bartowski/Llama-Song-Stream-3B-Instruct-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-Song-Stream-3B-Instruct-GGUF
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-09-22 02:09:18 +08:00
commit 7f9534173d
26 changed files with 312 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

58
.gitattributes vendored Normal file
View File

@@ -0,0 +1,58 @@
*.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-Song-Stream-3B-Instruct-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
Llama-Song-Stream-3B-Instruct-Q6_K_L.gguf filter=lfs diff=lfs merge=lfs -text
Llama-Song-Stream-3B-Instruct-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
Llama-Song-Stream-3B-Instruct-Q5_K_L.gguf filter=lfs diff=lfs merge=lfs -text
Llama-Song-Stream-3B-Instruct-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
Llama-Song-Stream-3B-Instruct-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
Llama-Song-Stream-3B-Instruct-Q4_K_L.gguf filter=lfs diff=lfs merge=lfs -text
Llama-Song-Stream-3B-Instruct-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
Llama-Song-Stream-3B-Instruct-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
Llama-Song-Stream-3B-Instruct-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
Llama-Song-Stream-3B-Instruct-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text
Llama-Song-Stream-3B-Instruct-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
Llama-Song-Stream-3B-Instruct-Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
Llama-Song-Stream-3B-Instruct-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
Llama-Song-Stream-3B-Instruct-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
Llama-Song-Stream-3B-Instruct-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
Llama-Song-Stream-3B-Instruct-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
Llama-Song-Stream-3B-Instruct-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
Llama-Song-Stream-3B-Instruct-Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text
Llama-Song-Stream-3B-Instruct-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
Llama-Song-Stream-3B-Instruct-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text
Llama-Song-Stream-3B-Instruct-f16.gguf filter=lfs diff=lfs merge=lfs -text
Llama-Song-Stream-3B-Instruct.imatrix filter=lfs diff=lfs merge=lfs -text

3
Llama-Song-Stream-3B-Instruct-IQ2_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1b9e36d9198ca807244cfab1d26f92ed13ba9ad8d9706e823221b9e01060329b
size 1229033376

3
Llama-Song-Stream-3B-Instruct-IQ3_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:204b89ef568f5f0b548f427aac40ee247c6b606b368a5025e583b5ec51cf6837
size 1599670176

3
Llama-Song-Stream-3B-Instruct-IQ3_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:92bf49cb082e1e38bd60a4b1a35211c32d7381ddd472a4f12ccabade19da75ec
size 1476790176

3
Llama-Song-Stream-3B-Instruct-IQ4_NL.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:8fb91cc56e57326870f1be6b6914f528f0ab8673a3d473d86426c2bd708e48be
size 1917192096

3
Llama-Song-Stream-3B-Instruct-IQ4_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:4bccf3e06a2c2125d6354d6d012d2631a131d122af98ebc535758bd2052d0398
size 1829111712

3
Llama-Song-Stream-3B-Instruct-Q2_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5239ec98b6e2dc82f391010463c890e6feca69e5f712814c37641e9816c7af7b
size 1363937184

3
Llama-Song-Stream-3B-Instruct-Q2_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:8c472ee62a0c73f883a6d3cfd962b0bdc9bfde760365fcd92eaff2678b669c2c
size 1459359648

3
Llama-Song-Stream-3B-Instruct-Q3_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ade6b658549e10e11532a609cb4d7f3085ef1f9ca2b25532cdf5d92cbad46985
size 1815349152

3
Llama-Song-Stream-3B-Instruct-Q3_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:18e00a50b321bfc9de15c34d1cf28582e3cdd559b095a59d736a2fefb7142b4a
size 1687160736

3
Llama-Song-Stream-3B-Instruct-Q3_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0a3fe27eefa896294ff1761ec659660cd370ba211814a3901a762c9fd4a0b19d
size 1542850464

3
Llama-Song-Stream-3B-Instruct-Q3_K_XL.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:64913237c5e344361f4c2df8b847c597d055fa28482aa1ca5dfe3077bc2ca447
size 1910771616

3
Llama-Song-Stream-3B-Instruct-Q4_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:6b3563143e658409fac28bc6b1590fed5a176631e88d654f3acf9ea5c7e4db0f
size 1921910688

3
Llama-Song-Stream-3B-Instruct-Q4_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f690c545dbbdaaddc2761c4139ccc9a39ab26657c592594be8e1ac6c21e3736b
size 2114801568

3
Llama-Song-Stream-3B-Instruct-Q4_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:62e4a79eb7a0f80184dc37ab01a5490708e600dad5f074de8bcda6ec5a77cca8
size 2019379104

3
Llama-Song-Stream-3B-Instruct-Q4_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:bf7416892783c23d055230b88413e3dde3d3aa6acdc6b0f46607ca952acb02e2
size 1928202144

3
Llama-Song-Stream-3B-Instruct-Q5_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:00c011e6b6ac2f4bcc1ec8e52753a3c65741ba6ed2bc6c822ff006d99dfc6d49
size 2417577888

3
Llama-Song-Stream-3B-Instruct-Q5_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:fdddd027731ee9d4c0e0257cf73498220c7a7b5905c79ec078a0e62752815ec0
size 2322155424

3
Llama-Song-Stream-3B-Instruct-Q5_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b7fcdd1fe08aad595a0f58b66807da2e76f6ae0110ce2c3bb0188f43b6a8b98b
size 2269513632

3
Llama-Song-Stream-3B-Instruct-Q6_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:13e9babfc8519180624f53032d84965ec1c93dcab5d5b51e3a6028cd5f58dbfa
size 2643855264

3
Llama-Song-Stream-3B-Instruct-Q6_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:300e408365c57794d3a850b44d2bbc3db57ba179fbac7d08a24bc20bceb5ce15
size 2739277728

3
Llama-Song-Stream-3B-Instruct-Q8_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3fbdfbfda93d5ad1232e0667410941d62efb283758ac04132b3b28e6b049829c
size 3421900704

3
Llama-Song-Stream-3B-Instruct-f16.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:02556796472e439c3ff8dd54290cabbd05ed2cccdc8a64dc6698fdb9950a2868
size 6433689184

3
Llama-Song-Stream-3B-Instruct.imatrix Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e30ffca9bfdadcef56cdb92032d066a1ecb6d8fe506f5e40b61f555906734612
size 2988390

184
README.md Normal file
View File

@@ -0,0 +1,184 @@
---
quantized_by: bartowski
pipeline_tag: text-generation
language:
- en
datasets:
- prithivMLmods/Song-Catalogue-Long-Thought
tags:
- safetensors
- Llama3.2
- 3B
- Extended-Stream
- text-generation-inference
- Instruct
license: apache-2.0
base_model: prithivMLmods/Llama-Song-Stream-3B-Instruct
---
## Llamacpp imatrix Quantizations of Llama-Song-Stream-3B-Instruct
Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b4369">b4369</a> for quantization.
Original model: https://huggingface.co/prithivMLmods/Llama-Song-Stream-3B-Instruct
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|>
Cutting Knowledge Date: December 2023
Today Date: 26 July 2024
{system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>
{prompt}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
```
## What's new:
Fix tokenizer
## Download a file (not the whole branch) from below:
| Filename | Quant type | File Size | Split | Description |
| -------- | ---------- | --------- | ----- | ----------- |
| [Llama-Song-Stream-3B-Instruct-f16.gguf](https://huggingface.co/bartowski/Llama-Song-Stream-3B-Instruct-GGUF/blob/main/Llama-Song-Stream-3B-Instruct-f16.gguf) | f16 | 6.43GB | false | Full F16 weights. |
| [Llama-Song-Stream-3B-Instruct-Q8_0.gguf](https://huggingface.co/bartowski/Llama-Song-Stream-3B-Instruct-GGUF/blob/main/Llama-Song-Stream-3B-Instruct-Q8_0.gguf) | Q8_0 | 3.42GB | false | Extremely high quality, generally unneeded but max available quant. |
| [Llama-Song-Stream-3B-Instruct-Q6_K_L.gguf](https://huggingface.co/bartowski/Llama-Song-Stream-3B-Instruct-GGUF/blob/main/Llama-Song-Stream-3B-Instruct-Q6_K_L.gguf) | Q6_K_L | 2.74GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. |
| [Llama-Song-Stream-3B-Instruct-Q6_K.gguf](https://huggingface.co/bartowski/Llama-Song-Stream-3B-Instruct-GGUF/blob/main/Llama-Song-Stream-3B-Instruct-Q6_K.gguf) | Q6_K | 2.64GB | false | Very high quality, near perfect, *recommended*. |
| [Llama-Song-Stream-3B-Instruct-Q5_K_L.gguf](https://huggingface.co/bartowski/Llama-Song-Stream-3B-Instruct-GGUF/blob/main/Llama-Song-Stream-3B-Instruct-Q5_K_L.gguf) | Q5_K_L | 2.42GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. |
| [Llama-Song-Stream-3B-Instruct-Q5_K_M.gguf](https://huggingface.co/bartowski/Llama-Song-Stream-3B-Instruct-GGUF/blob/main/Llama-Song-Stream-3B-Instruct-Q5_K_M.gguf) | Q5_K_M | 2.32GB | false | High quality, *recommended*. |
| [Llama-Song-Stream-3B-Instruct-Q5_K_S.gguf](https://huggingface.co/bartowski/Llama-Song-Stream-3B-Instruct-GGUF/blob/main/Llama-Song-Stream-3B-Instruct-Q5_K_S.gguf) | Q5_K_S | 2.27GB | false | High quality, *recommended*. |
| [Llama-Song-Stream-3B-Instruct-Q4_K_L.gguf](https://huggingface.co/bartowski/Llama-Song-Stream-3B-Instruct-GGUF/blob/main/Llama-Song-Stream-3B-Instruct-Q4_K_L.gguf) | Q4_K_L | 2.11GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. |
| [Llama-Song-Stream-3B-Instruct-Q4_K_M.gguf](https://huggingface.co/bartowski/Llama-Song-Stream-3B-Instruct-GGUF/blob/main/Llama-Song-Stream-3B-Instruct-Q4_K_M.gguf) | Q4_K_M | 2.02GB | false | Good quality, default size for most use cases, *recommended*. |
| [Llama-Song-Stream-3B-Instruct-Q4_K_S.gguf](https://huggingface.co/bartowski/Llama-Song-Stream-3B-Instruct-GGUF/blob/main/Llama-Song-Stream-3B-Instruct-Q4_K_S.gguf) | Q4_K_S | 1.93GB | false | Slightly lower quality with more space savings, *recommended*. |
| [Llama-Song-Stream-3B-Instruct-Q4_0.gguf](https://huggingface.co/bartowski/Llama-Song-Stream-3B-Instruct-GGUF/blob/main/Llama-Song-Stream-3B-Instruct-Q4_0.gguf) | Q4_0 | 1.92GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. |
| [Llama-Song-Stream-3B-Instruct-IQ4_NL.gguf](https://huggingface.co/bartowski/Llama-Song-Stream-3B-Instruct-GGUF/blob/main/Llama-Song-Stream-3B-Instruct-IQ4_NL.gguf) | IQ4_NL | 1.92GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. |
| [Llama-Song-Stream-3B-Instruct-Q3_K_XL.gguf](https://huggingface.co/bartowski/Llama-Song-Stream-3B-Instruct-GGUF/blob/main/Llama-Song-Stream-3B-Instruct-Q3_K_XL.gguf) | Q3_K_XL | 1.91GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. |
| [Llama-Song-Stream-3B-Instruct-IQ4_XS.gguf](https://huggingface.co/bartowski/Llama-Song-Stream-3B-Instruct-GGUF/blob/main/Llama-Song-Stream-3B-Instruct-IQ4_XS.gguf) | IQ4_XS | 1.83GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
| [Llama-Song-Stream-3B-Instruct-Q3_K_L.gguf](https://huggingface.co/bartowski/Llama-Song-Stream-3B-Instruct-GGUF/blob/main/Llama-Song-Stream-3B-Instruct-Q3_K_L.gguf) | Q3_K_L | 1.82GB | false | Lower quality but usable, good for low RAM availability. |
| [Llama-Song-Stream-3B-Instruct-Q3_K_M.gguf](https://huggingface.co/bartowski/Llama-Song-Stream-3B-Instruct-GGUF/blob/main/Llama-Song-Stream-3B-Instruct-Q3_K_M.gguf) | Q3_K_M | 1.69GB | false | Low quality. |
| [Llama-Song-Stream-3B-Instruct-IQ3_M.gguf](https://huggingface.co/bartowski/Llama-Song-Stream-3B-Instruct-GGUF/blob/main/Llama-Song-Stream-3B-Instruct-IQ3_M.gguf) | IQ3_M | 1.60GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
| [Llama-Song-Stream-3B-Instruct-Q3_K_S.gguf](https://huggingface.co/bartowski/Llama-Song-Stream-3B-Instruct-GGUF/blob/main/Llama-Song-Stream-3B-Instruct-Q3_K_S.gguf) | Q3_K_S | 1.54GB | false | Low quality, not recommended. |
| [Llama-Song-Stream-3B-Instruct-IQ3_XS.gguf](https://huggingface.co/bartowski/Llama-Song-Stream-3B-Instruct-GGUF/blob/main/Llama-Song-Stream-3B-Instruct-IQ3_XS.gguf) | IQ3_XS | 1.48GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
| [Llama-Song-Stream-3B-Instruct-Q2_K_L.gguf](https://huggingface.co/bartowski/Llama-Song-Stream-3B-Instruct-GGUF/blob/main/Llama-Song-Stream-3B-Instruct-Q2_K_L.gguf) | Q2_K_L | 1.46GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. |
| [Llama-Song-Stream-3B-Instruct-Q2_K.gguf](https://huggingface.co/bartowski/Llama-Song-Stream-3B-Instruct-GGUF/blob/main/Llama-Song-Stream-3B-Instruct-Q2_K.gguf) | Q2_K | 1.36GB | false | Very low quality but surprisingly usable. |
| [Llama-Song-Stream-3B-Instruct-IQ2_M.gguf](https://huggingface.co/bartowski/Llama-Song-Stream-3B-Instruct-GGUF/blob/main/Llama-Song-Stream-3B-Instruct-IQ2_M.gguf) | IQ2_M | 1.23GB | 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-Song-Stream-3B-Instruct-GGUF --include "Llama-Song-Stream-3B-Instruct-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-Song-Stream-3B-Instruct-GGUF --include "Llama-Song-Stream-3B-Instruct-Q8_0/*" --local-dir ./
```
You can either specify a new local-dir (Llama-Song-Stream-3B-Instruct-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}