bartowski/Llama-3.1_OpenScholar-8B-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/Llama-3.1_OpenScholar-8B-GGUF
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-06-18 00:08:13 +08:00
commit bdedf27bc5
28 changed files with 306 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
Llama-3.1_OpenScholar-8B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
Llama-3.1_OpenScholar-8B-Q6_K_L.gguf filter=lfs diff=lfs merge=lfs -text
Llama-3.1_OpenScholar-8B-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
Llama-3.1_OpenScholar-8B-Q5_K_L.gguf filter=lfs diff=lfs merge=lfs -text
Llama-3.1_OpenScholar-8B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
Llama-3.1_OpenScholar-8B-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
Llama-3.1_OpenScholar-8B-Q4_K_L.gguf filter=lfs diff=lfs merge=lfs -text
Llama-3.1_OpenScholar-8B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
Llama-3.1_OpenScholar-8B-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
Llama-3.1_OpenScholar-8B-Q4_0_8_8.gguf filter=lfs diff=lfs merge=lfs -text
Llama-3.1_OpenScholar-8B-Q4_0_4_8.gguf filter=lfs diff=lfs merge=lfs -text
Llama-3.1_OpenScholar-8B-Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text
Llama-3.1_OpenScholar-8B-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
Llama-3.1_OpenScholar-8B-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
Llama-3.1_OpenScholar-8B-Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
Llama-3.1_OpenScholar-8B-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
Llama-3.1_OpenScholar-8B-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
Llama-3.1_OpenScholar-8B-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
Llama-3.1_OpenScholar-8B-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
Llama-3.1_OpenScholar-8B-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
Llama-3.1_OpenScholar-8B-Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text
Llama-3.1_OpenScholar-8B-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
Llama-3.1_OpenScholar-8B-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text
Llama-3.1_OpenScholar-8B-f16.gguf filter=lfs diff=lfs merge=lfs -text
Llama-3.1_OpenScholar-8B.imatrix filter=lfs diff=lfs merge=lfs -text

3
Llama-3.1_OpenScholar-8B-IQ2_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:6057fde113b867a0a68bfd46dff19af40024d527b507bc1892b13380302158d4
size 2948281568

3
Llama-3.1_OpenScholar-8B-IQ3_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f95f97f5374e8bbba66d823a28c43c3363039842605fff68094b1a5f5a69bd68
size 3784824032

3
Llama-3.1_OpenScholar-8B-IQ3_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:735b3a8c0c515816fcb91f478644749d3c9822e25175870f86f0641d144af02d
size 3518747872

3
Llama-3.1_OpenScholar-8B-IQ4_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:135bdf4328da919026a0e7dabfa1b02a841f391aa84c134f1ab3583a212ecd96
size 4447663328

3
Llama-3.1_OpenScholar-8B-Q2_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:fa4b4bda43d7ba616b8d03592d1ef5e7d0c71ddb45b4508ea37cbdb7e92900fe
size 3179132128

3
Llama-3.1_OpenScholar-8B-Q2_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:bded69f1ab3aafc2ae97164391a13f67e217c4e54a4a6686f07c76919e0ba80d
size 3692156128

3
Llama-3.1_OpenScholar-8B-Q3_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:00d203a93c1931a9d1ddc03e480e04c7b0cb44d0917e3b7b8bb6c9f4276cbf0e
size 4321957088

3
Llama-3.1_OpenScholar-8B-Q3_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:85d707d88fb251f5407862a4503a3dd9c0c67cba74663d212341761ece3df692
size 4018918624

3
Llama-3.1_OpenScholar-8B-Q3_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0a7e880aaedad98c31a47b9be6f28405e1728651a6f15629a30f4384e3fb7a12
size 3664499936

3
Llama-3.1_OpenScholar-8B-Q3_K_XL.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:265b371f27beedcf007b71fe20799e8dda7ced3ee29c97f8519baabd27e0cdd6
size 4781626592

3
Llama-3.1_OpenScholar-8B-Q4_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b7f90f14359870e5e7d83fb66f16246c40bb3d4d9ae0bd6f5e8844b8afbd5c1f
size 4675892448

3
Llama-3.1_OpenScholar-8B-Q4_0_4_4.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:56947117a3b89ea0f524bb2be5d5921879df4421286067858c04faa459e0ec3c
size 4661212384

3
Llama-3.1_OpenScholar-8B-Q4_0_4_8.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:6de7180d7a4e325c62e61fd58e9385e343a4972b57a44ab5dfc2fdfe079d8724
size 4661212384

3
Llama-3.1_OpenScholar-8B-Q4_0_8_8.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:dd19da00e7413b4dcd54470bafb6c7accfadc760694efafb400e30c8fb947052
size 4661212384

3
Llama-3.1_OpenScholar-8B-Q4_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:330c70a197df7659629eb3da3bb74a3273b12be654e391e740f8bea290847388
size 5310633184

3
Llama-3.1_OpenScholar-8B-Q4_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:54865fc86451959b495c494a51bb1806c8b62bf1415600f0da2966a8a1fe6c7d
size 4920734944

3
Llama-3.1_OpenScholar-8B-Q4_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:4f6c5929cbdf4f91f7dbefce8d2b38e04f8af108039c8a0b976b8e59813f90ee
size 4692669664

3
Llama-3.1_OpenScholar-8B-Q5_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:75b66fd4d56551964688f3cb00f83006646adfe8b4d4b24a44146b117f392a5a
size 6057219296

3
Llama-3.1_OpenScholar-8B-Q5_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c1584e2b3a7e54075b5b5cfbcc9f3094e1c41e4583c1572e6605bd25c30d5088
size 5732988128

3
Llama-3.1_OpenScholar-8B-Q5_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9bdf0656a6ff9dc0941535ee741f6ef9c374116903684061c63f3d1ea7238b35
size 5599294688

3
Llama-3.1_OpenScholar-8B-Q6_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:cbcc7de869a79f1a7e440b015f7b6beffab5e9414ac5735ecd7d04e48fb07332
size 6596007136

3
Llama-3.1_OpenScholar-8B-Q6_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:33fcd9e20b3099567f055816ca0bf50772f32444fa122be2612cb7eaec4c419a
size 6850467040

3
Llama-3.1_OpenScholar-8B-Q8_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:50d74c013670c0de36876a6968846a531f5ffbe45c6a191b1eddd7536177fb9c
size 8540771552

3
Llama-3.1_OpenScholar-8B-f16.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ac9e80906e24484ae385f9b84525918557693de927a52bdfe1d8e81569c0fb53
size 16068891584

3
Llama-3.1_OpenScholar-8B.imatrix Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ddf3d108cec6c109e5e792aca36f13481d07a93b8db06f45ee6d2037a2a007ac
size 4988170

170
README.md Normal file
View File

@@ -0,0 +1,170 @@
---
quantized_by: bartowski
pipeline_tag: text-generation
base_model: OpenScholar/Llama-3.1_OpenScholar-8B
license: apache-2.0
language:
- en
---
## Llamacpp imatrix Quantizations of Llama-3.1_OpenScholar-8B
Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b4132">b4132</a> for quantization.
Original model: https://huggingface.co/OpenScholar/Llama-3.1_OpenScholar-8B
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_text|><|start_header_id|>system<|end_header_id|>
{system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>
{prompt}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
```
## Download a file (not the whole branch) from below:
| Filename | Quant type | File Size | Split | Description |
| -------- | ---------- | --------- | ----- | ----------- |
| [Llama-3.1_OpenScholar-8B-f16.gguf](https://huggingface.co/bartowski/Llama-3.1_OpenScholar-8B-GGUF/blob/main/Llama-3.1_OpenScholar-8B-f16.gguf) | f16 | 16.07GB | false | Full F16 weights. |
| [Llama-3.1_OpenScholar-8B-Q8_0.gguf](https://huggingface.co/bartowski/Llama-3.1_OpenScholar-8B-GGUF/blob/main/Llama-3.1_OpenScholar-8B-Q8_0.gguf) | Q8_0 | 8.54GB | false | Extremely high quality, generally unneeded but max available quant. |
| [Llama-3.1_OpenScholar-8B-Q6_K_L.gguf](https://huggingface.co/bartowski/Llama-3.1_OpenScholar-8B-GGUF/blob/main/Llama-3.1_OpenScholar-8B-Q6_K_L.gguf) | Q6_K_L | 6.85GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. |
| [Llama-3.1_OpenScholar-8B-Q6_K.gguf](https://huggingface.co/bartowski/Llama-3.1_OpenScholar-8B-GGUF/blob/main/Llama-3.1_OpenScholar-8B-Q6_K.gguf) | Q6_K | 6.60GB | false | Very high quality, near perfect, *recommended*. |
| [Llama-3.1_OpenScholar-8B-Q5_K_L.gguf](https://huggingface.co/bartowski/Llama-3.1_OpenScholar-8B-GGUF/blob/main/Llama-3.1_OpenScholar-8B-Q5_K_L.gguf) | Q5_K_L | 6.06GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. |
| [Llama-3.1_OpenScholar-8B-Q5_K_M.gguf](https://huggingface.co/bartowski/Llama-3.1_OpenScholar-8B-GGUF/blob/main/Llama-3.1_OpenScholar-8B-Q5_K_M.gguf) | Q5_K_M | 5.73GB | false | High quality, *recommended*. |
| [Llama-3.1_OpenScholar-8B-Q5_K_S.gguf](https://huggingface.co/bartowski/Llama-3.1_OpenScholar-8B-GGUF/blob/main/Llama-3.1_OpenScholar-8B-Q5_K_S.gguf) | Q5_K_S | 5.60GB | false | High quality, *recommended*. |
| [Llama-3.1_OpenScholar-8B-Q4_K_L.gguf](https://huggingface.co/bartowski/Llama-3.1_OpenScholar-8B-GGUF/blob/main/Llama-3.1_OpenScholar-8B-Q4_K_L.gguf) | Q4_K_L | 5.31GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. |
| [Llama-3.1_OpenScholar-8B-Q4_K_M.gguf](https://huggingface.co/bartowski/Llama-3.1_OpenScholar-8B-GGUF/blob/main/Llama-3.1_OpenScholar-8B-Q4_K_M.gguf) | Q4_K_M | 4.92GB | false | Good quality, default size for most use cases, *recommended*. |
| [Llama-3.1_OpenScholar-8B-Q3_K_XL.gguf](https://huggingface.co/bartowski/Llama-3.1_OpenScholar-8B-GGUF/blob/main/Llama-3.1_OpenScholar-8B-Q3_K_XL.gguf) | Q3_K_XL | 4.78GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. |
| [Llama-3.1_OpenScholar-8B-Q4_K_S.gguf](https://huggingface.co/bartowski/Llama-3.1_OpenScholar-8B-GGUF/blob/main/Llama-3.1_OpenScholar-8B-Q4_K_S.gguf) | Q4_K_S | 4.69GB | false | Slightly lower quality with more space savings, *recommended*. |
| [Llama-3.1_OpenScholar-8B-Q4_0.gguf](https://huggingface.co/bartowski/Llama-3.1_OpenScholar-8B-GGUF/blob/main/Llama-3.1_OpenScholar-8B-Q4_0.gguf) | Q4_0 | 4.68GB | false | Legacy format, generally not worth using over similarly sized formats |
| [Llama-3.1_OpenScholar-8B-Q4_0_8_8.gguf](https://huggingface.co/bartowski/Llama-3.1_OpenScholar-8B-GGUF/blob/main/Llama-3.1_OpenScholar-8B-Q4_0_8_8.gguf) | Q4_0_8_8 | 4.66GB | false | Optimized for ARM and AVX inference. Requires 'sve' support for ARM (see details below). *Don't use on Mac*. |
| [Llama-3.1_OpenScholar-8B-Q4_0_4_8.gguf](https://huggingface.co/bartowski/Llama-3.1_OpenScholar-8B-GGUF/blob/main/Llama-3.1_OpenScholar-8B-Q4_0_4_8.gguf) | Q4_0_4_8 | 4.66GB | false | Optimized for ARM inference. Requires 'i8mm' support (see details below). *Don't use on Mac*. |
| [Llama-3.1_OpenScholar-8B-Q4_0_4_4.gguf](https://huggingface.co/bartowski/Llama-3.1_OpenScholar-8B-GGUF/blob/main/Llama-3.1_OpenScholar-8B-Q4_0_4_4.gguf) | Q4_0_4_4 | 4.66GB | false | Optimized for ARM inference. Should work well on all ARM chips, not for use with GPUs. *Don't use on Mac*. |
| [Llama-3.1_OpenScholar-8B-IQ4_XS.gguf](https://huggingface.co/bartowski/Llama-3.1_OpenScholar-8B-GGUF/blob/main/Llama-3.1_OpenScholar-8B-IQ4_XS.gguf) | IQ4_XS | 4.45GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
| [Llama-3.1_OpenScholar-8B-Q3_K_L.gguf](https://huggingface.co/bartowski/Llama-3.1_OpenScholar-8B-GGUF/blob/main/Llama-3.1_OpenScholar-8B-Q3_K_L.gguf) | Q3_K_L | 4.32GB | false | Lower quality but usable, good for low RAM availability. |
| [Llama-3.1_OpenScholar-8B-Q3_K_M.gguf](https://huggingface.co/bartowski/Llama-3.1_OpenScholar-8B-GGUF/blob/main/Llama-3.1_OpenScholar-8B-Q3_K_M.gguf) | Q3_K_M | 4.02GB | false | Low quality. |
| [Llama-3.1_OpenScholar-8B-IQ3_M.gguf](https://huggingface.co/bartowski/Llama-3.1_OpenScholar-8B-GGUF/blob/main/Llama-3.1_OpenScholar-8B-IQ3_M.gguf) | IQ3_M | 3.78GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
| [Llama-3.1_OpenScholar-8B-Q2_K_L.gguf](https://huggingface.co/bartowski/Llama-3.1_OpenScholar-8B-GGUF/blob/main/Llama-3.1_OpenScholar-8B-Q2_K_L.gguf) | Q2_K_L | 3.69GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. |
| [Llama-3.1_OpenScholar-8B-Q3_K_S.gguf](https://huggingface.co/bartowski/Llama-3.1_OpenScholar-8B-GGUF/blob/main/Llama-3.1_OpenScholar-8B-Q3_K_S.gguf) | Q3_K_S | 3.66GB | false | Low quality, not recommended. |
| [Llama-3.1_OpenScholar-8B-IQ3_XS.gguf](https://huggingface.co/bartowski/Llama-3.1_OpenScholar-8B-GGUF/blob/main/Llama-3.1_OpenScholar-8B-IQ3_XS.gguf) | IQ3_XS | 3.52GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
| [Llama-3.1_OpenScholar-8B-Q2_K.gguf](https://huggingface.co/bartowski/Llama-3.1_OpenScholar-8B-GGUF/blob/main/Llama-3.1_OpenScholar-8B-Q2_K.gguf) | Q2_K | 3.18GB | false | Very low quality but surprisingly usable. |
| [Llama-3.1_OpenScholar-8B-IQ2_M.gguf](https://huggingface.co/bartowski/Llama-3.1_OpenScholar-8B-GGUF/blob/main/Llama-3.1_OpenScholar-8B-IQ2_M.gguf) | IQ2_M | 2.95GB | 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/Llama-3.1_OpenScholar-8B-GGUF --include "Llama-3.1_OpenScholar-8B-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/Llama-3.1_OpenScholar-8B-GGUF --include "Llama-3.1_OpenScholar-8B-Q8_0/*" --local-dir ./
```
You can either specify a new local-dir (Llama-3.1_OpenScholar-8B-Q8_0) or download them all in place (./)
</details>
## Q4_0_X_X information
<details>
<summary>Click to view Q4_0_X_X information</summary>
These are *NOT* for Metal (Apple) or GPU (nvidia/AMD/intel) offloading, only ARM chips (and certain AVX2/AVX512 CPUs).
If you're using an ARM chip, the Q4_0_X_X quants will have a substantial speedup. Check out Q4_0_4_4 speed comparisons [on the original pull request](https://github.com/ggerganov/llama.cpp/pull/5780#pullrequestreview-21657544660)
To check which one would work best for your ARM chip, you can check [AArch64 SoC features](https://gpages.juszkiewicz.com.pl/arm-socs-table/arm-socs.html) (thanks EloyOn!).
If you're using a CPU that supports AVX2 or AVX512 (typically server CPUs and AMD's latest Zen5 CPUs) and are not offloading to a GPU, the Q4_0_8_8 may offer a nice speed as well:
<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}