bartowski/DeepSeek-R1-Distill-Qwen-1.5B-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/DeepSeek-R1-Distill-Qwen-1.5B-GGUF
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-07-04 09:06:12 +08:00
commit f2c96e6cb1
28 changed files with 299 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

60
.gitattributes vendored Normal file
View File

@@ -0,0 +1,60 @@
*.7z filter=lfs diff=lfs merge=lfs -text
*.arrow filter=lfs diff=lfs merge=lfs -text
*.bin filter=lfs diff=lfs merge=lfs -text
*.bz2 filter=lfs diff=lfs merge=lfs -text
*.ckpt 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
*.mlmodel filter=lfs diff=lfs merge=lfs -text
*.model filter=lfs diff=lfs merge=lfs -text
*.msgpack filter=lfs diff=lfs merge=lfs -text
*.npy filter=lfs diff=lfs merge=lfs -text
*.npz 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
*.pickle filter=lfs diff=lfs merge=lfs -text
*.pkl 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
*.safetensors filter=lfs diff=lfs merge=lfs -text
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
*.tar.* 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
*.wasm filter=lfs diff=lfs merge=lfs -text
*.xz filter=lfs diff=lfs merge=lfs -text
*.zip filter=lfs diff=lfs merge=lfs -text
*.zst filter=lfs diff=lfs merge=lfs -text
*tfevents* filter=lfs diff=lfs merge=lfs -text
DeepSeek-R1-Distill-Qwen-1.5B-f16.gguf filter=lfs diff=lfs merge=lfs -text
DeepSeek-R1-Distill-Qwen-1.5B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
DeepSeek-R1-Distill-Qwen-1.5B-Q6_K_L.gguf filter=lfs diff=lfs merge=lfs -text
DeepSeek-R1-Distill-Qwen-1.5B-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
DeepSeek-R1-Distill-Qwen-1.5B-Q5_K_L.gguf filter=lfs diff=lfs merge=lfs -text
DeepSeek-R1-Distill-Qwen-1.5B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
DeepSeek-R1-Distill-Qwen-1.5B-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
DeepSeek-R1-Distill-Qwen-1.5B-Q4_K_L.gguf filter=lfs diff=lfs merge=lfs -text
DeepSeek-R1-Distill-Qwen-1.5B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
DeepSeek-R1-Distill-Qwen-1.5B-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
DeepSeek-R1-Distill-Qwen-1.5B-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text
DeepSeek-R1-Distill-Qwen-1.5B-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
DeepSeek-R1-Distill-Qwen-1.5B-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text
DeepSeek-R1-Distill-Qwen-1.5B-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
DeepSeek-R1-Distill-Qwen-1.5B-Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
DeepSeek-R1-Distill-Qwen-1.5B-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
DeepSeek-R1-Distill-Qwen-1.5B-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
DeepSeek-R1-Distill-Qwen-1.5B-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
DeepSeek-R1-Distill-Qwen-1.5B-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
DeepSeek-R1-Distill-Qwen-1.5B-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
DeepSeek-R1-Distill-Qwen-1.5B-Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text
DeepSeek-R1-Distill-Qwen-1.5B-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
DeepSeek-R1-Distill-Qwen-1.5B-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text
DeepSeek-R1-Distill-Qwen-1.5B-f32.gguf filter=lfs diff=lfs merge=lfs -text
DeepSeek-R1-Distill-Qwen-1.5B.imatrix filter=lfs diff=lfs merge=lfs -text

3
DeepSeek-R1-Distill-Qwen-1.5B-IQ2_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:7b99832b3040f184ab3929409de0094bd5edcc485d6343f82bc861fd4c0c308a
size 701332064

3
DeepSeek-R1-Distill-Qwen-1.5B-IQ3_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:65380a89c4ccf3a2941739fe8fde454c9bfbeccd3548a7a0899324cd66e80f4e
size 876941408

3
DeepSeek-R1-Distill-Qwen-1.5B-IQ3_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:57ca6b0a339fddf2cd8043bc24c2251f9f3379dec9b440e7eb0ec0fe07bc070d
size 831976544

3
DeepSeek-R1-Distill-Qwen-1.5B-IQ4_NL.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a837a26cb7eea2342f6e1762cc8d39531d46e96b0316be518c18af70c80c357c
size 1067603552

3
DeepSeek-R1-Distill-Qwen-1.5B-IQ4_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:463c6bc48a2b728fd1811a320031ace1c03e867918067f1eed9a36483f0eadac
size 1019711072

3
DeepSeek-R1-Distill-Qwen-1.5B-Q2_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:902a0f3910078db0fdb1cf58686d36160794b96e4698eae577fb18b35f2b0d87
size 752880224

3
DeepSeek-R1-Distill-Qwen-1.5B-Q2_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:951621d7d8033c721009d466123e0a45db598be228276ddea262609291040e57
size 980784224

3
DeepSeek-R1-Distill-Qwen-1.5B-Q3_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:94a1204af6bcf2fcfeda851fcfdecbebc15767c4235ede9999adac9f2648f0e5
size 980440160

3
DeepSeek-R1-Distill-Qwen-1.5B-Q3_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b1094879ee7e222cba5be013e6de2d0658c64f91aef5d3c9bff0db5cefbfa020
size 924456032

3
DeepSeek-R1-Distill-Qwen-1.5B-Q3_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:006aa33911fc8b74607e88f09615ffcb8c7e4500a192abfb03a841b945869cd2
size 861221984

3
DeepSeek-R1-Distill-Qwen-1.5B-Q3_K_XL.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:51c560753ea3d58489b0aaa0d5d17dadd05df19dd98161d8f6498b8f0cfc40e2
size 1184642144

3
DeepSeek-R1-Distill-Qwen-1.5B-Q4_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b3af887d0a015b39fab2395e4faf682c1a81a6a3fd09a43f0d4292f7d94bf4d0
size 1068807776

3
DeepSeek-R1-Distill-Qwen-1.5B-Q4_1.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:70ab8eae63c96946cc17bd8ee5a912ecd2af251bdda4bd3794fc448148ca0588
size 1162700384

3
DeepSeek-R1-Distill-Qwen-1.5B-Q4_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1512d97de835f40e203ece1cd60933d26c562da9a23fba48612ad0f44c14eb62
size 1290527840

3
DeepSeek-R1-Distill-Qwen-1.5B-Q4_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1741e5b2d062b07acf048bf0d2c514dadf2a48f94e2b4aa0cfe069af3838ee2f
size 1117320800

3
DeepSeek-R1-Distill-Qwen-1.5B-Q4_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:843e1b28b613872cf9f04e5c6d92493b32cfb6b4b9f4682bea2c57e14dbfec05
size 1071584864

3
DeepSeek-R1-Distill-Qwen-1.5B-Q5_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5fc782efeab30642496dd86441dc9e5af8ff7f953175048595b8ac069cbacd28
size 1429529696

3
DeepSeek-R1-Distill-Qwen-1.5B-Q5_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:4d8f6465e96258cf44303eb02812c391d15f6c77f0d72e47757c98fd14994608
size 1285494368

3
DeepSeek-R1-Distill-Qwen-1.5B-Q5_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2b231465c95e9005d8b214b166baaca43618b8453cc0079c4a8ef4dc268230bd
size 1259173472

3
DeepSeek-R1-Distill-Qwen-1.5B-Q6_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c9c8aff5a84e2e9c1fd6ea57af5ab52cf5d7272d34460403d82880075e611039
size 1464178784

3
DeepSeek-R1-Distill-Qwen-1.5B-Q6_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3a19b43e78eba4e4e3e6415f5e1b8e20e6c20ab6df1390fa1e554dd56a172296
size 1577219168

3
DeepSeek-R1-Distill-Qwen-1.5B-Q8_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:166baa90e6a963de31a7713ff034f82317ff1fa41602f7c3ce583d3f6b551829
size 1894532192

3
DeepSeek-R1-Distill-Qwen-1.5B-f16.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c96782c9c74110d23da375c0194dd0e5d05a10b8dd475d87972b97022b5ac9d4
size 3560416352

3
DeepSeek-R1-Distill-Qwen-1.5B-f32.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2bba076a57ede3796768f36438c2ebec2d1f8cdd9f210851fe64cc9a87a93c63
size 7114302272

3
DeepSeek-R1-Distill-Qwen-1.5B.imatrix Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:8de239b3f37d1cac59294f89e4689889bb2ff592cb6edbd7d141281d4764de90
size 2042214

163
README.md Normal file
View File

@@ -0,0 +1,163 @@
---
quantized_by: bartowski
pipeline_tag: text-generation
base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
---
## Llamacpp imatrix Quantizations of DeepSeek-R1-Distill-Qwen-1.5B
Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b4514">b4514</a> for quantization.
Original model: https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
All quants made using imatrix option with dataset from [here](https://gist.github.com/bartowski1182/eb213dccb3571f863da82e99418f81e8)
Run them in [LM Studio](https://lmstudio.ai/)
## Prompt format
```
<｜begin▁of▁sentence｜>{system_prompt}<｜User｜>{prompt}<｜Assistant｜>
```
## Download a file (not the whole branch) from below:
| Filename | Quant type | File Size | Split | Description |
| -------- | ---------- | --------- | ----- | ----------- |
| [DeepSeek-R1-Distill-Qwen-1.5B-f32.gguf](https://huggingface.co/bartowski/DeepSeek-R1-Distill-Qwen-1.5B-GGUF/blob/main/DeepSeek-R1-Distill-Qwen-1.5B-f32.gguf) | f32 | 7.11GB | false | Full F32 weights. |
| [DeepSeek-R1-Distill-Qwen-1.5B-f16.gguf](https://huggingface.co/bartowski/DeepSeek-R1-Distill-Qwen-1.5B-GGUF/blob/main/DeepSeek-R1-Distill-Qwen-1.5B-f16.gguf) | f16 | 3.56GB | false | Full F16 weights. |
| [DeepSeek-R1-Distill-Qwen-1.5B-Q8_0.gguf](https://huggingface.co/bartowski/DeepSeek-R1-Distill-Qwen-1.5B-GGUF/blob/main/DeepSeek-R1-Distill-Qwen-1.5B-Q8_0.gguf) | Q8_0 | 1.89GB | false | Extremely high quality, generally unneeded but max available quant. |
| [DeepSeek-R1-Distill-Qwen-1.5B-Q6_K_L.gguf](https://huggingface.co/bartowski/DeepSeek-R1-Distill-Qwen-1.5B-GGUF/blob/main/DeepSeek-R1-Distill-Qwen-1.5B-Q6_K_L.gguf) | Q6_K_L | 1.58GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. |
| [DeepSeek-R1-Distill-Qwen-1.5B-Q6_K.gguf](https://huggingface.co/bartowski/DeepSeek-R1-Distill-Qwen-1.5B-GGUF/blob/main/DeepSeek-R1-Distill-Qwen-1.5B-Q6_K.gguf) | Q6_K | 1.46GB | false | Very high quality, near perfect, *recommended*. |
| [DeepSeek-R1-Distill-Qwen-1.5B-Q5_K_L.gguf](https://huggingface.co/bartowski/DeepSeek-R1-Distill-Qwen-1.5B-GGUF/blob/main/DeepSeek-R1-Distill-Qwen-1.5B-Q5_K_L.gguf) | Q5_K_L | 1.43GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. |
| [DeepSeek-R1-Distill-Qwen-1.5B-Q5_K_M.gguf](https://huggingface.co/bartowski/DeepSeek-R1-Distill-Qwen-1.5B-GGUF/blob/main/DeepSeek-R1-Distill-Qwen-1.5B-Q5_K_M.gguf) | Q5_K_M | 1.29GB | false | High quality, *recommended*. |
| [DeepSeek-R1-Distill-Qwen-1.5B-Q4_K_L.gguf](https://huggingface.co/bartowski/DeepSeek-R1-Distill-Qwen-1.5B-GGUF/blob/main/DeepSeek-R1-Distill-Qwen-1.5B-Q4_K_L.gguf) | Q4_K_L | 1.29GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. |
| [DeepSeek-R1-Distill-Qwen-1.5B-Q5_K_S.gguf](https://huggingface.co/bartowski/DeepSeek-R1-Distill-Qwen-1.5B-GGUF/blob/main/DeepSeek-R1-Distill-Qwen-1.5B-Q5_K_S.gguf) | Q5_K_S | 1.26GB | false | High quality, *recommended*. |
| [DeepSeek-R1-Distill-Qwen-1.5B-Q3_K_XL.gguf](https://huggingface.co/bartowski/DeepSeek-R1-Distill-Qwen-1.5B-GGUF/blob/main/DeepSeek-R1-Distill-Qwen-1.5B-Q3_K_XL.gguf) | Q3_K_XL | 1.18GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. |
| [DeepSeek-R1-Distill-Qwen-1.5B-Q4_1.gguf](https://huggingface.co/bartowski/DeepSeek-R1-Distill-Qwen-1.5B-GGUF/blob/main/DeepSeek-R1-Distill-Qwen-1.5B-Q4_1.gguf) | Q4_1 | 1.16GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. |
| [DeepSeek-R1-Distill-Qwen-1.5B-Q4_K_M.gguf](https://huggingface.co/bartowski/DeepSeek-R1-Distill-Qwen-1.5B-GGUF/blob/main/DeepSeek-R1-Distill-Qwen-1.5B-Q4_K_M.gguf) | Q4_K_M | 1.12GB | false | Good quality, default size for most use cases, *recommended*. |
| [DeepSeek-R1-Distill-Qwen-1.5B-Q4_K_S.gguf](https://huggingface.co/bartowski/DeepSeek-R1-Distill-Qwen-1.5B-GGUF/blob/main/DeepSeek-R1-Distill-Qwen-1.5B-Q4_K_S.gguf) | Q4_K_S | 1.07GB | false | Slightly lower quality with more space savings, *recommended*. |
| [DeepSeek-R1-Distill-Qwen-1.5B-Q4_0.gguf](https://huggingface.co/bartowski/DeepSeek-R1-Distill-Qwen-1.5B-GGUF/blob/main/DeepSeek-R1-Distill-Qwen-1.5B-Q4_0.gguf) | Q4_0 | 1.07GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. |
| [DeepSeek-R1-Distill-Qwen-1.5B-IQ4_NL.gguf](https://huggingface.co/bartowski/DeepSeek-R1-Distill-Qwen-1.5B-GGUF/blob/main/DeepSeek-R1-Distill-Qwen-1.5B-IQ4_NL.gguf) | IQ4_NL | 1.07GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. |
| [DeepSeek-R1-Distill-Qwen-1.5B-IQ4_XS.gguf](https://huggingface.co/bartowski/DeepSeek-R1-Distill-Qwen-1.5B-GGUF/blob/main/DeepSeek-R1-Distill-Qwen-1.5B-IQ4_XS.gguf) | IQ4_XS | 1.02GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
| [DeepSeek-R1-Distill-Qwen-1.5B-Q3_K_L.gguf](https://huggingface.co/bartowski/DeepSeek-R1-Distill-Qwen-1.5B-GGUF/blob/main/DeepSeek-R1-Distill-Qwen-1.5B-Q3_K_L.gguf) | Q3_K_L | 0.98GB | false | Lower quality but usable, good for low RAM availability. |
| [DeepSeek-R1-Distill-Qwen-1.5B-Q2_K_L.gguf](https://huggingface.co/bartowski/DeepSeek-R1-Distill-Qwen-1.5B-GGUF/blob/main/DeepSeek-R1-Distill-Qwen-1.5B-Q2_K_L.gguf) | Q2_K_L | 0.98GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. |
| [DeepSeek-R1-Distill-Qwen-1.5B-Q3_K_M.gguf](https://huggingface.co/bartowski/DeepSeek-R1-Distill-Qwen-1.5B-GGUF/blob/main/DeepSeek-R1-Distill-Qwen-1.5B-Q3_K_M.gguf) | Q3_K_M | 0.92GB | false | Low quality. |
| [DeepSeek-R1-Distill-Qwen-1.5B-IQ3_M.gguf](https://huggingface.co/bartowski/DeepSeek-R1-Distill-Qwen-1.5B-GGUF/blob/main/DeepSeek-R1-Distill-Qwen-1.5B-IQ3_M.gguf) | IQ3_M | 0.88GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
| [DeepSeek-R1-Distill-Qwen-1.5B-Q3_K_S.gguf](https://huggingface.co/bartowski/DeepSeek-R1-Distill-Qwen-1.5B-GGUF/blob/main/DeepSeek-R1-Distill-Qwen-1.5B-Q3_K_S.gguf) | Q3_K_S | 0.86GB | false | Low quality, not recommended. |
| [DeepSeek-R1-Distill-Qwen-1.5B-IQ3_XS.gguf](https://huggingface.co/bartowski/DeepSeek-R1-Distill-Qwen-1.5B-GGUF/blob/main/DeepSeek-R1-Distill-Qwen-1.5B-IQ3_XS.gguf) | IQ3_XS | 0.83GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
| [DeepSeek-R1-Distill-Qwen-1.5B-Q2_K.gguf](https://huggingface.co/bartowski/DeepSeek-R1-Distill-Qwen-1.5B-GGUF/blob/main/DeepSeek-R1-Distill-Qwen-1.5B-Q2_K.gguf) | Q2_K | 0.75GB | false | Very low quality but surprisingly usable. |
| [DeepSeek-R1-Distill-Qwen-1.5B-IQ2_M.gguf](https://huggingface.co/bartowski/DeepSeek-R1-Distill-Qwen-1.5B-GGUF/blob/main/DeepSeek-R1-Distill-Qwen-1.5B-IQ2_M.gguf) | IQ2_M | 0.70GB | 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/DeepSeek-R1-Distill-Qwen-1.5B-GGUF --include "DeepSeek-R1-Distill-Qwen-1.5B-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/DeepSeek-R1-Distill-Qwen-1.5B-GGUF --include "DeepSeek-R1-Distill-Qwen-1.5B-Q8_0/*" --local-dir ./
```
You can either specify a new local-dir (DeepSeek-R1-Distill-Qwen-1.5B-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 and Apple Metal, but will be slower than their K-quant equivalent, so speed vs performance is a tradeoff you'll have to decide.
The I-quants are *not* compatible with Vulcan, which is also AMD, so if you have an AMD card double check if you're using the rocBLAS build or the Vulcan build. At the time of writing this, LM Studio has a preview with ROCm support, and other inference engines have specific builds for ROCm.
</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.
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}