bartowski/POLARIS-Project_Polaris-7B-Preview-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/POLARIS-Project_Polaris-7B-Preview-GGUF
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-07-30 18:19:14 +08:00
commit 9ba340aba9
28 changed files with 289 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
POLARIS-Project_Polaris-7B-Preview-IQ2_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:4121a48ba4d9a146db4e91ad047214ed71353172fa64fbd41073c86b7475daec
size 2780342592

3
POLARIS-Project_Polaris-7B-Preview-IQ3_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:7b1843d131e7eac895879fc0b76c7c32277dea47f8f12d773011470d59d4dca4
size 3574012224

3
POLARIS-Project_Polaris-7B-Preview-IQ3_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f8dc0461fa86c95e63694aa638b44c887f0f7ce858914e7ea714bd5c76903f2f
size 3346256192

3
POLARIS-Project_Polaris-7B-Preview-IQ3_XXS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9be5cdbf660877542e6b0af45966626ca43e6f807d520cfceb6004fd4f51b8a5
size 3114514752

3
POLARIS-Project_Polaris-7B-Preview-IQ4_NL.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f1107290b1496a06f4850a21552a5dac05cd46417f406e6937c372eb9c88a9ce
size 4437813568

3
POLARIS-Project_Polaris-7B-Preview-IQ4_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2ca70c1f44634f5c6ab357ab030a78e01d5e06d7056aea42222208eb3f520e04
size 4218472768

3
POLARIS-Project_Polaris-7B-Preview-Q2_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:8f83b64e2f25cd04ba6a84a4616ad57a358aba1a9ab1941344952c5ccabfc8d7
size 3015940416

3
POLARIS-Project_Polaris-7B-Preview-Q2_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f4e7c1b27d03390fc92ad785ff701a0d154750dfa8e953a8c9e50d5872c14f9d
size 3548164416

3
POLARIS-Project_Polaris-7B-Preview-Q3_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0be40eb344aaa7ce4359bc221ed9c7ee315639bc9d067d0511916ddb06ae8fe6
size 4088459584

3
POLARIS-Project_Polaris-7B-Preview-Q3_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ce0fe7076382d72cec88e656e5adbf789577a51e0d15ec26413c4d7521d8cc17
size 3808391488

3
POLARIS-Project_Polaris-7B-Preview-Q3_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:163b911bbf5b8331bcc5ee134e82d9da0a4d8a1c56b6fde04842ef483270993b
size 3492368704

3
POLARIS-Project_Polaris-7B-Preview-Q3_K_XL.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c542d483189beda75651c25cde3acf2b3965aa8525bbcb2ab03dadedc6a68927
size 4565332288

3
POLARIS-Project_Polaris-7B-Preview-Q4_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:494cddf494afe4cba0367d379d7ba23b515bf1eb58e20ab5943826794b561eeb
size 4444121408

3
POLARIS-Project_Polaris-7B-Preview-Q4_1.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f829fe421c8db725c6ca15f6dc9e3c18a4baf91bc34830b5416b1da21e04321b
size 4873283904

3
POLARIS-Project_Polaris-7B-Preview-Q4_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a1d1c62b199f2d486c57c2c0b323982244eb816686f554186e3e08f5a5df162f
size 5087564096

3
POLARIS-Project_Polaris-7B-Preview-Q4_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b4c0f7b98472bacf01df64459db9234b512ae607b3a48f1c017429133ac0de81
size 4683073856

3
POLARIS-Project_Polaris-7B-Preview-Q4_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1306bec7afcd29597d5dc2b4b5ffe7a71fc068629efc1f9d938ebdcb7052cc3d
size 4457769280

3
POLARIS-Project_Polaris-7B-Preview-Q5_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:857dada71323546ef57bf29f0e04090bc132c3b5eb9852e235e5d529f4c287b4
size 5781197120

3
POLARIS-Project_Polaris-7B-Preview-Q5_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:408d5ad28b5b37fa91dcc698f8ad0d7f0322b4eb37d6a352d56525075ef85525
size 5444831552

3
POLARIS-Project_Polaris-7B-Preview-Q5_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:6180d8faa1d43fe39f83a35b121238a0fb0b3c63cfbdfa61d286514c63a0deb8
size 5315176768

3
POLARIS-Project_Polaris-7B-Preview-Q6_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:016867ccd28c2fcaae547656d326fe880b1019c262415a04e08185c973903ec8
size 6254199104

3
POLARIS-Project_Polaris-7B-Preview-Q6_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:6b3819f9b82cbcd4c67cfdef981044e0aedeb0470e435a1318933cdebe3de5c2
size 6518182208

3
POLARIS-Project_Polaris-7B-Preview-Q8_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:7e90da8d5fbb7cbdeff1e4591c9581cb521ee475bf525b09f9ecc23eca562537
size 8098525504

3
POLARIS-Project_Polaris-7B-Preview-bf16.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:69a81e220ecc768e81440820fce88838b6a0505493748e0a7a932ad33b426f11
size 15237853216

BIN
POLARIS-Project_Polaris-7B-Preview.imatrix Normal file
View File

Binary file not shown.

169
README.md Normal file
View File

@@ -0,0 +1,169 @@
---
quantized_by: bartowski
pipeline_tag: text-generation
base_model: POLARIS-Project/Polaris-7B-Preview
base_model_relation: quantized
metrics:
- accuracy
license: apache-2.0
---
## Llamacpp imatrix Quantizations of Polaris-7B-Preview by POLARIS-Project
Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b5697">b5697</a> for quantization.
Original model: https://huggingface.co/POLARIS-Project/Polaris-7B-Preview
All quants made using imatrix option with dataset from [here](https://gist.github.com/bartowski1182/eb213dccb3571f863da82e99418f81e8)
Run them in [LM Studio](https://lmstudio.ai/)
Run them directly with [llama.cpp](https://github.com/ggerganov/llama.cpp), or any other llama.cpp based project
## Prompt format
```
<｜begin▁of▁sentence｜>{system_prompt}<｜User｜>{prompt}<｜Assistant｜><｜end▁of▁sentence｜><｜Assistant｜><think>
```
## Download a file (not the whole branch) from below:
| Filename | Quant type | File Size | Split | Description |
| -------- | ---------- | --------- | ----- | ----------- |
| [Polaris-7B-Preview-bf16.gguf](https://huggingface.co/bartowski/POLARIS-Project_Polaris-7B-Preview-GGUF/blob/main/POLARIS-Project_Polaris-7B-Preview-bf16.gguf) | bf16 | 15.24GB | false | Full BF16 weights. |
| [Polaris-7B-Preview-Q8_0.gguf](https://huggingface.co/bartowski/POLARIS-Project_Polaris-7B-Preview-GGUF/blob/main/POLARIS-Project_Polaris-7B-Preview-Q8_0.gguf) | Q8_0 | 8.10GB | false | Extremely high quality, generally unneeded but max available quant. |
| [Polaris-7B-Preview-Q6_K_L.gguf](https://huggingface.co/bartowski/POLARIS-Project_Polaris-7B-Preview-GGUF/blob/main/POLARIS-Project_Polaris-7B-Preview-Q6_K_L.gguf) | Q6_K_L | 6.52GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. |
| [Polaris-7B-Preview-Q6_K.gguf](https://huggingface.co/bartowski/POLARIS-Project_Polaris-7B-Preview-GGUF/blob/main/POLARIS-Project_Polaris-7B-Preview-Q6_K.gguf) | Q6_K | 6.25GB | false | Very high quality, near perfect, *recommended*. |
| [Polaris-7B-Preview-Q5_K_L.gguf](https://huggingface.co/bartowski/POLARIS-Project_Polaris-7B-Preview-GGUF/blob/main/POLARIS-Project_Polaris-7B-Preview-Q5_K_L.gguf) | Q5_K_L | 5.78GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. |
| [Polaris-7B-Preview-Q5_K_M.gguf](https://huggingface.co/bartowski/POLARIS-Project_Polaris-7B-Preview-GGUF/blob/main/POLARIS-Project_Polaris-7B-Preview-Q5_K_M.gguf) | Q5_K_M | 5.44GB | false | High quality, *recommended*. |
| [Polaris-7B-Preview-Q5_K_S.gguf](https://huggingface.co/bartowski/POLARIS-Project_Polaris-7B-Preview-GGUF/blob/main/POLARIS-Project_Polaris-7B-Preview-Q5_K_S.gguf) | Q5_K_S | 5.32GB | false | High quality, *recommended*. |
| [Polaris-7B-Preview-Q4_K_L.gguf](https://huggingface.co/bartowski/POLARIS-Project_Polaris-7B-Preview-GGUF/blob/main/POLARIS-Project_Polaris-7B-Preview-Q4_K_L.gguf) | Q4_K_L | 5.09GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. |
| [Polaris-7B-Preview-Q4_1.gguf](https://huggingface.co/bartowski/POLARIS-Project_Polaris-7B-Preview-GGUF/blob/main/POLARIS-Project_Polaris-7B-Preview-Q4_1.gguf) | Q4_1 | 4.87GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. |
| [Polaris-7B-Preview-Q4_K_M.gguf](https://huggingface.co/bartowski/POLARIS-Project_Polaris-7B-Preview-GGUF/blob/main/POLARIS-Project_Polaris-7B-Preview-Q4_K_M.gguf) | Q4_K_M | 4.68GB | false | Good quality, default size for most use cases, *recommended*. |
| [Polaris-7B-Preview-Q3_K_XL.gguf](https://huggingface.co/bartowski/POLARIS-Project_Polaris-7B-Preview-GGUF/blob/main/POLARIS-Project_Polaris-7B-Preview-Q3_K_XL.gguf) | Q3_K_XL | 4.57GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. |
| [Polaris-7B-Preview-Q4_K_S.gguf](https://huggingface.co/bartowski/POLARIS-Project_Polaris-7B-Preview-GGUF/blob/main/POLARIS-Project_Polaris-7B-Preview-Q4_K_S.gguf) | Q4_K_S | 4.46GB | false | Slightly lower quality with more space savings, *recommended*. |
| [Polaris-7B-Preview-Q4_0.gguf](https://huggingface.co/bartowski/POLARIS-Project_Polaris-7B-Preview-GGUF/blob/main/POLARIS-Project_Polaris-7B-Preview-Q4_0.gguf) | Q4_0 | 4.44GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. |
| [Polaris-7B-Preview-IQ4_NL.gguf](https://huggingface.co/bartowski/POLARIS-Project_Polaris-7B-Preview-GGUF/blob/main/POLARIS-Project_Polaris-7B-Preview-IQ4_NL.gguf) | IQ4_NL | 4.44GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. |
| [Polaris-7B-Preview-IQ4_XS.gguf](https://huggingface.co/bartowski/POLARIS-Project_Polaris-7B-Preview-GGUF/blob/main/POLARIS-Project_Polaris-7B-Preview-IQ4_XS.gguf) | IQ4_XS | 4.22GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
| [Polaris-7B-Preview-Q3_K_L.gguf](https://huggingface.co/bartowski/POLARIS-Project_Polaris-7B-Preview-GGUF/blob/main/POLARIS-Project_Polaris-7B-Preview-Q3_K_L.gguf) | Q3_K_L | 4.09GB | false | Lower quality but usable, good for low RAM availability. |
| [Polaris-7B-Preview-Q3_K_M.gguf](https://huggingface.co/bartowski/POLARIS-Project_Polaris-7B-Preview-GGUF/blob/main/POLARIS-Project_Polaris-7B-Preview-Q3_K_M.gguf) | Q3_K_M | 3.81GB | false | Low quality. |
| [Polaris-7B-Preview-IQ3_M.gguf](https://huggingface.co/bartowski/POLARIS-Project_Polaris-7B-Preview-GGUF/blob/main/POLARIS-Project_Polaris-7B-Preview-IQ3_M.gguf) | IQ3_M | 3.57GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
| [Polaris-7B-Preview-Q2_K_L.gguf](https://huggingface.co/bartowski/POLARIS-Project_Polaris-7B-Preview-GGUF/blob/main/POLARIS-Project_Polaris-7B-Preview-Q2_K_L.gguf) | Q2_K_L | 3.55GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. |
| [Polaris-7B-Preview-Q3_K_S.gguf](https://huggingface.co/bartowski/POLARIS-Project_Polaris-7B-Preview-GGUF/blob/main/POLARIS-Project_Polaris-7B-Preview-Q3_K_S.gguf) | Q3_K_S | 3.49GB | false | Low quality, not recommended. |
| [Polaris-7B-Preview-IQ3_XS.gguf](https://huggingface.co/bartowski/POLARIS-Project_Polaris-7B-Preview-GGUF/blob/main/POLARIS-Project_Polaris-7B-Preview-IQ3_XS.gguf) | IQ3_XS | 3.35GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
| [Polaris-7B-Preview-IQ3_XXS.gguf](https://huggingface.co/bartowski/POLARIS-Project_Polaris-7B-Preview-GGUF/blob/main/POLARIS-Project_Polaris-7B-Preview-IQ3_XXS.gguf) | IQ3_XXS | 3.11GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. |
| [Polaris-7B-Preview-Q2_K.gguf](https://huggingface.co/bartowski/POLARIS-Project_Polaris-7B-Preview-GGUF/blob/main/POLARIS-Project_Polaris-7B-Preview-Q2_K.gguf) | Q2_K | 3.02GB | false | Very low quality but surprisingly usable. |
| [Polaris-7B-Preview-IQ2_M.gguf](https://huggingface.co/bartowski/POLARIS-Project_Polaris-7B-Preview-GGUF/blob/main/POLARIS-Project_Polaris-7B-Preview-IQ2_M.gguf) | IQ2_M | 2.78GB | 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/POLARIS-Project_Polaris-7B-Preview-GGUF --include "POLARIS-Project_Polaris-7B-Preview-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/POLARIS-Project_Polaris-7B-Preview-GGUF --include "POLARIS-Project_Polaris-7B-Preview-Q8_0/*" --local-dir ./
```
You can either specify a new local-dir (POLARIS-Project_Polaris-7B-Preview-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, 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}