bartowski/Impish_Mind_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/Impish_Mind_8B-GGUF
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-07-18 23:51:07 +08:00
commit 7d33e2c1a0
29 changed files with 312 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

61
.gitattributes vendored Normal file
View File

@@ -0,0 +1,61 @@
*.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
Impish_Mind_8B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
Impish_Mind_8B-Q6_K_L.gguf filter=lfs diff=lfs merge=lfs -text
Impish_Mind_8B-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
Impish_Mind_8B-Q5_K_L.gguf filter=lfs diff=lfs merge=lfs -text
Impish_Mind_8B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
Impish_Mind_8B-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
Impish_Mind_8B-Q4_K_L.gguf filter=lfs diff=lfs merge=lfs -text
Impish_Mind_8B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
Impish_Mind_8B-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
Impish_Mind_8B-Q4_0_8_8.gguf filter=lfs diff=lfs merge=lfs -text
Impish_Mind_8B-Q4_0_4_8.gguf filter=lfs diff=lfs merge=lfs -text
Impish_Mind_8B-Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text
Impish_Mind_8B-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
Impish_Mind_8B-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text
Impish_Mind_8B-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
Impish_Mind_8B-Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
Impish_Mind_8B-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
Impish_Mind_8B-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
Impish_Mind_8B-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
Impish_Mind_8B-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
Impish_Mind_8B-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
Impish_Mind_8B-Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text
Impish_Mind_8B-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
Impish_Mind_8B-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text
Impish_Mind_8B-f16.gguf filter=lfs diff=lfs merge=lfs -text
Impish_Mind_8B.imatrix filter=lfs diff=lfs merge=lfs -text

3
Impish_Mind_8B-IQ2_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:6321fb49d6c16c697e4f449ec9a9914f25efb25c0bc247dda2df038d212e52b6
size 2948299840

3
Impish_Mind_8B-IQ3_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:82999b454d283930dd06df589bdb5a66125af11b339df5a4c1ffaf65c025afd6
size 3784844480

3
Impish_Mind_8B-IQ3_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:790af4501735ba7991ad57ebb237b6cc8bc57c2e068b7cad11afe48660fe35db
size 3518768320

3
Impish_Mind_8B-IQ4_NL.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:7bbfafe9992d029d0f71b1df8a3b1055bb326f2fa861800919caf521165edf17
size 4678012224

3
Impish_Mind_8B-IQ4_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d3cb8e2d3c8d7af6aafac74cdd4720024a8007cc94cafe16bb5ffdce825cf437
size 4447685440

3
Impish_Mind_8B-Q2_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:51cfeda70b12f3c6e50c8d89006a295747243aa4277b1dd36f5741ea024c24d2
size 3179150912

3
Impish_Mind_8B-Q2_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:922e95e0f45e936406f7d49ddfbe09b11cf63066e0e48390426861705ba77b17
size 3692190912

3
Impish_Mind_8B-Q3_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f19ef8e014b66ca3d09d04a382c044913918f07450a8075af14060b66fc83fb0
size 4321977536

3
Impish_Mind_8B-Q3_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5575c407393f38535d5e762ee562d11c686b6fb7e016e14ce35883b091c9e3ab
size 4018939072

3
Impish_Mind_8B-Q3_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2b4669f4ebddae78b22ab2b735c51f26cd1cb8e7db286a388b97837c3d2cddf5
size 3664520384

3
Impish_Mind_8B-Q3_K_XL.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e6a8307bc8ae0eef410601d53ae1abf101ace145c54271a3ab5f11cde13d2104
size 4781661376

3
Impish_Mind_8B-Q4_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ba4b422c2dc4aef908342e6b554be5b7116d8329b07c29aa0a6728f556495ef8
size 4675915072

3
Impish_Mind_8B-Q4_0_4_4.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:8b73401c9b1b40fe2ec2f09ba18ad5dd71dd46296fa6f5ee7a229cc5441aa0d7
size 4661235008

3
Impish_Mind_8B-Q4_0_4_8.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:7ac7e1fd96e359797d3c1f0870d297037f9bf7b777875ebe547148d2aeb79bd6
size 4661235008

3
Impish_Mind_8B-Q4_0_8_8.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:160928ec5232428388d5460359316848b87e3af26f1aa5adf0de69c688c2882c
size 4661235008

3
Impish_Mind_8B-Q4_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5fcd5c1a27a0d600f975e67f426dbb756db2a83901192dc949e7def950a505a7
size 5310667968

3
Impish_Mind_8B-Q4_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:918f82bcb893c75fa2e846156df7bd3ce359464b960e32ae9171035ee14e7c51
size 4920757568

3
Impish_Mind_8B-Q4_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ce9a3f2f31602de6214b65c296361c0ce2fab8a6d7a53c77402d6fd09a98ee41
size 4692692288

3
Impish_Mind_8B-Q5_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:88a1688fad1a3556f54d0bed03a94cd4c0012329cc5e242b461d66d1623cbb5d
size 6057254080

3
Impish_Mind_8B-Q5_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2f49bd9a09d34df97f62bab7faa40bfc17dd0f10b595f8f896b2b9ee4c0fd500
size 5733012800

3
Impish_Mind_8B-Q5_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ef5a2614f8c6ac05b96d72a7db83314f29db62a9cd5d120ffc2a94b6d44a658c
size 5599319360

3
Impish_Mind_8B-Q6_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:7c9a1b692a49cec414cd90fd081fcd4bb7b52ed844e58dac3a537def3c747460
size 6596033984

3
Impish_Mind_8B-Q6_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d15ffd89b0d044f31c22664995417362563d09bcc669b480c3f2741ee0fb03ca
size 6850501824

3
Impish_Mind_8B-Q8_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:65bbb497a72c36ba171b77262bd1a636c7f2a850f5c99f7b369bee296df1e8bb
size 8540806336

3
Impish_Mind_8B-f16.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:da0257a4bdab32fdea1d65d86067dca740ab791ac79c8131ea72a64cd7ad8801
size 16068957088

3
Impish_Mind_8B.imatrix Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:28c99cd6e2c5391c5b45f5994d748f9b087641a0b22a742c45bfdd02118c7423
size 4988170

172
README.md Normal file
View File

@@ -0,0 +1,172 @@
---
quantized_by: bartowski
pipeline_tag: text-generation
base_model: SicariusSicariiStuff/Impish_Mind_8B
language:
- en
license: apache-2.0
---
## Llamacpp imatrix Quantizations of Impish_Mind_8B
Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b4273">b4273</a> for quantization.
Original model: https://huggingface.co/SicariusSicariiStuff/Impish_Mind_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 |
| -------- | ---------- | --------- | ----- | ----------- |
| [Impish_Mind_8B-f16.gguf](https://huggingface.co/bartowski/Impish_Mind_8B-GGUF/blob/main/Impish_Mind_8B-f16.gguf) | f16 | 16.07GB | false | Full F16 weights. |
| [Impish_Mind_8B-Q8_0.gguf](https://huggingface.co/bartowski/Impish_Mind_8B-GGUF/blob/main/Impish_Mind_8B-Q8_0.gguf) | Q8_0 | 8.54GB | false | Extremely high quality, generally unneeded but max available quant. |
| [Impish_Mind_8B-Q6_K_L.gguf](https://huggingface.co/bartowski/Impish_Mind_8B-GGUF/blob/main/Impish_Mind_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*. |
| [Impish_Mind_8B-Q6_K.gguf](https://huggingface.co/bartowski/Impish_Mind_8B-GGUF/blob/main/Impish_Mind_8B-Q6_K.gguf) | Q6_K | 6.60GB | false | Very high quality, near perfect, *recommended*. |
| [Impish_Mind_8B-Q5_K_L.gguf](https://huggingface.co/bartowski/Impish_Mind_8B-GGUF/blob/main/Impish_Mind_8B-Q5_K_L.gguf) | Q5_K_L | 6.06GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. |
| [Impish_Mind_8B-Q5_K_M.gguf](https://huggingface.co/bartowski/Impish_Mind_8B-GGUF/blob/main/Impish_Mind_8B-Q5_K_M.gguf) | Q5_K_M | 5.73GB | false | High quality, *recommended*. |
| [Impish_Mind_8B-Q5_K_S.gguf](https://huggingface.co/bartowski/Impish_Mind_8B-GGUF/blob/main/Impish_Mind_8B-Q5_K_S.gguf) | Q5_K_S | 5.60GB | false | High quality, *recommended*. |
| [Impish_Mind_8B-Q4_K_L.gguf](https://huggingface.co/bartowski/Impish_Mind_8B-GGUF/blob/main/Impish_Mind_8B-Q4_K_L.gguf) | Q4_K_L | 5.31GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. |
| [Impish_Mind_8B-Q4_K_M.gguf](https://huggingface.co/bartowski/Impish_Mind_8B-GGUF/blob/main/Impish_Mind_8B-Q4_K_M.gguf) | Q4_K_M | 4.92GB | false | Good quality, default size for most use cases, *recommended*. |
| [Impish_Mind_8B-Q3_K_XL.gguf](https://huggingface.co/bartowski/Impish_Mind_8B-GGUF/blob/main/Impish_Mind_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. |
| [Impish_Mind_8B-Q4_K_S.gguf](https://huggingface.co/bartowski/Impish_Mind_8B-GGUF/blob/main/Impish_Mind_8B-Q4_K_S.gguf) | Q4_K_S | 4.69GB | false | Slightly lower quality with more space savings, *recommended*. |
| [Impish_Mind_8B-Q4_0.gguf](https://huggingface.co/bartowski/Impish_Mind_8B-GGUF/blob/main/Impish_Mind_8B-Q4_0.gguf) | Q4_0 | 4.68GB | false | Legacy format, offers online repacking for ARM CPU inference. |
| [Impish_Mind_8B-IQ4_NL.gguf](https://huggingface.co/bartowski/Impish_Mind_8B-GGUF/blob/main/Impish_Mind_8B-IQ4_NL.gguf) | IQ4_NL | 4.68GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. |
| [Impish_Mind_8B-Q4_0_8_8.gguf](https://huggingface.co/bartowski/Impish_Mind_8B-GGUF/blob/main/Impish_Mind_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*. |
| [Impish_Mind_8B-Q4_0_4_8.gguf](https://huggingface.co/bartowski/Impish_Mind_8B-GGUF/blob/main/Impish_Mind_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*. |
| [Impish_Mind_8B-Q4_0_4_4.gguf](https://huggingface.co/bartowski/Impish_Mind_8B-GGUF/blob/main/Impish_Mind_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*. |
| [Impish_Mind_8B-IQ4_XS.gguf](https://huggingface.co/bartowski/Impish_Mind_8B-GGUF/blob/main/Impish_Mind_8B-IQ4_XS.gguf) | IQ4_XS | 4.45GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
| [Impish_Mind_8B-Q3_K_L.gguf](https://huggingface.co/bartowski/Impish_Mind_8B-GGUF/blob/main/Impish_Mind_8B-Q3_K_L.gguf) | Q3_K_L | 4.32GB | false | Lower quality but usable, good for low RAM availability. |
| [Impish_Mind_8B-Q3_K_M.gguf](https://huggingface.co/bartowski/Impish_Mind_8B-GGUF/blob/main/Impish_Mind_8B-Q3_K_M.gguf) | Q3_K_M | 4.02GB | false | Low quality. |
| [Impish_Mind_8B-IQ3_M.gguf](https://huggingface.co/bartowski/Impish_Mind_8B-GGUF/blob/main/Impish_Mind_8B-IQ3_M.gguf) | IQ3_M | 3.78GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
| [Impish_Mind_8B-Q2_K_L.gguf](https://huggingface.co/bartowski/Impish_Mind_8B-GGUF/blob/main/Impish_Mind_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. |
| [Impish_Mind_8B-Q3_K_S.gguf](https://huggingface.co/bartowski/Impish_Mind_8B-GGUF/blob/main/Impish_Mind_8B-Q3_K_S.gguf) | Q3_K_S | 3.66GB | false | Low quality, not recommended. |
| [Impish_Mind_8B-IQ3_XS.gguf](https://huggingface.co/bartowski/Impish_Mind_8B-GGUF/blob/main/Impish_Mind_8B-IQ3_XS.gguf) | IQ3_XS | 3.52GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
| [Impish_Mind_8B-Q2_K.gguf](https://huggingface.co/bartowski/Impish_Mind_8B-GGUF/blob/main/Impish_Mind_8B-Q2_K.gguf) | Q2_K | 3.18GB | false | Very low quality but surprisingly usable. |
| [Impish_Mind_8B-IQ2_M.gguf](https://huggingface.co/bartowski/Impish_Mind_8B-GGUF/blob/main/Impish_Mind_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/Impish_Mind_8B-GGUF --include "Impish_Mind_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/Impish_Mind_8B-GGUF --include "Impish_Mind_8B-Q8_0/*" --local-dir ./
```
You can either specify a new local-dir (Impish_Mind_8B-Q8_0) or download them all in place (./)
</details>
## Q4_0_X_X information
New: Thanks to efforts made to have online repacking of weights in [this PR](https://github.com/ggerganov/llama.cpp/pull/9921), you can now just use Q4_0 if your llama.cpp has been compiled for your ARM device.
Similarly, if you want to get slightly better performance, 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</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}