初始化项目，由ModelHub XC社区提供模型
Model: bartowski/lemon07r_VellumMini-0.1-Qwen3-14B-GGUF Source: Original Platform
This commit is contained in:
ModelHub XC
74
.gitattributes
vendored
Normal file
74
.gitattributes
vendored
Normal file
@@ -0,0 +1,74 @@
|
||||
*.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
|
||||
|
||||
lemon07r_VellumMini-0.1-Qwen3-14B-Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
lemon07r_VellumMini-0.1-Qwen3-14B-Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
lemon07r_VellumMini-0.1-Qwen3-14B-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
lemon07r_VellumMini-0.1-Qwen3-14B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
lemon07r_VellumMini-0.1-Qwen3-14B-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
lemon07r_VellumMini-0.1-Qwen3-14B-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
lemon07r_VellumMini-0.1-Qwen3-14B-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
lemon07r_VellumMini-0.1-Qwen3-14B-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
lemon07r_VellumMini-0.1-Qwen3-14B-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
lemon07r_VellumMini-0.1-Qwen3-14B-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
lemon07r_VellumMini-0.1-Qwen3-14B-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
lemon07r_VellumMini-0.1-Qwen3-14B-bf16.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
lemon07r_VellumMini-0.1-Qwen3-14B-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
lemon07r_VellumMini-0.1-Qwen3-14B-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
lemon07r_VellumMini-0.1-Qwen3-14B-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
lemon07r_VellumMini-0.1-Qwen3-14B-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
lemon07r_VellumMini-0.1-Qwen3-14B-Q6_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
lemon07r_VellumMini-0.1-Qwen3-14B-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
lemon07r_VellumMini-0.1-Qwen3-14B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
lemon07r_VellumMini-0.1-Qwen3-14B-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
lemon07r_VellumMini-0.1-Qwen3-14B-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
lemon07r_VellumMini-0.1-Qwen3-14B-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
lemon07r_VellumMini-0.1-Qwen3-14B-Q4_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
lemon07r_VellumMini-0.1-Qwen3-14B-Q5_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
lemon07r_VellumMini-0.1-Qwen3-14B-imatrix.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
lemon07r_VellumMini-0.1-Qwen3-14B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
165
README.md
Normal file
165
README.md
Normal file
@@ -0,0 +1,165 @@
|
||||
---
|
||||
quantized_by: bartowski
|
||||
pipeline_tag: text-generation
|
||||
base_model_relation: quantized
|
||||
base_model: lemon07r/VellumMini-0.1-Qwen3-14B
|
||||
---
|
||||
|
||||
## Llamacpp imatrix Quantizations of VellumMini-0.1-Qwen3-14B by lemon07r
|
||||
|
||||
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/b6683">b6683</a> for quantization.
|
||||
|
||||
Original model: https://huggingface.co/lemon07r/VellumMini-0.1-Qwen3-14B
|
||||
|
||||
All quants made using imatrix option with dataset from [here](https://gist.github.com/bartowski1182/eb213dccb3571f863da82e99418f81e8) combined with a subset of combined_all_small.parquet from Ed Addario [here](https://huggingface.co/datasets/eaddario/imatrix-calibration/blob/main/combined_all_small.parquet)
|
||||
|
||||
Run them in [LM Studio](https://lmstudio.ai/)
|
||||
|
||||
Run them directly with [llama.cpp](https://github.com/ggml-org/llama.cpp), or any other llama.cpp based project
|
||||
|
||||
## Prompt format
|
||||
|
||||
No prompt format found, check original model page
|
||||
|
||||
## Download a file (not the whole branch) from below:
|
||||
|
||||
| Filename | Quant type | File Size | Split | Description |
|
||||
| -------- | ---------- | --------- | ----- | ----------- |
|
||||
| [VellumMini-0.1-Qwen3-14B-bf16.gguf](https://huggingface.co/bartowski/lemon07r_VellumMini-0.1-Qwen3-14B-GGUF/blob/main/lemon07r_VellumMini-0.1-Qwen3-14B-bf16.gguf) | bf16 | 29.54GB | false | Full BF16 weights. |
|
||||
| [VellumMini-0.1-Qwen3-14B-Q8_0.gguf](https://huggingface.co/bartowski/lemon07r_VellumMini-0.1-Qwen3-14B-GGUF/blob/main/lemon07r_VellumMini-0.1-Qwen3-14B-Q8_0.gguf) | Q8_0 | 15.70GB | false | Extremely high quality, generally unneeded but max available quant. |
|
||||
| [VellumMini-0.1-Qwen3-14B-Q6_K_L.gguf](https://huggingface.co/bartowski/lemon07r_VellumMini-0.1-Qwen3-14B-GGUF/blob/main/lemon07r_VellumMini-0.1-Qwen3-14B-Q6_K_L.gguf) | Q6_K_L | 12.50GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. |
|
||||
| [VellumMini-0.1-Qwen3-14B-Q6_K.gguf](https://huggingface.co/bartowski/lemon07r_VellumMini-0.1-Qwen3-14B-GGUF/blob/main/lemon07r_VellumMini-0.1-Qwen3-14B-Q6_K.gguf) | Q6_K | 12.12GB | false | Very high quality, near perfect, *recommended*. |
|
||||
| [VellumMini-0.1-Qwen3-14B-Q5_K_L.gguf](https://huggingface.co/bartowski/lemon07r_VellumMini-0.1-Qwen3-14B-GGUF/blob/main/lemon07r_VellumMini-0.1-Qwen3-14B-Q5_K_L.gguf) | Q5_K_L | 10.99GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. |
|
||||
| [VellumMini-0.1-Qwen3-14B-Q5_K_M.gguf](https://huggingface.co/bartowski/lemon07r_VellumMini-0.1-Qwen3-14B-GGUF/blob/main/lemon07r_VellumMini-0.1-Qwen3-14B-Q5_K_M.gguf) | Q5_K_M | 10.51GB | false | High quality, *recommended*. |
|
||||
| [VellumMini-0.1-Qwen3-14B-Q5_K_S.gguf](https://huggingface.co/bartowski/lemon07r_VellumMini-0.1-Qwen3-14B-GGUF/blob/main/lemon07r_VellumMini-0.1-Qwen3-14B-Q5_K_S.gguf) | Q5_K_S | 10.26GB | false | High quality, *recommended*. |
|
||||
| [VellumMini-0.1-Qwen3-14B-Q4_K_L.gguf](https://huggingface.co/bartowski/lemon07r_VellumMini-0.1-Qwen3-14B-GGUF/blob/main/lemon07r_VellumMini-0.1-Qwen3-14B-Q4_K_L.gguf) | Q4_K_L | 9.58GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. |
|
||||
| [VellumMini-0.1-Qwen3-14B-Q4_1.gguf](https://huggingface.co/bartowski/lemon07r_VellumMini-0.1-Qwen3-14B-GGUF/blob/main/lemon07r_VellumMini-0.1-Qwen3-14B-Q4_1.gguf) | Q4_1 | 9.39GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. |
|
||||
| [VellumMini-0.1-Qwen3-14B-Q4_K_M.gguf](https://huggingface.co/bartowski/lemon07r_VellumMini-0.1-Qwen3-14B-GGUF/blob/main/lemon07r_VellumMini-0.1-Qwen3-14B-Q4_K_M.gguf) | Q4_K_M | 9.00GB | false | Good quality, default size for most use cases, *recommended*. |
|
||||
| [VellumMini-0.1-Qwen3-14B-Q3_K_XL.gguf](https://huggingface.co/bartowski/lemon07r_VellumMini-0.1-Qwen3-14B-GGUF/blob/main/lemon07r_VellumMini-0.1-Qwen3-14B-Q3_K_XL.gguf) | Q3_K_XL | 8.58GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. |
|
||||
| [VellumMini-0.1-Qwen3-14B-Q4_K_S.gguf](https://huggingface.co/bartowski/lemon07r_VellumMini-0.1-Qwen3-14B-GGUF/blob/main/lemon07r_VellumMini-0.1-Qwen3-14B-Q4_K_S.gguf) | Q4_K_S | 8.57GB | false | Slightly lower quality with more space savings, *recommended*. |
|
||||
| [VellumMini-0.1-Qwen3-14B-Q4_0.gguf](https://huggingface.co/bartowski/lemon07r_VellumMini-0.1-Qwen3-14B-GGUF/blob/main/lemon07r_VellumMini-0.1-Qwen3-14B-Q4_0.gguf) | Q4_0 | 8.54GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. |
|
||||
| [VellumMini-0.1-Qwen3-14B-IQ4_NL.gguf](https://huggingface.co/bartowski/lemon07r_VellumMini-0.1-Qwen3-14B-GGUF/blob/main/lemon07r_VellumMini-0.1-Qwen3-14B-IQ4_NL.gguf) | IQ4_NL | 8.54GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. |
|
||||
| [VellumMini-0.1-Qwen3-14B-IQ4_XS.gguf](https://huggingface.co/bartowski/lemon07r_VellumMini-0.1-Qwen3-14B-GGUF/blob/main/lemon07r_VellumMini-0.1-Qwen3-14B-IQ4_XS.gguf) | IQ4_XS | 8.11GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
|
||||
| [VellumMini-0.1-Qwen3-14B-Q3_K_L.gguf](https://huggingface.co/bartowski/lemon07r_VellumMini-0.1-Qwen3-14B-GGUF/blob/main/lemon07r_VellumMini-0.1-Qwen3-14B-Q3_K_L.gguf) | Q3_K_L | 7.90GB | false | Lower quality but usable, good for low RAM availability. |
|
||||
| [VellumMini-0.1-Qwen3-14B-Q3_K_M.gguf](https://huggingface.co/bartowski/lemon07r_VellumMini-0.1-Qwen3-14B-GGUF/blob/main/lemon07r_VellumMini-0.1-Qwen3-14B-Q3_K_M.gguf) | Q3_K_M | 7.32GB | false | Low quality. |
|
||||
| [VellumMini-0.1-Qwen3-14B-IQ3_M.gguf](https://huggingface.co/bartowski/lemon07r_VellumMini-0.1-Qwen3-14B-GGUF/blob/main/lemon07r_VellumMini-0.1-Qwen3-14B-IQ3_M.gguf) | IQ3_M | 6.88GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
|
||||
| [VellumMini-0.1-Qwen3-14B-Q3_K_S.gguf](https://huggingface.co/bartowski/lemon07r_VellumMini-0.1-Qwen3-14B-GGUF/blob/main/lemon07r_VellumMini-0.1-Qwen3-14B-Q3_K_S.gguf) | Q3_K_S | 6.66GB | false | Low quality, not recommended. |
|
||||
| [VellumMini-0.1-Qwen3-14B-Q2_K_L.gguf](https://huggingface.co/bartowski/lemon07r_VellumMini-0.1-Qwen3-14B-GGUF/blob/main/lemon07r_VellumMini-0.1-Qwen3-14B-Q2_K_L.gguf) | Q2_K_L | 6.51GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. |
|
||||
| [VellumMini-0.1-Qwen3-14B-IQ3_XS.gguf](https://huggingface.co/bartowski/lemon07r_VellumMini-0.1-Qwen3-14B-GGUF/blob/main/lemon07r_VellumMini-0.1-Qwen3-14B-IQ3_XS.gguf) | IQ3_XS | 6.38GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
|
||||
| [VellumMini-0.1-Qwen3-14B-IQ3_XXS.gguf](https://huggingface.co/bartowski/lemon07r_VellumMini-0.1-Qwen3-14B-GGUF/blob/main/lemon07r_VellumMini-0.1-Qwen3-14B-IQ3_XXS.gguf) | IQ3_XXS | 5.94GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. |
|
||||
| [VellumMini-0.1-Qwen3-14B-Q2_K.gguf](https://huggingface.co/bartowski/lemon07r_VellumMini-0.1-Qwen3-14B-GGUF/blob/main/lemon07r_VellumMini-0.1-Qwen3-14B-Q2_K.gguf) | Q2_K | 5.75GB | false | Very low quality but surprisingly usable. |
|
||||
| [VellumMini-0.1-Qwen3-14B-IQ2_M.gguf](https://huggingface.co/bartowski/lemon07r_VellumMini-0.1-Qwen3-14B-GGUF/blob/main/lemon07r_VellumMini-0.1-Qwen3-14B-IQ2_M.gguf) | IQ2_M | 5.32GB | false | Relatively low quality, uses SOTA techniques to be surprisingly usable. |
|
||||
| [VellumMini-0.1-Qwen3-14B-IQ2_S.gguf](https://huggingface.co/bartowski/lemon07r_VellumMini-0.1-Qwen3-14B-GGUF/blob/main/lemon07r_VellumMini-0.1-Qwen3-14B-IQ2_S.gguf) | IQ2_S | 4.96GB | false | Low quality, uses SOTA techniques to be 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/lemon07r_VellumMini-0.1-Qwen3-14B-GGUF --include "lemon07r_VellumMini-0.1-Qwen3-14B-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/lemon07r_VellumMini-0.1-Qwen3-14B-GGUF --include "lemon07r_VellumMini-0.1-Qwen3-14B-Q8_0/*" --local-dir ./
|
||||
```
|
||||
|
||||
You can either specify a new local-dir (lemon07r_VellumMini-0.1-Qwen3-14B-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
1
configuration.json
Normal file
@@ -0,0 +1 @@
|
||||
{"framework": "pytorch", "task": "text-generation", "allow_remote": true}
|
||||
3
lemon07r_VellumMini-0.1-Qwen3-14B-IQ2_M.gguf
Normal file
3
lemon07r_VellumMini-0.1-Qwen3-14B-IQ2_M.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:9e77254921cd28cc6b7f97d2dc911cdb4099ce40276d621a57c08d6956b8d7da
|
||||
size 5322941568
|
||||
3
lemon07r_VellumMini-0.1-Qwen3-14B-IQ2_S.gguf
Normal file
3
lemon07r_VellumMini-0.1-Qwen3-14B-IQ2_S.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:b36580a9748aaf86ee267135ee1c92db1de6c93d7d5fb977769e2be2661b04b7
|
||||
size 4963312768
|
||||
3
lemon07r_VellumMini-0.1-Qwen3-14B-IQ3_M.gguf
Normal file
3
lemon07r_VellumMini-0.1-Qwen3-14B-IQ3_M.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:c861703386165acdc5a6e836e37c8de58907288fa5b0566749df425570b68701
|
||||
size 6883410048
|
||||
3
lemon07r_VellumMini-0.1-Qwen3-14B-IQ3_XS.gguf
Normal file
3
lemon07r_VellumMini-0.1-Qwen3-14B-IQ3_XS.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:e3596f0794fb47a2a9d1347c721b4f87852d839022b26a200da4040ec2584d36
|
||||
size 6375301248
|
||||
3
lemon07r_VellumMini-0.1-Qwen3-14B-IQ3_XXS.gguf
Normal file
3
lemon07r_VellumMini-0.1-Qwen3-14B-IQ3_XXS.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:c7ef5a0997372dfe9c744877536a5807ce7cbc168f4713a066079ff0f25b27b1
|
||||
size 5942666368
|
||||
3
lemon07r_VellumMini-0.1-Qwen3-14B-IQ4_NL.gguf
Normal file
3
lemon07r_VellumMini-0.1-Qwen3-14B-IQ4_NL.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:b9e2fcefe0a6d2cdbc1337c2890ae17112ed3c3513e005f0fce749907facd08e
|
||||
size 8541363328
|
||||
3
lemon07r_VellumMini-0.1-Qwen3-14B-IQ4_XS.gguf
Normal file
3
lemon07r_VellumMini-0.1-Qwen3-14B-IQ4_XS.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:862d2611e71da538c44978b8f851533442bd82a90dd83292c1c33ef8e546772f
|
||||
size 8110730368
|
||||
3
lemon07r_VellumMini-0.1-Qwen3-14B-Q2_K.gguf
Normal file
3
lemon07r_VellumMini-0.1-Qwen3-14B-Q2_K.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:0b3880e9d2fc88a7fce38d97b4f28c148730e0467666fe722c602089645c9f96
|
||||
size 5753984128
|
||||
3
lemon07r_VellumMini-0.1-Qwen3-14B-Q2_K_L.gguf
Normal file
3
lemon07r_VellumMini-0.1-Qwen3-14B-Q2_K_L.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:d2c53635f6443c2e2dd46b1375dc0b06bc0e0f18c9baaf0317fa5b5483f28324
|
||||
size 6513664128
|
||||
3
lemon07r_VellumMini-0.1-Qwen3-14B-Q3_K_L.gguf
Normal file
3
lemon07r_VellumMini-0.1-Qwen3-14B-Q3_K_L.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:b1bfdd6f4e45459b8b0c386e5d55e897984895ba5be100aea07ea8437740d93f
|
||||
size 7900651648
|
||||
3
lemon07r_VellumMini-0.1-Qwen3-14B-Q3_K_M.gguf
Normal file
3
lemon07r_VellumMini-0.1-Qwen3-14B-Q3_K_M.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:b52d391010144e19e359140fe2cfdb546b83fe29aa5001baeb1dc8c56a716c19
|
||||
size 7321313408
|
||||
3
lemon07r_VellumMini-0.1-Qwen3-14B-Q3_K_S.gguf
Normal file
3
lemon07r_VellumMini-0.1-Qwen3-14B-Q3_K_S.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:55a7aa9ac5edf3a0e8d35a29d7e792497e07de97bb769057d4c601ed8e7de9c0
|
||||
size 6657106048
|
||||
3
lemon07r_VellumMini-0.1-Qwen3-14B-Q3_K_XL.gguf
Normal file
3
lemon07r_VellumMini-0.1-Qwen3-14B-Q3_K_XL.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:c2f530bbb9ee2d980624958ec5ac650cfea1415c47b381cecf4070a6c9247a30
|
||||
size 8581324928
|
||||
3
lemon07r_VellumMini-0.1-Qwen3-14B-Q4_0.gguf
Normal file
3
lemon07r_VellumMini-0.1-Qwen3-14B-Q4_0.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:23b43a4ca32bafd133548a7edfabfe10abdab46a9f5ff77a5cf47e2bf2c6bd67
|
||||
size 8543001728
|
||||
3
lemon07r_VellumMini-0.1-Qwen3-14B-Q4_1.gguf
Normal file
3
lemon07r_VellumMini-0.1-Qwen3-14B-Q4_1.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:b56269dcadf1f7aa7fbeb81145d5b610821121acc3a7cc37e2860729dfd56f0d
|
||||
size 9389522048
|
||||
3
lemon07r_VellumMini-0.1-Qwen3-14B-Q4_K_L.gguf
Normal file
3
lemon07r_VellumMini-0.1-Qwen3-14B-Q4_K_L.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:deaddadfc28bf95bf48e974699f7482f4b1ac8adadf934d8291af02751a1ded5
|
||||
size 9579110528
|
||||
3
lemon07r_VellumMini-0.1-Qwen3-14B-Q4_K_M.gguf
Normal file
3
lemon07r_VellumMini-0.1-Qwen3-14B-Q4_K_M.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:7c56980b12c757e06bd4d4e99fca4eacf76fbad9bc46d59fde5fb62280157320
|
||||
size 9001753728
|
||||
3
lemon07r_VellumMini-0.1-Qwen3-14B-Q4_K_S.gguf
Normal file
3
lemon07r_VellumMini-0.1-Qwen3-14B-Q4_K_S.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:56b8fcc2ba9ac8ff1f356a051bdef349bf751161c380140ebce9a2379c5265ee
|
||||
size 8573475968
|
||||
3
lemon07r_VellumMini-0.1-Qwen3-14B-Q5_K_L.gguf
Normal file
3
lemon07r_VellumMini-0.1-Qwen3-14B-Q5_K_L.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:7f5b5cd6b153b0af7cd4acba0224ec0103918800b832980ac40f08abfe8d1f01
|
||||
size 10994688128
|
||||
3
lemon07r_VellumMini-0.1-Qwen3-14B-Q5_K_M.gguf
Normal file
3
lemon07r_VellumMini-0.1-Qwen3-14B-Q5_K_M.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:a82d4ff8e07a2aa22846d74458dd23276c101c5fb5287d4a437444b0877762b0
|
||||
size 10514570368
|
||||
3
lemon07r_VellumMini-0.1-Qwen3-14B-Q5_K_S.gguf
Normal file
3
lemon07r_VellumMini-0.1-Qwen3-14B-Q5_K_S.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:95229867401697f8ace6279f15c2c90cc00ac010ff89c018545da34ebc80e38b
|
||||
size 10263895168
|
||||
3
lemon07r_VellumMini-0.1-Qwen3-14B-Q6_K.gguf
Normal file
3
lemon07r_VellumMini-0.1-Qwen3-14B-Q6_K.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:3a15c0570718b6c388780575f2efb73b2d74cf24c9349df6c0818650e6499781
|
||||
size 12121938048
|
||||
3
lemon07r_VellumMini-0.1-Qwen3-14B-Q6_K_L.gguf
Normal file
3
lemon07r_VellumMini-0.1-Qwen3-14B-Q6_K_L.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:a296c3f76e42d5ceba1a0c4b10e08c5a2669d8cb43fd4f0e4ae1017112615d77
|
||||
size 12498739328
|
||||
3
lemon07r_VellumMini-0.1-Qwen3-14B-Q8_0.gguf
Normal file
3
lemon07r_VellumMini-0.1-Qwen3-14B-Q8_0.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:aa499475ea3ef826610d418658d5947d29cc4b03b74ef9d3a1ff7d9486e7c1da
|
||||
size 15698534528
|
||||
3
lemon07r_VellumMini-0.1-Qwen3-14B-bf16.gguf
Normal file
3
lemon07r_VellumMini-0.1-Qwen3-14B-bf16.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:b77791e6fecd442fd8245b70aa741128bfba9b48c6f37e3d284962da317872bd
|
||||
size 29543423840
|
||||
3
lemon07r_VellumMini-0.1-Qwen3-14B-imatrix.gguf
Normal file
3
lemon07r_VellumMini-0.1-Qwen3-14B-imatrix.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:0a1cf0eb8eedeb32947ed50c8c0dd07151826dbcc9e18d8218c53d001340d236
|
||||
size 7743584
|
||||
Reference in New Issue
Block a user