bartowski/FutureMa_Eva-4B-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/FutureMa_Eva-4B-GGUF
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-08-13 08:49:12 +08:00
commit b0a03c7df1
28 changed files with 339 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
FutureMa_Eva-4B-bf16.gguf filter=lfs diff=lfs merge=lfs -text
FutureMa_Eva-4B-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
FutureMa_Eva-4B-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
FutureMa_Eva-4B-Q6_K_L.gguf filter=lfs diff=lfs merge=lfs -text
FutureMa_Eva-4B-Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text
FutureMa_Eva-4B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
FutureMa_Eva-4B-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
FutureMa_Eva-4B-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text
FutureMa_Eva-4B-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
FutureMa_Eva-4B-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
FutureMa_Eva-4B-imatrix.gguf filter=lfs diff=lfs merge=lfs -text
FutureMa_Eva-4B-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
FutureMa_Eva-4B-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text
FutureMa_Eva-4B-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text
FutureMa_Eva-4B-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
FutureMa_Eva-4B-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text
FutureMa_Eva-4B-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
FutureMa_Eva-4B-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
FutureMa_Eva-4B-Q5_K_L.gguf filter=lfs diff=lfs merge=lfs -text
FutureMa_Eva-4B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
FutureMa_Eva-4B-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
FutureMa_Eva-4B-Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
FutureMa_Eva-4B-Q4_K_L.gguf filter=lfs diff=lfs merge=lfs -text
FutureMa_Eva-4B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
FutureMa_Eva-4B-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text

3
FutureMa_Eva-4B-IQ2_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e8aceb00bcfd44a8f1496a2f2e19e045e5115e73e8a8279df190fb7550585b0f
size 1512982688

3
FutureMa_Eva-4B-IQ3_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2a4338bf5799d1a5e1eff594cb0915bec56c34dbb2b75fec5bf905125690a256
size 1962895008

3
FutureMa_Eva-4B-IQ3_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:112eba5e57067c57765e153e0666a550da5e485e51648a2b7ffe18757f2e8182
size 1814374048

3
FutureMa_Eva-4B-IQ3_XXS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c47187add7f3407d9f0a5fbf0eef6e9fa7dca4d5947af4baeaea1d48faced389
size 1670187168

3
FutureMa_Eva-4B-IQ4_NL.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:4ca8e8769e1f1b114d6bb0a7de83ff3c30f8cdec1cb415b18e36b4d07100e1d3
size 2381342368

3
FutureMa_Eva-4B-IQ4_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:6b8b79439912de51bd3a0035615232f71025f7e066a02374909681d386d20fc7
size 2270750368

3
FutureMa_Eva-4B-Q2_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:677b0dcfedff4450113614bad5c647a2e5e74d11b8625bfea993da41a5d23963
size 1669498528

3
FutureMa_Eva-4B-Q2_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:22d0a1fab5008f8354e807f2062c6f5ec4808070e8bdb1c3d7865ae8393d9533
size 1763698848

3
FutureMa_Eva-4B-Q3_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c9a1efbbc7bfadf9984bdacd3d0f1b85cbf9b5cdcc8031692642c16b057fe3d6
size 2239784608

3
FutureMa_Eva-4B-Q3_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ab7a1809335068285b13bf7d70b52a5ef8adf21797523b64a9d32d430f78ad7f
size 2075616928

3
FutureMa_Eva-4B-Q3_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c6299cdf70750b419938b4f0eeb3b317604b66d05ba02ea4e619e69048dbb59b
size 1886996128

3
FutureMa_Eva-4B-Q3_K_XL.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:104c8bf24d4b517c9916fe182e940f3c40a077e1c61e547440e146305c2ce459
size 2333984928

3
FutureMa_Eva-4B-Q4_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:74b9431cc6e249de64286feebd57779c5226670323e8b6e46b339484403e6c9c
size 2375771808

3
FutureMa_Eva-4B-Q4_1.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2ef57c36e4b6ba6548b40491f067e713f835361cf4c967632cc5d7dfa89876f6
size 2596628128

3
FutureMa_Eva-4B-Q4_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:422cceaad788aa25bc636df651c1ed9971444836fe21229f8d3cf86a8c6fb0fb
size 2591479968

3
FutureMa_Eva-4B-Q4_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:db5ba57f303a399c8807341cdeb8eb0361282e3714a3f1c5639aef0d9457d601
size 2497279648

3
FutureMa_Eva-4B-Q4_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1d5cd64304957b9b9a0becdf7c793e5ceff938a0721f00bbe322f2e70d99d0e7
size 2383308448

3
FutureMa_Eva-4B-Q5_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5b76ac32bdd7c0e55449e97bb8bf6b8b6cd2670f94be84cf7e64407081eee23a
size 2983712928

3
FutureMa_Eva-4B-Q5_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:467a39ab9b05f957c5e476b750b6b633235a093f1513eda3d6898c1dd9f7514a
size 2889512608

3
FutureMa_Eva-4B-Q5_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:54b5f33339a1f00461d34b13dd7184947a85a1de11a97fe05dfd9ced3d76b20b
size 2823710368

3
FutureMa_Eva-4B-Q6_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:abe088bfbc408ce781fb40e175c288202bc6cf76ffba829aeddb1fb3ff0c6bf9
size 3306260128

3
FutureMa_Eva-4B-Q6_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e133b2519810e877774d904086c37dbbcd52ce0340f5c75d73a20dc7fcfc522f
size 3400460448

3
FutureMa_Eva-4B-Q8_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:cf99354cc59572c0c4066a0e2a9f8b276651f80e1a198f014cb32a88b4f6c5d8
size 4280404128

3
FutureMa_Eva-4B-bf16.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c952578afc5b1325f15c33751191b64ccf090e4838de31fa106993224f9e38aa
size 8051283872

3
FutureMa_Eva-4B-imatrix.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d05e007862800d5969353396ce4a62ee6c1630b5a6e6506b26a19e391a5f17f5
size 3872640

190
README.md Normal file
View File

@@ -0,0 +1,190 @@
---
quantized_by: bartowski
pipeline_tag: text-generation
tags:
- finance
- earnings-calls
- financial-nlp
- text-classification
- qwen3
- llm-as-judge
- distillation
base_model_relation: quantized
base_model: FutureMa/Eva-4B
license: apache-2.0
language:
- en
spaces:
- FutureMa/financial-evasion-detection
---
## Llamacpp imatrix Quantizations of Eva-4B by FutureMa
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/b7703">b7703</a> for quantization.
Original model: https://huggingface.co/FutureMa/Eva-4B
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)
- [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)
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 |
| -------- | ---------- | --------- | ----- | ----------- |
| [Eva-4B-bf16.gguf](https://huggingface.co/bartowski/FutureMa_Eva-4B-GGUF/blob/main/FutureMa_Eva-4B-bf16.gguf) | bf16 | 8.05GB | false | Full BF16 weights. |
| [Eva-4B-Q8_0.gguf](https://huggingface.co/bartowski/FutureMa_Eva-4B-GGUF/blob/main/FutureMa_Eva-4B-Q8_0.gguf) | Q8_0 | 4.28GB | false | Extremely high quality, generally unneeded but max available quant. |
| [Eva-4B-Q6_K_L.gguf](https://huggingface.co/bartowski/FutureMa_Eva-4B-GGUF/blob/main/FutureMa_Eva-4B-Q6_K_L.gguf) | Q6_K_L | 3.40GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. |
| [Eva-4B-Q6_K.gguf](https://huggingface.co/bartowski/FutureMa_Eva-4B-GGUF/blob/main/FutureMa_Eva-4B-Q6_K.gguf) | Q6_K | 3.31GB | false | Very high quality, near perfect, *recommended*. |
| [Eva-4B-Q5_K_L.gguf](https://huggingface.co/bartowski/FutureMa_Eva-4B-GGUF/blob/main/FutureMa_Eva-4B-Q5_K_L.gguf) | Q5_K_L | 2.98GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. |
| [Eva-4B-Q5_K_M.gguf](https://huggingface.co/bartowski/FutureMa_Eva-4B-GGUF/blob/main/FutureMa_Eva-4B-Q5_K_M.gguf) | Q5_K_M | 2.89GB | false | High quality, *recommended*. |
| [Eva-4B-Q5_K_S.gguf](https://huggingface.co/bartowski/FutureMa_Eva-4B-GGUF/blob/main/FutureMa_Eva-4B-Q5_K_S.gguf) | Q5_K_S | 2.82GB | false | High quality, *recommended*. |
| [Eva-4B-Q4_1.gguf](https://huggingface.co/bartowski/FutureMa_Eva-4B-GGUF/blob/main/FutureMa_Eva-4B-Q4_1.gguf) | Q4_1 | 2.60GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. |
| [Eva-4B-Q4_K_L.gguf](https://huggingface.co/bartowski/FutureMa_Eva-4B-GGUF/blob/main/FutureMa_Eva-4B-Q4_K_L.gguf) | Q4_K_L | 2.59GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. |
| [Eva-4B-Q4_K_M.gguf](https://huggingface.co/bartowski/FutureMa_Eva-4B-GGUF/blob/main/FutureMa_Eva-4B-Q4_K_M.gguf) | Q4_K_M | 2.50GB | false | Good quality, default size for most use cases, *recommended*. |
| [Eva-4B-Q4_K_S.gguf](https://huggingface.co/bartowski/FutureMa_Eva-4B-GGUF/blob/main/FutureMa_Eva-4B-Q4_K_S.gguf) | Q4_K_S | 2.38GB | false | Slightly lower quality with more space savings, *recommended*. |
| [Eva-4B-Q4_0.gguf](https://huggingface.co/bartowski/FutureMa_Eva-4B-GGUF/blob/main/FutureMa_Eva-4B-Q4_0.gguf) | Q4_0 | 2.38GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. |
| [Eva-4B-IQ4_NL.gguf](https://huggingface.co/bartowski/FutureMa_Eva-4B-GGUF/blob/main/FutureMa_Eva-4B-IQ4_NL.gguf) | IQ4_NL | 2.38GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. |
| [Eva-4B-Q3_K_XL.gguf](https://huggingface.co/bartowski/FutureMa_Eva-4B-GGUF/blob/main/FutureMa_Eva-4B-Q3_K_XL.gguf) | Q3_K_XL | 2.33GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. |
| [Eva-4B-IQ4_XS.gguf](https://huggingface.co/bartowski/FutureMa_Eva-4B-GGUF/blob/main/FutureMa_Eva-4B-IQ4_XS.gguf) | IQ4_XS | 2.27GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
| [Eva-4B-Q3_K_L.gguf](https://huggingface.co/bartowski/FutureMa_Eva-4B-GGUF/blob/main/FutureMa_Eva-4B-Q3_K_L.gguf) | Q3_K_L | 2.24GB | false | Lower quality but usable, good for low RAM availability. |
| [Eva-4B-Q3_K_M.gguf](https://huggingface.co/bartowski/FutureMa_Eva-4B-GGUF/blob/main/FutureMa_Eva-4B-Q3_K_M.gguf) | Q3_K_M | 2.08GB | false | Low quality. |
| [Eva-4B-IQ3_M.gguf](https://huggingface.co/bartowski/FutureMa_Eva-4B-GGUF/blob/main/FutureMa_Eva-4B-IQ3_M.gguf) | IQ3_M | 1.96GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
| [Eva-4B-Q3_K_S.gguf](https://huggingface.co/bartowski/FutureMa_Eva-4B-GGUF/blob/main/FutureMa_Eva-4B-Q3_K_S.gguf) | Q3_K_S | 1.89GB | false | Low quality, not recommended. |
| [Eva-4B-IQ3_XS.gguf](https://huggingface.co/bartowski/FutureMa_Eva-4B-GGUF/blob/main/FutureMa_Eva-4B-IQ3_XS.gguf) | IQ3_XS | 1.81GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
| [Eva-4B-Q2_K_L.gguf](https://huggingface.co/bartowski/FutureMa_Eva-4B-GGUF/blob/main/FutureMa_Eva-4B-Q2_K_L.gguf) | Q2_K_L | 1.76GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. |
| [Eva-4B-IQ3_XXS.gguf](https://huggingface.co/bartowski/FutureMa_Eva-4B-GGUF/blob/main/FutureMa_Eva-4B-IQ3_XXS.gguf) | IQ3_XXS | 1.67GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. |
| [Eva-4B-Q2_K.gguf](https://huggingface.co/bartowski/FutureMa_Eva-4B-GGUF/blob/main/FutureMa_Eva-4B-Q2_K.gguf) | Q2_K | 1.67GB | false | Very low quality but surprisingly usable. |
| [Eva-4B-IQ2_M.gguf](https://huggingface.co/bartowski/FutureMa_Eva-4B-GGUF/blob/main/FutureMa_Eva-4B-IQ2_M.gguf) | IQ2_M | 1.51GB | 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/FutureMa_Eva-4B-GGUF --include "FutureMa_Eva-4B-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/FutureMa_Eva-4B-GGUF --include "FutureMa_Eva-4B-Q8_0/*" --local-dir ./
```
You can either specify a new local-dir (FutureMa_Eva-4B-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 for , 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 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/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.
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}