bartowski/FINAL-Bench_Darwin-4B-Chimera-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/FINAL-Bench_Darwin-4B-Chimera-GGUF
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-07-22 16:00:09 +08:00
commit ad53530805
28 changed files with 337 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

73
.gitattributes vendored Normal file
View File

@@ -0,0 +1,73 @@
*.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
*.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
*.gguf* filter=lfs diff=lfs merge=lfs -text

3
FINAL-Bench_Darwin-4B-Chimera-IQ2_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1a3ab011b8fb08b1ae8adad10146d3927bf061805a25bf8706a23542a4f7f00b
size 1693904288

3
FINAL-Bench_Darwin-4B-Chimera-IQ3_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:763379e5916a3afc0b30f28d13d2dde45eda64fba8fb1ec9e2ab7c69692b2e1f
size 2048420768

3
FINAL-Bench_Darwin-4B-Chimera-IQ3_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:289f7600ab70ca3ba6b78defa7c9104fdde306557019f84ea3a4060cc8523aef
size 1910221728

3
FINAL-Bench_Darwin-4B-Chimera-IQ3_XXS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:db607fc54980b6699991d8455ee62a7cc88288e185a6dbb2234230534fd128a7
size 1782255008

3
FINAL-Bench_Darwin-4B-Chimera-IQ4_NL.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b84af9da95289f4e5cdc551894bff5d017b96bae62a92ae6ead6ff8997559830
size 2442537888

3
FINAL-Bench_Darwin-4B-Chimera-IQ4_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:655edd938446cbc46ea467ba02fa9da440e61e121b9c01918f12275801ee23b8
size 2337844128

3
FINAL-Bench_Darwin-4B-Chimera-Q2_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:bda9267e55a594dac2886b96ee6c10c4a58d56747e682bab8c92e78047959f61
size 1762397088

3
FINAL-Bench_Darwin-4B-Chimera-Q2_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:29f1f62f46cffa59fd043c1d08dc6af458756e77099349cc82e8960c77f49e86
size 1856597408

3
FINAL-Bench_Darwin-4B-Chimera-Q3_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:6b010326f4972b1a3dbd1b7e5560973d799f912d4c38fd1bad8da443b94bbaae
size 2266327968

3
FINAL-Bench_Darwin-4B-Chimera-Q3_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:084721a413e96ed2923fb189dd38a1ba2fcf107f30d20872b2f02dc1aeb7cf14
size 2154589088

3
FINAL-Bench_Darwin-4B-Chimera-Q3_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:423c6c5bc33d28c7504cecf1a7adea4fd454b805d88617f677ed43f26fad687b
size 1960725408

3
FINAL-Bench_Darwin-4B-Chimera-Q3_K_XL.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ee6b1d25612164e893d77ac85a943f19f69ecf634abaaebca8642eacf956a795
size 2360528288

3
FINAL-Bench_Darwin-4B-Chimera-Q4_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:43fda61bf338fe4e13534aaa1ca946b61697109e0fd3790c1940753ff12a4390
size 2424433568

3
FINAL-Bench_Darwin-4B-Chimera-Q4_1.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0b0cb55400ba8130c91a1378d192f0140ab8d619af61d7a326526d0b3ffbac71
size 2633493408

3
FINAL-Bench_Darwin-4B-Chimera-Q4_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:4486549837cd600df2475ab1fa8d68fa1470cfcef4261bad039f0562cfbbbf4e
size 2699124128

3
FINAL-Bench_Darwin-4B-Chimera-Q4_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:24ad4371b526999ed02cc2e279150ab4700c4c4c3d72fd554e24b40bb0755afb
size 2604923808

3
FINAL-Bench_Darwin-4B-Chimera-Q4_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f393044b348339cd639af3922cec3f5dc4849168dbd54d645d89150371a15bfc
size 2436557728

3
FINAL-Bench_Darwin-4B-Chimera-Q5_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:349b8a8cff7422777e32e490c1b28345668a655680ff933cdb56fd7d93fcd6c2
size 3071450528

3
FINAL-Bench_Darwin-4B-Chimera-Q5_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:cdbc753971ca83fad803b1b818c7fa584b44f946e6e487c259f9da73c6086958
size 2977250208

3
FINAL-Bench_Darwin-4B-Chimera-Q5_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1480a321ea3cc7e2ef8ef896be60a5ebc05b27d8da8024913cd363da422541fc
size 2848779168

3
FINAL-Bench_Darwin-4B-Chimera-Q6_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ed4bbd5d9006f10e0dcd49cbb124862b096e8d4a26b185bac663548f98c65cfc
size 3477679008

3
FINAL-Bench_Darwin-4B-Chimera-Q6_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1ef01f1d7482ebae00f40391506ef70fe710bfb1a4c37b00051e5d53a987a82d
size 3571879328

3
FINAL-Bench_Darwin-4B-Chimera-Q8_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a0e915ba790ea3593aea53ea56bc26ac92573a3eb0c7e91133427c2a787112a0
size 4280405408

3
FINAL-Bench_Darwin-4B-Chimera-bf16.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f302861b679303e5dd92eaffcbe852d812945f79e6b866156946a607e3bbc494
size 8051285120

3
FINAL-Bench_Darwin-4B-Chimera-imatrix.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1803a3dec59b30b7acf400d121d30bd73ad68638e9d9d3cd14bd846d5d7febd6
size 3872640

188
README.md Normal file
View File

@@ -0,0 +1,188 @@
---
quantized_by: bartowski
pipeline_tag: text-generation
tags:
- chimera
- darwin
- vidraft
- korean
- kmmlu
- reasoning
license: gemma
base_model: FINAL-Bench/Darwin-4B-Chimera
base_model_relation: quantized
language:
- ko
- en
---
## Llamacpp imatrix Quantizations of Darwin-4B-Chimera by FINAL-Bench
Using <a href="https://github.com/ggml-org/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggml-org/llama.cpp/releases/tag/b10068">b10068</a> for quantization.
Original model: https://huggingface.co/FINAL-Bench/Darwin-4B-Chimera
All quants made using imatrix option with dataset from [here](https://gist.github.com/bartowski1182/82ae9b520227f57d79ba04add13d0d0d)
Run them in your choice of tools:
- [llama.cpp](https://github.com/ggml-org/llama.cpp)
- [ramalama](https://github.com/containers/ramalama)
- [LM Studio](https://lmstudio.ai/)
- [koboldcpp](https://github.com/LostRuins/koboldcpp)
- [Jan AI](https://www.jan.ai/)
- [Text Generation Web UI](https://github.com/oobabooga/text-generation-webui)
- [LoLLMs](https://github.com/ParisNeo/lollms)
- [Atomic Chat](https://atomic.chat/)
Note: if it's a newly supported model, you may need to wait for an update from the developers.
## 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 |
| -------- | ---------- | --------- | ----- | ----------- |
| [FINAL-Bench_Darwin-4B-Chimera-bf16.gguf](https://huggingface.co/bartowski/FINAL-Bench_Darwin-4B-Chimera-GGUF/blob/main/FINAL-Bench_Darwin-4B-Chimera-bf16.gguf) | bf16 | 8.05GB | false | Full BF16 weights. |
| [FINAL-Bench_Darwin-4B-Chimera-Q8_0.gguf](https://huggingface.co/bartowski/FINAL-Bench_Darwin-4B-Chimera-GGUF/blob/main/FINAL-Bench_Darwin-4B-Chimera-Q8_0.gguf) | Q8_0 | 4.28GB | false | Extremely high quality, generally unneeded but max available quant. |
| [FINAL-Bench_Darwin-4B-Chimera-Q6_K_L.gguf](https://huggingface.co/bartowski/FINAL-Bench_Darwin-4B-Chimera-GGUF/blob/main/FINAL-Bench_Darwin-4B-Chimera-Q6_K_L.gguf) | Q6_K_L | 3.57GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. |
| [FINAL-Bench_Darwin-4B-Chimera-Q6_K.gguf](https://huggingface.co/bartowski/FINAL-Bench_Darwin-4B-Chimera-GGUF/blob/main/FINAL-Bench_Darwin-4B-Chimera-Q6_K.gguf) | Q6_K | 3.48GB | false | Very high quality, near perfect, *recommended*. |
| [FINAL-Bench_Darwin-4B-Chimera-Q5_K_L.gguf](https://huggingface.co/bartowski/FINAL-Bench_Darwin-4B-Chimera-GGUF/blob/main/FINAL-Bench_Darwin-4B-Chimera-Q5_K_L.gguf) | Q5_K_L | 3.07GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. |
| [FINAL-Bench_Darwin-4B-Chimera-Q5_K_M.gguf](https://huggingface.co/bartowski/FINAL-Bench_Darwin-4B-Chimera-GGUF/blob/main/FINAL-Bench_Darwin-4B-Chimera-Q5_K_M.gguf) | Q5_K_M | 2.98GB | false | High quality, *recommended*. |
| [FINAL-Bench_Darwin-4B-Chimera-Q5_K_S.gguf](https://huggingface.co/bartowski/FINAL-Bench_Darwin-4B-Chimera-GGUF/blob/main/FINAL-Bench_Darwin-4B-Chimera-Q5_K_S.gguf) | Q5_K_S | 2.85GB | false | High quality, *recommended*. |
| [FINAL-Bench_Darwin-4B-Chimera-Q4_K_L.gguf](https://huggingface.co/bartowski/FINAL-Bench_Darwin-4B-Chimera-GGUF/blob/main/FINAL-Bench_Darwin-4B-Chimera-Q4_K_L.gguf) | Q4_K_L | 2.70GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. |
| [FINAL-Bench_Darwin-4B-Chimera-Q4_1.gguf](https://huggingface.co/bartowski/FINAL-Bench_Darwin-4B-Chimera-GGUF/blob/main/FINAL-Bench_Darwin-4B-Chimera-Q4_1.gguf) | Q4_1 | 2.63GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. |
| [FINAL-Bench_Darwin-4B-Chimera-Q4_K_M.gguf](https://huggingface.co/bartowski/FINAL-Bench_Darwin-4B-Chimera-GGUF/blob/main/FINAL-Bench_Darwin-4B-Chimera-Q4_K_M.gguf) | Q4_K_M | 2.60GB | false | Good quality, default size for most use cases, *recommended*. |
| [FINAL-Bench_Darwin-4B-Chimera-IQ4_NL.gguf](https://huggingface.co/bartowski/FINAL-Bench_Darwin-4B-Chimera-GGUF/blob/main/FINAL-Bench_Darwin-4B-Chimera-IQ4_NL.gguf) | IQ4_NL | 2.44GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. |
| [FINAL-Bench_Darwin-4B-Chimera-Q4_K_S.gguf](https://huggingface.co/bartowski/FINAL-Bench_Darwin-4B-Chimera-GGUF/blob/main/FINAL-Bench_Darwin-4B-Chimera-Q4_K_S.gguf) | Q4_K_S | 2.44GB | false | Slightly lower quality with more space savings, *recommended*. |
| [FINAL-Bench_Darwin-4B-Chimera-Q4_0.gguf](https://huggingface.co/bartowski/FINAL-Bench_Darwin-4B-Chimera-GGUF/blob/main/FINAL-Bench_Darwin-4B-Chimera-Q4_0.gguf) | Q4_0 | 2.42GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. |
| [FINAL-Bench_Darwin-4B-Chimera-Q3_K_XL.gguf](https://huggingface.co/bartowski/FINAL-Bench_Darwin-4B-Chimera-GGUF/blob/main/FINAL-Bench_Darwin-4B-Chimera-Q3_K_XL.gguf) | Q3_K_XL | 2.36GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. |
| [FINAL-Bench_Darwin-4B-Chimera-IQ4_XS.gguf](https://huggingface.co/bartowski/FINAL-Bench_Darwin-4B-Chimera-GGUF/blob/main/FINAL-Bench_Darwin-4B-Chimera-IQ4_XS.gguf) | IQ4_XS | 2.34GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
| [FINAL-Bench_Darwin-4B-Chimera-Q3_K_L.gguf](https://huggingface.co/bartowski/FINAL-Bench_Darwin-4B-Chimera-GGUF/blob/main/FINAL-Bench_Darwin-4B-Chimera-Q3_K_L.gguf) | Q3_K_L | 2.27GB | false | Lower quality but usable, good for low RAM availability. |
| [FINAL-Bench_Darwin-4B-Chimera-Q3_K_M.gguf](https://huggingface.co/bartowski/FINAL-Bench_Darwin-4B-Chimera-GGUF/blob/main/FINAL-Bench_Darwin-4B-Chimera-Q3_K_M.gguf) | Q3_K_M | 2.15GB | false | Low quality. |
| [FINAL-Bench_Darwin-4B-Chimera-IQ3_M.gguf](https://huggingface.co/bartowski/FINAL-Bench_Darwin-4B-Chimera-GGUF/blob/main/FINAL-Bench_Darwin-4B-Chimera-IQ3_M.gguf) | IQ3_M | 2.05GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
| [FINAL-Bench_Darwin-4B-Chimera-Q3_K_S.gguf](https://huggingface.co/bartowski/FINAL-Bench_Darwin-4B-Chimera-GGUF/blob/main/FINAL-Bench_Darwin-4B-Chimera-Q3_K_S.gguf) | Q3_K_S | 1.96GB | false | Low quality, not recommended. |
| [FINAL-Bench_Darwin-4B-Chimera-IQ3_XS.gguf](https://huggingface.co/bartowski/FINAL-Bench_Darwin-4B-Chimera-GGUF/blob/main/FINAL-Bench_Darwin-4B-Chimera-IQ3_XS.gguf) | IQ3_XS | 1.91GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
| [FINAL-Bench_Darwin-4B-Chimera-Q2_K_L.gguf](https://huggingface.co/bartowski/FINAL-Bench_Darwin-4B-Chimera-GGUF/blob/main/FINAL-Bench_Darwin-4B-Chimera-Q2_K_L.gguf) | Q2_K_L | 1.86GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. |
| [FINAL-Bench_Darwin-4B-Chimera-IQ3_XXS.gguf](https://huggingface.co/bartowski/FINAL-Bench_Darwin-4B-Chimera-GGUF/blob/main/FINAL-Bench_Darwin-4B-Chimera-IQ3_XXS.gguf) | IQ3_XXS | 1.78GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. |
| [FINAL-Bench_Darwin-4B-Chimera-Q2_K.gguf](https://huggingface.co/bartowski/FINAL-Bench_Darwin-4B-Chimera-GGUF/blob/main/FINAL-Bench_Darwin-4B-Chimera-Q2_K.gguf) | Q2_K | 1.76GB | false | Very low quality but surprisingly usable. |
| [FINAL-Bench_Darwin-4B-Chimera-IQ2_M.gguf](https://huggingface.co/bartowski/FINAL-Bench_Darwin-4B-Chimera-GGUF/blob/main/FINAL-Bench_Darwin-4B-Chimera-IQ2_M.gguf) | IQ2_M | 1.69GB | 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 huggingface-cli installed:
```
pip install -U "huggingface_hub[cli]"
```
Then, you can target the specific file you want:
```
huggingface-cli download bartowski/FINAL-Bench_Darwin-4B-Chimera-GGUF --include "FINAL-Bench_Darwin-4B-Chimera-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/FINAL-Bench_Darwin-4B-Chimera-GGUF --include "FINAL-Bench_Darwin-4B-Chimera-Q8_0/*" --local-dir ./
```
You can either specify a new local-dir (FINAL-Bench_Darwin-4B-Chimera-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/ggml-org/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/ggml-org/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, you can use IQ4_NL thanks to [this PR](https://github.com/ggml-org/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 increase.
<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/ggml-org/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.
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}