bartowski/DRT-o1-14B-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/DRT-o1-14B-GGUF
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-08-07 16:35:13 +08:00
commit b74523fc5f
27 changed files with 306 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

59
.gitattributes vendored Normal file
View File

@@ -0,0 +1,59 @@
*.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
DRT-o1-14B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
DRT-o1-14B-Q6_K_L.gguf filter=lfs diff=lfs merge=lfs -text
DRT-o1-14B-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
DRT-o1-14B-Q5_K_L.gguf filter=lfs diff=lfs merge=lfs -text
DRT-o1-14B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
DRT-o1-14B-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
DRT-o1-14B-Q4_K_L.gguf filter=lfs diff=lfs merge=lfs -text
DRT-o1-14B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
DRT-o1-14B-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
DRT-o1-14B-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text
DRT-o1-14B-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
DRT-o1-14B-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text
DRT-o1-14B-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
DRT-o1-14B-Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
DRT-o1-14B-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
DRT-o1-14B-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
DRT-o1-14B-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
DRT-o1-14B-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
DRT-o1-14B-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
DRT-o1-14B-Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text
DRT-o1-14B-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
DRT-o1-14B-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text
DRT-o1-14B-f16.gguf filter=lfs diff=lfs merge=lfs -text
DRT-o1-14B.imatrix filter=lfs diff=lfs merge=lfs -text

3
DRT-o1-14B-IQ2_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5dd1e8b5b777cf55f8f0c831a7ce3bb1b55fb3de1ade3677fba92133623914e1
size 5356146720

3
DRT-o1-14B-IQ3_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:eadf2fe02ed01b6be9f81d08475b768dae509bfc8f4bd9fe500b5679fc1d83f5
size 6916538400

3
DRT-o1-14B-IQ3_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:892a82a6f33c5d7d584d75a9b6b6adc4f85d2b7c8132342bbf87b9d1235931ae
size 6383362080

3
DRT-o1-14B-IQ4_NL.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:51c30e0fbf80c4cd96137c91c5cbf3d25d20df10df45de1febea1e79122f2e7f
size 8549183520

3
DRT-o1-14B-IQ4_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:dad55ff05c25138f8105333fe1348b2f5dac383a3a18ff69a25096f2fce968a1
size 8119840800

3
DRT-o1-14B-Q2_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a46cf579cff481321f7c7401fa3c70a2b8e9055d38e3344565b1fdac5c8cae91
size 5770498080

3
DRT-o1-14B-Q2_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:41b9721adafd83970ba014a172286afca629896cff06358051b7ec7cd5530976
size 6530818080

3
DRT-o1-14B-Q3_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0c33ad412a02890ce17c6ddf09c84dea3a4d152b5ca9cf0b64aea60b648b6c9c
size 7924768800

3
DRT-o1-14B-Q3_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ee579a8bf34f92a874090fb5b69decd44b072457984fb10e6ac6085b3f52b096
size 7339204640

3
DRT-o1-14B-Q3_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:72ee31b9a3e8633a5a301d60ed4cb60a9ea9bbcd64ca41fde1ed2ab25bd3cdf8
size 6659596320

3
DRT-o1-14B-Q3_K_XL.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:991f7d3742cb3c75660e58a563a61bbf14e5e5e951c21fec4c36bee15bc477ee
size 8606015520

3
DRT-o1-14B-Q4_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b3c53bf7c4e958950598cf5cff722db97605c585b402a6a6860b56fadd51c88d
size 8544268320

3
DRT-o1-14B-Q4_1.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:4b785015ed9e42055ce8dc6db9d98fb5842f4ae02feeff7a75dfd597cf793f64
size 9392140320

3
DRT-o1-14B-Q4_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:15afbd920e09dde688e24e325a61198975057a2a0da7483dd5f676d6692c56e6
size 9565954080

3
DRT-o1-14B-Q4_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9619ca984cf4ce8e4f69bcde831de17b2ce05dd89536e3130608877521e3d328
size 8988110880

3
DRT-o1-14B-Q4_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5237677537fe6563d7b33d42f90df67bffa15fca7c14ceaeea176c7fb5d4d31e
size 8573431840

3
DRT-o1-14B-Q5_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:46cdb30cf0d9b8117675c499a923357284ed752a847553ae32761ddcfbd8863c
size 10989396000

3
DRT-o1-14B-Q5_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2c59415801818ccfed599cb71acef3a30f82b71ae02ed59297419687bf4fc72d
size 10508873760

3
DRT-o1-14B-Q5_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:6c9ff415b29d1e89bc9611daf13a36b58b90c457ad1d00efb79a9087dc0567e0
size 10266554400

3
DRT-o1-14B-Q6_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:16c5d7e07ffcfef9f8d668264233e117df6fde6608b2e550cebe88fc3d81b2f9
size 12124684320

3
DRT-o1-14B-Q6_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:6ae8cf3fcffa48cfa648d0cae2a186f016db1c3da873206002316e0271bf6257
size 12501803040

3
DRT-o1-14B-Q8_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ea9e0b6d09d79ed060db5c1657dcdb6b847cfb62e3cdd764ac3e31f7037b4431
size 15701598240

3
DRT-o1-14B-f16.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:63c5e2b2b805dd3d4fce89340a78aa94b53f8f42a96b7fa4d79c9a8a9131e6b3
size 29547716384

3
DRT-o1-14B.imatrix Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ceb06381c9b36fddbc697c0a07ade9d4b748e09d4e2fe68a7a5a2dcc9b3a0eb0
size 8563610

174
README.md Normal file
View File

@@ -0,0 +1,174 @@
---
quantized_by: bartowski
pipeline_tag: text-generation
base_model: Krystalan/DRT-o1-14B
license: cc-by-nc-sa-4.0
tags:
- machine tranlsation
- O1-like model
- Chat
language:
- en
- zh
---
## Llamacpp imatrix Quantizations of DRT-o1-14B
Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b4381">b4381</a> for quantization.
Original model: https://huggingface.co/Krystalan/DRT-o1-14B
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
```
<|im_start|>system
{system_prompt}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
```
## Download a file (not the whole branch) from below:
| Filename | Quant type | File Size | Split | Description |
| -------- | ---------- | --------- | ----- | ----------- |
| [DRT-o1-14B-f16.gguf](https://huggingface.co/bartowski/DRT-o1-14B-GGUF/blob/main/DRT-o1-14B-f16.gguf) | f16 | 29.55GB | false | Full F16 weights. |
| [DRT-o1-14B-Q8_0.gguf](https://huggingface.co/bartowski/DRT-o1-14B-GGUF/blob/main/DRT-o1-14B-Q8_0.gguf) | Q8_0 | 15.70GB | false | Extremely high quality, generally unneeded but max available quant. |
| [DRT-o1-14B-Q6_K_L.gguf](https://huggingface.co/bartowski/DRT-o1-14B-GGUF/blob/main/DRT-o1-14B-Q6_K_L.gguf) | Q6_K_L | 12.50GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. |
| [DRT-o1-14B-Q6_K.gguf](https://huggingface.co/bartowski/DRT-o1-14B-GGUF/blob/main/DRT-o1-14B-Q6_K.gguf) | Q6_K | 12.12GB | false | Very high quality, near perfect, *recommended*. |
| [DRT-o1-14B-Q5_K_L.gguf](https://huggingface.co/bartowski/DRT-o1-14B-GGUF/blob/main/DRT-o1-14B-Q5_K_L.gguf) | Q5_K_L | 10.99GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. |
| [DRT-o1-14B-Q5_K_M.gguf](https://huggingface.co/bartowski/DRT-o1-14B-GGUF/blob/main/DRT-o1-14B-Q5_K_M.gguf) | Q5_K_M | 10.51GB | false | High quality, *recommended*. |
| [DRT-o1-14B-Q5_K_S.gguf](https://huggingface.co/bartowski/DRT-o1-14B-GGUF/blob/main/DRT-o1-14B-Q5_K_S.gguf) | Q5_K_S | 10.27GB | false | High quality, *recommended*. |
| [DRT-o1-14B-Q4_K_L.gguf](https://huggingface.co/bartowski/DRT-o1-14B-GGUF/blob/main/DRT-o1-14B-Q4_K_L.gguf) | Q4_K_L | 9.57GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. |
| [DRT-o1-14B-Q4_1.gguf](https://huggingface.co/bartowski/DRT-o1-14B-GGUF/blob/main/DRT-o1-14B-Q4_1.gguf) | Q4_1 | 9.39GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. |
| [DRT-o1-14B-Q4_K_M.gguf](https://huggingface.co/bartowski/DRT-o1-14B-GGUF/blob/main/DRT-o1-14B-Q4_K_M.gguf) | Q4_K_M | 8.99GB | false | Good quality, default size for most use cases, *recommended*. |
| [DRT-o1-14B-Q3_K_XL.gguf](https://huggingface.co/bartowski/DRT-o1-14B-GGUF/blob/main/DRT-o1-14B-Q3_K_XL.gguf) | Q3_K_XL | 8.61GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. |
| [DRT-o1-14B-Q4_K_S.gguf](https://huggingface.co/bartowski/DRT-o1-14B-GGUF/blob/main/DRT-o1-14B-Q4_K_S.gguf) | Q4_K_S | 8.57GB | false | Slightly lower quality with more space savings, *recommended*. |
| [DRT-o1-14B-IQ4_NL.gguf](https://huggingface.co/bartowski/DRT-o1-14B-GGUF/blob/main/DRT-o1-14B-IQ4_NL.gguf) | IQ4_NL | 8.55GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. |
| [DRT-o1-14B-Q4_0.gguf](https://huggingface.co/bartowski/DRT-o1-14B-GGUF/blob/main/DRT-o1-14B-Q4_0.gguf) | Q4_0 | 8.54GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. |
| [DRT-o1-14B-IQ4_XS.gguf](https://huggingface.co/bartowski/DRT-o1-14B-GGUF/blob/main/DRT-o1-14B-IQ4_XS.gguf) | IQ4_XS | 8.12GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
| [DRT-o1-14B-Q3_K_L.gguf](https://huggingface.co/bartowski/DRT-o1-14B-GGUF/blob/main/DRT-o1-14B-Q3_K_L.gguf) | Q3_K_L | 7.92GB | false | Lower quality but usable, good for low RAM availability. |
| [DRT-o1-14B-Q3_K_M.gguf](https://huggingface.co/bartowski/DRT-o1-14B-GGUF/blob/main/DRT-o1-14B-Q3_K_M.gguf) | Q3_K_M | 7.34GB | false | Low quality. |
| [DRT-o1-14B-IQ3_M.gguf](https://huggingface.co/bartowski/DRT-o1-14B-GGUF/blob/main/DRT-o1-14B-IQ3_M.gguf) | IQ3_M | 6.92GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
| [DRT-o1-14B-Q3_K_S.gguf](https://huggingface.co/bartowski/DRT-o1-14B-GGUF/blob/main/DRT-o1-14B-Q3_K_S.gguf) | Q3_K_S | 6.66GB | false | Low quality, not recommended. |
| [DRT-o1-14B-Q2_K_L.gguf](https://huggingface.co/bartowski/DRT-o1-14B-GGUF/blob/main/DRT-o1-14B-Q2_K_L.gguf) | Q2_K_L | 6.53GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. |
| [DRT-o1-14B-IQ3_XS.gguf](https://huggingface.co/bartowski/DRT-o1-14B-GGUF/blob/main/DRT-o1-14B-IQ3_XS.gguf) | IQ3_XS | 6.38GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
| [DRT-o1-14B-Q2_K.gguf](https://huggingface.co/bartowski/DRT-o1-14B-GGUF/blob/main/DRT-o1-14B-Q2_K.gguf) | Q2_K | 5.77GB | false | Very low quality but surprisingly usable. |
| [DRT-o1-14B-IQ2_M.gguf](https://huggingface.co/bartowski/DRT-o1-14B-GGUF/blob/main/DRT-o1-14B-IQ2_M.gguf) | IQ2_M | 5.36GB | 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/DRT-o1-14B-GGUF --include "DRT-o1-14B-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/DRT-o1-14B-GGUF --include "DRT-o1-14B-Q8_0/*" --local-dir ./
```
You can either specify a new local-dir (DRT-o1-14B-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}