bartowski/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-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-ReDistill-Qwen-1.5B-v1.0-GGUF
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-07-13 14:47:06 +08:00
commit d2e30184cf
28 changed files with 302 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-ReDistill-Qwen-1.5B-v1.0-f16.gguf filter=lfs diff=lfs merge=lfs -text
DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-Q6_K_L.gguf filter=lfs diff=lfs merge=lfs -text
DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-Q5_K_L.gguf filter=lfs diff=lfs merge=lfs -text
DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-Q4_K_L.gguf filter=lfs diff=lfs merge=lfs -text
DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text
DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text
DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text
DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text
DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-f32.gguf filter=lfs diff=lfs merge=lfs -text
DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0.imatrix filter=lfs diff=lfs merge=lfs -text

3
DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-IQ2_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f3372f72b120868f2a75868abb5ab2e5fcf840ebe364ed8e3a53f9c44fe37fc8
size 701554848

3
DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-IQ3_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:44a49e899287fe34830b02bde8f1ebcfbd0d3f0ad2e06a5fd2cac628e668f4de
size 877190304

3
DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-IQ3_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f8cee380151db6db68ef2d6c85c1420eacc5d974825f19c37300fae303850074
size 832225440

3
DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-IQ4_NL.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:cb0b1fe5d5829d02df014f7719d119e6b091c7f662f3c69d327ae33ff516af44
size 1067878560

3
DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-IQ4_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:8458a79397edbaa021058900711528a19e39916bf3ab2a1ee7c2af4e8f38a9ca
size 1019979936

3
DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-Q2_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:6ea908d5661a1a30164d2d5ff00aa6cb72079f8ddb145aadb930da72bb96567b
size 753109152

3
DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-Q2_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:459e0e398ab0ac82d8e59081feff30b54f3fc19028801ba58c014d9f76e5bd6e
size 981205152

3
DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-Q3_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c7cbd02316e06348eb98363986c8d34be334cdb8dafea70d84bc8cdb3ff82418
size 980689056

3
DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-Q3_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:872346f6b3486ae50b71ef46455d2665e7d2d5c544d0eff3e2b18347fb60f201
size 924704928

3
DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-Q3_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e98c8d5b10751991a59c4086a8c64f7879bbbe8e485ecc7b414cfae7b8f274fc
size 861470880

3
DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-Q3_K_XL.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:395a373317960b0f748d5cab473013a2492ed65037489a1110c0b468089402a9
size 1185063072

3
DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-Q4_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:dd3568917e7faf4b65ed7a6a81c89a801ee4ddde76f25197d1a17a1cff504387
size 1069082784

3
DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-Q4_1.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:dfbd0041f2bfc83e912f737a8ab458ad5297ced83ab51c2c4e601fee7bfdebbb
size 1162987680

3
DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-Q4_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0451ab1f02cd89068ad3d3fae23efb1791a49c2fa68f55a82ae6231f3a7d4095
size 1290948768

3
DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-Q4_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:22afcc39becec6a6e35fb3c6b5fe96ed47b3df038a7f621d79920e581d3e5593
size 1117595808

3
DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-Q4_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:efdd582cfc114647dd02e6b079d7bdcfebf060d08c5b5579dc6598dff2a31505
size 1071859872

3
DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-Q5_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2d28de57bcef809bea064a9c93a9df99f0c5f85317c49cfec9fcdd8dae6b4e8e
size 1429950624

3
DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-Q5_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:66967af8d8412dc1e546fccdc8b3cf31f019c79fd69f7d669052ece7cf63a2a8
size 1285793952

3
DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-Q5_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:28def9ec52ea6a502f56772c39253d357f360e53347ee2d330c327aeb41f3e7e
size 1259473056

3
DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-Q6_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:7af9750416b6eea1fe2ae6b8c61250d0e0fed6c760bce84083869ad58034d5b0
size 1464504480

3
DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-Q6_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:816abfb73d4d50a24de442cd4d10220fec73cec6015dce70494f829f6f6d7423
size 1577640096

3
DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-Q8_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:53d18b2f5ff4794fa8dd401e6086cf8cb9c41e5280e98711d39f4e084b7d0644
size 1894953120

3
DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-f16.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:bdf39603db99452e6c13e54c60d06ec09d8844ae70283d1311e82ec297dbec1d
size 3561205920

3
DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-f32.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0c922ee4021fa06e6bd1aa3f23450d4b03aae60ecfe4d92e400c1d8efce9c6c5
size 7115878272

3
DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0.imatrix Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:51d1ae221463641ba1712841c5c89b64faa02dde9516f03f753f4bfec29290d0
size 2042214

166
README.md Normal file
View File

@@ -0,0 +1,166 @@
---
quantized_by: bartowski
pipeline_tag: text-generation
license: mit
base_model: mobiuslabsgmbh/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0
inference: false
train: false
---
## Llamacpp imatrix Quantizations of DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0
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/mobiuslabsgmbh/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0
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｜><｜end▁of▁sentence｜><｜Assistant｜>
```
## Download a file (not the whole branch) from below:
| Filename | Quant type | File Size | Split | Description |
| -------- | ---------- | --------- | ----- | ----------- |
| [DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-f32.gguf](https://huggingface.co/bartowski/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-GGUF/blob/main/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-f32.gguf) | f32 | 7.12GB | false | Full F32 weights. |
| [DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-f16.gguf](https://huggingface.co/bartowski/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-GGUF/blob/main/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-f16.gguf) | f16 | 3.56GB | false | Full F16 weights. |
| [DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-Q8_0.gguf](https://huggingface.co/bartowski/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-GGUF/blob/main/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-Q8_0.gguf) | Q8_0 | 1.89GB | false | Extremely high quality, generally unneeded but max available quant. |
| [DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-Q6_K_L.gguf](https://huggingface.co/bartowski/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-GGUF/blob/main/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-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-ReDistill-Qwen-1.5B-v1.0-Q6_K.gguf](https://huggingface.co/bartowski/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-GGUF/blob/main/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-Q6_K.gguf) | Q6_K | 1.46GB | false | Very high quality, near perfect, *recommended*. |
| [DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-Q5_K_L.gguf](https://huggingface.co/bartowski/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-GGUF/blob/main/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-Q5_K_L.gguf) | Q5_K_L | 1.43GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. |
| [DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-Q5_K_M.gguf](https://huggingface.co/bartowski/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-GGUF/blob/main/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-Q5_K_M.gguf) | Q5_K_M | 1.29GB | false | High quality, *recommended*. |
| [DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-Q4_K_L.gguf](https://huggingface.co/bartowski/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-GGUF/blob/main/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-Q4_K_L.gguf) | Q4_K_L | 1.29GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. |
| [DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-Q5_K_S.gguf](https://huggingface.co/bartowski/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-GGUF/blob/main/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-Q5_K_S.gguf) | Q5_K_S | 1.26GB | false | High quality, *recommended*. |
| [DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-Q3_K_XL.gguf](https://huggingface.co/bartowski/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-GGUF/blob/main/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-Q3_K_XL.gguf) | Q3_K_XL | 1.19GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. |
| [DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-Q4_1.gguf](https://huggingface.co/bartowski/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-GGUF/blob/main/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-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-ReDistill-Qwen-1.5B-v1.0-Q4_K_M.gguf](https://huggingface.co/bartowski/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-GGUF/blob/main/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-Q4_K_M.gguf) | Q4_K_M | 1.12GB | false | Good quality, default size for most use cases, *recommended*. |
| [DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-Q4_K_S.gguf](https://huggingface.co/bartowski/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-GGUF/blob/main/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-Q4_K_S.gguf) | Q4_K_S | 1.07GB | false | Slightly lower quality with more space savings, *recommended*. |
| [DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-Q4_0.gguf](https://huggingface.co/bartowski/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-GGUF/blob/main/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-Q4_0.gguf) | Q4_0 | 1.07GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. |
| [DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-IQ4_NL.gguf](https://huggingface.co/bartowski/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-GGUF/blob/main/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-IQ4_NL.gguf) | IQ4_NL | 1.07GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. |
| [DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-IQ4_XS.gguf](https://huggingface.co/bartowski/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-GGUF/blob/main/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-IQ4_XS.gguf) | IQ4_XS | 1.02GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
| [DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-Q3_K_L.gguf](https://huggingface.co/bartowski/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-GGUF/blob/main/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-Q3_K_L.gguf) | Q3_K_L | 0.98GB | false | Lower quality but usable, good for low RAM availability. |
| [DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-Q2_K_L.gguf](https://huggingface.co/bartowski/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-GGUF/blob/main/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-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-ReDistill-Qwen-1.5B-v1.0-Q3_K_M.gguf](https://huggingface.co/bartowski/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-GGUF/blob/main/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-Q3_K_M.gguf) | Q3_K_M | 0.92GB | false | Low quality. |
| [DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-IQ3_M.gguf](https://huggingface.co/bartowski/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-GGUF/blob/main/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-IQ3_M.gguf) | IQ3_M | 0.88GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
| [DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-Q3_K_S.gguf](https://huggingface.co/bartowski/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-GGUF/blob/main/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-Q3_K_S.gguf) | Q3_K_S | 0.86GB | false | Low quality, not recommended. |
| [DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-IQ3_XS.gguf](https://huggingface.co/bartowski/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-GGUF/blob/main/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-IQ3_XS.gguf) | IQ3_XS | 0.83GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
| [DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-Q2_K.gguf](https://huggingface.co/bartowski/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-GGUF/blob/main/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-Q2_K.gguf) | Q2_K | 0.75GB | false | Very low quality but surprisingly usable. |
| [DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-IQ2_M.gguf](https://huggingface.co/bartowski/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-GGUF/blob/main/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-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-ReDistill-Qwen-1.5B-v1.0-GGUF --include "DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-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-ReDistill-Qwen-1.5B-v1.0-GGUF --include "DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-Q8_0/*" --local-dir ./
```
You can either specify a new local-dir (DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-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}