3
View File
@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:04def197579d7dd6d06143fb4c7645d1a91fbfbcb74e1965fceb79ecf1f3fd46
size 667980320
+3
View File
@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e22399c8efab48dce8abf95a10ee9424e3ff4be01ac531a9ea3fbff8cd30b8e5
size 697848352
+3
View File
@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:7c71fdc438679510775569e8d27546bcf3f690c33b5adbab08e8555ed18e3d34
size 760500768
+3
View File
@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3e66dfb97cb9f6a5259704f3f323c117490a20ac1a9e5b7fa4c7c60cfee6a3a2
size 763400736
+3
View File
@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:6bdf2292a137c12264a065d73c12b61065293440b753249727cec0b6dc350d64
size 730894880
+3
View File
@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:7311ecb492afe453750ee6356763a9275e76cb1f93e765def1802a5f1faaf4bc
size 700469792
+3
View File
@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e04d2c077c4bacafe38fe7cba9d4175ddb151030e869610a86927198e5598126
size 875860512
+3
View File
@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f52d446aacd440b4d451f52703cc4f69fe39a637ba939e6d644dacff04188191
size 843354656
+3
View File
@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0ece7011e9ec0ad5f84b016bfa9c50c4c4f86c33575ab7204aaeca0bc3cb5e59
size 825250336
+3
View File
@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1c1f1ef1fcfc81b6b047123bc6d23a327ce80e83dc2001b42ce043c08631f3bd
size 962843168
+3
View File
@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:8b93f8aa32246d3f806ffa83673dd3712f5c427a36c924ac54009b0e27bd5194
size 995349024
+3
View File
@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:4b05f48f31e7d0e7bc9b369c24abed6ff22df2d34868b78ff9dd0bcb90c5a21c
size 1246253600
+3
View File
@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2897913d03b5466309689329124f8ff707b7f39cb93b3b025562eeebc3e0569d
size 2343325952
+3
View File
@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e128463ecc515b6a1a3cc3c6544438b391ea335c0a6aa68672f2d48828399f08
size 1161536
+164
View File
@@ -0,0 +1,164 @@
---
quantized_by: bartowski
pipeline_tag: text-generation
base_model_relation: quantized
base_model: LiquidAI/LFM2-1.2B-Tool
---
## Llamacpp imatrix Quantizations of LFM2-1.2B-Tool by LiquidAI
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/b6683">b6683</a> for quantization.
Original model: https://huggingface.co/LiquidAI/LFM2-1.2B-Tool
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 |
| -------- | ---------- | --------- | ----- | ----------- |
| [LFM2-1.2B-Tool-bf16.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-1.2B-Tool-GGUF/blob/main/LiquidAI_LFM2-1.2B-Tool-bf16.gguf) | bf16 | 2.34GB | false | Full BF16 weights. |
| [LFM2-1.2B-Tool-Q8_0.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-1.2B-Tool-GGUF/blob/main/LiquidAI_LFM2-1.2B-Tool-Q8_0.gguf) | Q8_0 | 1.25GB | false | Extremely high quality, generally unneeded but max available quant. |
| [LFM2-1.2B-Tool-Q6_K_L.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-1.2B-Tool-GGUF/blob/main/LiquidAI_LFM2-1.2B-Tool-Q6_K_L.gguf) | Q6_K_L | 1.00GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. |
| [LFM2-1.2B-Tool-Q6_K.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-1.2B-Tool-GGUF/blob/main/LiquidAI_LFM2-1.2B-Tool-Q6_K.gguf) | Q6_K | 0.96GB | false | Very high quality, near perfect, *recommended*. |
| [LFM2-1.2B-Tool-Q5_K_L.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-1.2B-Tool-GGUF/blob/main/LiquidAI_LFM2-1.2B-Tool-Q5_K_L.gguf) | Q5_K_L | 0.88GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. |
| [LFM2-1.2B-Tool-Q5_K_M.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-1.2B-Tool-GGUF/blob/main/LiquidAI_LFM2-1.2B-Tool-Q5_K_M.gguf) | Q5_K_M | 0.84GB | false | High quality, *recommended*. |
| [LFM2-1.2B-Tool-Q5_K_S.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-1.2B-Tool-GGUF/blob/main/LiquidAI_LFM2-1.2B-Tool-Q5_K_S.gguf) | Q5_K_S | 0.83GB | false | High quality, *recommended*. |
| [LFM2-1.2B-Tool-Q4_K_L.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-1.2B-Tool-GGUF/blob/main/LiquidAI_LFM2-1.2B-Tool-Q4_K_L.gguf) | Q4_K_L | 0.76GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. |
| [LFM2-1.2B-Tool-Q4_1.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-1.2B-Tool-GGUF/blob/main/LiquidAI_LFM2-1.2B-Tool-Q4_1.gguf) | Q4_1 | 0.76GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. |
| [LFM2-1.2B-Tool-Q4_K_M.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-1.2B-Tool-GGUF/blob/main/LiquidAI_LFM2-1.2B-Tool-Q4_K_M.gguf) | Q4_K_M | 0.73GB | false | Good quality, default size for most use cases, *recommended*. |
| [LFM2-1.2B-Tool-Q4_K_S.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-1.2B-Tool-GGUF/blob/main/LiquidAI_LFM2-1.2B-Tool-Q4_K_S.gguf) | Q4_K_S | 0.70GB | false | Slightly lower quality with more space savings, *recommended*. |
| [LFM2-1.2B-Tool-Q4_0.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-1.2B-Tool-GGUF/blob/main/LiquidAI_LFM2-1.2B-Tool-Q4_0.gguf) | Q4_0 | 0.70GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. |
| [LFM2-1.2B-Tool-IQ4_NL.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-1.2B-Tool-GGUF/blob/main/LiquidAI_LFM2-1.2B-Tool-IQ4_NL.gguf) | IQ4_NL | 0.70GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. |
| [LFM2-1.2B-Tool-Q3_K_XL.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-1.2B-Tool-GGUF/blob/main/LiquidAI_LFM2-1.2B-Tool-Q3_K_XL.gguf) | Q3_K_XL | 0.67GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. |
| [LFM2-1.2B-Tool-IQ4_XS.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-1.2B-Tool-GGUF/blob/main/LiquidAI_LFM2-1.2B-Tool-IQ4_XS.gguf) | IQ4_XS | 0.66GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
| [LFM2-1.2B-Tool-Q3_K_L.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-1.2B-Tool-GGUF/blob/main/LiquidAI_LFM2-1.2B-Tool-Q3_K_L.gguf) | Q3_K_L | 0.64GB | false | Lower quality but usable, good for low RAM availability. |
| [LFM2-1.2B-Tool-Q3_K_M.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-1.2B-Tool-GGUF/blob/main/LiquidAI_LFM2-1.2B-Tool-Q3_K_M.gguf) | Q3_K_M | 0.60GB | false | Low quality. |
| [LFM2-1.2B-Tool-IQ3_M.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-1.2B-Tool-GGUF/blob/main/LiquidAI_LFM2-1.2B-Tool-IQ3_M.gguf) | IQ3_M | 0.57GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
| [LFM2-1.2B-Tool-Q3_K_S.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-1.2B-Tool-GGUF/blob/main/LiquidAI_LFM2-1.2B-Tool-Q3_K_S.gguf) | Q3_K_S | 0.56GB | false | Low quality, not recommended. |
| [LFM2-1.2B-Tool-IQ3_XS.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-1.2B-Tool-GGUF/blob/main/LiquidAI_LFM2-1.2B-Tool-IQ3_XS.gguf) | IQ3_XS | 0.54GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
| [LFM2-1.2B-Tool-Q2_K_L.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-1.2B-Tool-GGUF/blob/main/LiquidAI_LFM2-1.2B-Tool-Q2_K_L.gguf) | Q2_K_L | 0.52GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. |
| [LFM2-1.2B-Tool-IQ3_XXS.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-1.2B-Tool-GGUF/blob/main/LiquidAI_LFM2-1.2B-Tool-IQ3_XXS.gguf) | IQ3_XXS | 0.49GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. |
| [LFM2-1.2B-Tool-Q2_K.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-1.2B-Tool-GGUF/blob/main/LiquidAI_LFM2-1.2B-Tool-Q2_K.gguf) | Q2_K | 0.48GB | false | Very low quality but surprisingly usable. |
| [LFM2-1.2B-Tool-IQ2_M.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-1.2B-Tool-GGUF/blob/main/LiquidAI_LFM2-1.2B-Tool-IQ2_M.gguf) | IQ2_M | 0.43GB | 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/LiquidAI_LFM2-1.2B-Tool-GGUF --include "LiquidAI_LFM2-1.2B-Tool-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/LiquidAI_LFM2-1.2B-Tool-GGUF --include "LiquidAI_LFM2-1.2B-Tool-Q8_0/*" --local-dir ./
```
You can either specify a new local-dir (LiquidAI_LFM2-1.2B-Tool-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
View File
@@ -0,0 +1 @@
{"framework": "pytorch", "task": "text-generation", "allow_remote": true}