初始化项目，由ModelHub XC社区提供模型
Model: bartowski/smolagents_SmolVLM2-2.2B-Instruct-Agentic-GUI-GGUF Source: Original Platform
This commit is contained in:
ModelHub XC
62
.gitattributes
vendored
Normal file
62
.gitattributes
vendored
Normal file
@@ -0,0 +1,62 @@
|
||||
*.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
|
||||
smolagents_SmolVLM2-2.2B-Instruct-Agentic-GUI-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
smolagents_SmolVLM2-2.2B-Instruct-Agentic-GUI-Q6_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
smolagents_SmolVLM2-2.2B-Instruct-Agentic-GUI-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
smolagents_SmolVLM2-2.2B-Instruct-Agentic-GUI-Q5_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
smolagents_SmolVLM2-2.2B-Instruct-Agentic-GUI-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
smolagents_SmolVLM2-2.2B-Instruct-Agentic-GUI-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
smolagents_SmolVLM2-2.2B-Instruct-Agentic-GUI-Q4_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
smolagents_SmolVLM2-2.2B-Instruct-Agentic-GUI-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
smolagents_SmolVLM2-2.2B-Instruct-Agentic-GUI-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
smolagents_SmolVLM2-2.2B-Instruct-Agentic-GUI-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
smolagents_SmolVLM2-2.2B-Instruct-Agentic-GUI-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
smolagents_SmolVLM2-2.2B-Instruct-Agentic-GUI-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
smolagents_SmolVLM2-2.2B-Instruct-Agentic-GUI-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
smolagents_SmolVLM2-2.2B-Instruct-Agentic-GUI-Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
smolagents_SmolVLM2-2.2B-Instruct-Agentic-GUI-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
smolagents_SmolVLM2-2.2B-Instruct-Agentic-GUI-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
smolagents_SmolVLM2-2.2B-Instruct-Agentic-GUI-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
smolagents_SmolVLM2-2.2B-Instruct-Agentic-GUI-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
smolagents_SmolVLM2-2.2B-Instruct-Agentic-GUI-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
smolagents_SmolVLM2-2.2B-Instruct-Agentic-GUI-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
smolagents_SmolVLM2-2.2B-Instruct-Agentic-GUI-Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
smolagents_SmolVLM2-2.2B-Instruct-Agentic-GUI-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
smolagents_SmolVLM2-2.2B-Instruct-Agentic-GUI-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
smolagents_SmolVLM2-2.2B-Instruct-Agentic-GUI-bf16.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
smolagents_SmolVLM2-2.2B-Instruct-Agentic-GUI-imatrix.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
mmproj-smolagents_SmolVLM2-2.2B-Instruct-Agentic-GUI-f16.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
mmproj-smolagents_SmolVLM2-2.2B-Instruct-Agentic-GUI-bf16.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
164
README.md
Normal file
164
README.md
Normal file
@@ -0,0 +1,164 @@
|
||||
---
|
||||
quantized_by: bartowski
|
||||
pipeline_tag: image-text-to-text
|
||||
base_model_relation: quantized
|
||||
base_model: smolagents/SmolVLM2-2.2B-Instruct-Agentic-GUI
|
||||
---
|
||||
|
||||
## Llamacpp imatrix Quantizations of SmolVLM2-2.2B-Instruct-Agentic-GUI by smolagents
|
||||
|
||||
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/b6714">b6714</a> for quantization.
|
||||
|
||||
Original model: https://huggingface.co/smolagents/SmolVLM2-2.2B-Instruct-Agentic-GUI
|
||||
|
||||
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 |
|
||||
| -------- | ---------- | --------- | ----- | ----------- |
|
||||
| [SmolVLM2-2.2B-Instruct-Agentic-GUI-bf16.gguf](https://huggingface.co/bartowski/smolagents_SmolVLM2-2.2B-Instruct-Agentic-GUI-GGUF/blob/main/smolagents_SmolVLM2-2.2B-Instruct-Agentic-GUI-bf16.gguf) | bf16 | 3.63GB | false | Full BF16 weights. |
|
||||
| [SmolVLM2-2.2B-Instruct-Agentic-GUI-Q8_0.gguf](https://huggingface.co/bartowski/smolagents_SmolVLM2-2.2B-Instruct-Agentic-GUI-GGUF/blob/main/smolagents_SmolVLM2-2.2B-Instruct-Agentic-GUI-Q8_0.gguf) | Q8_0 | 1.93GB | false | Extremely high quality, generally unneeded but max available quant. |
|
||||
| [SmolVLM2-2.2B-Instruct-Agentic-GUI-Q6_K_L.gguf](https://huggingface.co/bartowski/smolagents_SmolVLM2-2.2B-Instruct-Agentic-GUI-GGUF/blob/main/smolagents_SmolVLM2-2.2B-Instruct-Agentic-GUI-Q6_K_L.gguf) | Q6_K_L | 1.54GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. |
|
||||
| [SmolVLM2-2.2B-Instruct-Agentic-GUI-Q6_K.gguf](https://huggingface.co/bartowski/smolagents_SmolVLM2-2.2B-Instruct-Agentic-GUI-GGUF/blob/main/smolagents_SmolVLM2-2.2B-Instruct-Agentic-GUI-Q6_K.gguf) | Q6_K | 1.49GB | false | Very high quality, near perfect, *recommended*. |
|
||||
| [SmolVLM2-2.2B-Instruct-Agentic-GUI-Q5_K_L.gguf](https://huggingface.co/bartowski/smolagents_SmolVLM2-2.2B-Instruct-Agentic-GUI-GGUF/blob/main/smolagents_SmolVLM2-2.2B-Instruct-Agentic-GUI-Q5_K_L.gguf) | Q5_K_L | 1.36GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. |
|
||||
| [SmolVLM2-2.2B-Instruct-Agentic-GUI-Q5_K_M.gguf](https://huggingface.co/bartowski/smolagents_SmolVLM2-2.2B-Instruct-Agentic-GUI-GGUF/blob/main/smolagents_SmolVLM2-2.2B-Instruct-Agentic-GUI-Q5_K_M.gguf) | Q5_K_M | 1.30GB | false | High quality, *recommended*. |
|
||||
| [SmolVLM2-2.2B-Instruct-Agentic-GUI-Q5_K_S.gguf](https://huggingface.co/bartowski/smolagents_SmolVLM2-2.2B-Instruct-Agentic-GUI-GGUF/blob/main/smolagents_SmolVLM2-2.2B-Instruct-Agentic-GUI-Q5_K_S.gguf) | Q5_K_S | 1.26GB | false | High quality, *recommended*. |
|
||||
| [SmolVLM2-2.2B-Instruct-Agentic-GUI-Q4_K_L.gguf](https://huggingface.co/bartowski/smolagents_SmolVLM2-2.2B-Instruct-Agentic-GUI-GGUF/blob/main/smolagents_SmolVLM2-2.2B-Instruct-Agentic-GUI-Q4_K_L.gguf) | Q4_K_L | 1.19GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. |
|
||||
| [SmolVLM2-2.2B-Instruct-Agentic-GUI-Q4_1.gguf](https://huggingface.co/bartowski/smolagents_SmolVLM2-2.2B-Instruct-Agentic-GUI-GGUF/blob/main/smolagents_SmolVLM2-2.2B-Instruct-Agentic-GUI-Q4_1.gguf) | Q4_1 | 1.15GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. |
|
||||
| [SmolVLM2-2.2B-Instruct-Agentic-GUI-Q4_K_M.gguf](https://huggingface.co/bartowski/smolagents_SmolVLM2-2.2B-Instruct-Agentic-GUI-GGUF/blob/main/smolagents_SmolVLM2-2.2B-Instruct-Agentic-GUI-Q4_K_M.gguf) | Q4_K_M | 1.11GB | false | Good quality, default size for most use cases, *recommended*. |
|
||||
| [SmolVLM2-2.2B-Instruct-Agentic-GUI-Q4_K_S.gguf](https://huggingface.co/bartowski/smolagents_SmolVLM2-2.2B-Instruct-Agentic-GUI-GGUF/blob/main/smolagents_SmolVLM2-2.2B-Instruct-Agentic-GUI-Q4_K_S.gguf) | Q4_K_S | 1.06GB | false | Slightly lower quality with more space savings, *recommended*. |
|
||||
| [SmolVLM2-2.2B-Instruct-Agentic-GUI-Q3_K_XL.gguf](https://huggingface.co/bartowski/smolagents_SmolVLM2-2.2B-Instruct-Agentic-GUI-GGUF/blob/main/smolagents_SmolVLM2-2.2B-Instruct-Agentic-GUI-Q3_K_XL.gguf) | Q3_K_XL | 1.06GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. |
|
||||
| [SmolVLM2-2.2B-Instruct-Agentic-GUI-Q4_0.gguf](https://huggingface.co/bartowski/smolagents_SmolVLM2-2.2B-Instruct-Agentic-GUI-GGUF/blob/main/smolagents_SmolVLM2-2.2B-Instruct-Agentic-GUI-Q4_0.gguf) | Q4_0 | 1.05GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. |
|
||||
| [SmolVLM2-2.2B-Instruct-Agentic-GUI-IQ4_NL.gguf](https://huggingface.co/bartowski/smolagents_SmolVLM2-2.2B-Instruct-Agentic-GUI-GGUF/blob/main/smolagents_SmolVLM2-2.2B-Instruct-Agentic-GUI-IQ4_NL.gguf) | IQ4_NL | 1.05GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. |
|
||||
| [SmolVLM2-2.2B-Instruct-Agentic-GUI-IQ4_XS.gguf](https://huggingface.co/bartowski/smolagents_SmolVLM2-2.2B-Instruct-Agentic-GUI-GGUF/blob/main/smolagents_SmolVLM2-2.2B-Instruct-Agentic-GUI-IQ4_XS.gguf) | IQ4_XS | 0.99GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
|
||||
| [SmolVLM2-2.2B-Instruct-Agentic-GUI-Q3_K_L.gguf](https://huggingface.co/bartowski/smolagents_SmolVLM2-2.2B-Instruct-Agentic-GUI-GGUF/blob/main/smolagents_SmolVLM2-2.2B-Instruct-Agentic-GUI-Q3_K_L.gguf) | Q3_K_L | 0.98GB | false | Lower quality but usable, good for low RAM availability. |
|
||||
| [SmolVLM2-2.2B-Instruct-Agentic-GUI-Q3_K_M.gguf](https://huggingface.co/bartowski/smolagents_SmolVLM2-2.2B-Instruct-Agentic-GUI-GGUF/blob/main/smolagents_SmolVLM2-2.2B-Instruct-Agentic-GUI-Q3_K_M.gguf) | Q3_K_M | 0.90GB | false | Low quality. |
|
||||
| [SmolVLM2-2.2B-Instruct-Agentic-GUI-IQ3_M.gguf](https://huggingface.co/bartowski/smolagents_SmolVLM2-2.2B-Instruct-Agentic-GUI-GGUF/blob/main/smolagents_SmolVLM2-2.2B-Instruct-Agentic-GUI-IQ3_M.gguf) | IQ3_M | 0.85GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
|
||||
| [SmolVLM2-2.2B-Instruct-Agentic-GUI-Q3_K_S.gguf](https://huggingface.co/bartowski/smolagents_SmolVLM2-2.2B-Instruct-Agentic-GUI-GGUF/blob/main/smolagents_SmolVLM2-2.2B-Instruct-Agentic-GUI-Q3_K_S.gguf) | Q3_K_S | 0.82GB | false | Low quality, not recommended. |
|
||||
| [SmolVLM2-2.2B-Instruct-Agentic-GUI-Q2_K_L.gguf](https://huggingface.co/bartowski/smolagents_SmolVLM2-2.2B-Instruct-Agentic-GUI-GGUF/blob/main/smolagents_SmolVLM2-2.2B-Instruct-Agentic-GUI-Q2_K_L.gguf) | Q2_K_L | 0.81GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. |
|
||||
| [SmolVLM2-2.2B-Instruct-Agentic-GUI-IQ3_XS.gguf](https://huggingface.co/bartowski/smolagents_SmolVLM2-2.2B-Instruct-Agentic-GUI-GGUF/blob/main/smolagents_SmolVLM2-2.2B-Instruct-Agentic-GUI-IQ3_XS.gguf) | IQ3_XS | 0.78GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
|
||||
| [SmolVLM2-2.2B-Instruct-Agentic-GUI-IQ3_XXS.gguf](https://huggingface.co/bartowski/smolagents_SmolVLM2-2.2B-Instruct-Agentic-GUI-GGUF/blob/main/smolagents_SmolVLM2-2.2B-Instruct-Agentic-GUI-IQ3_XXS.gguf) | IQ3_XXS | 0.72GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. |
|
||||
| [SmolVLM2-2.2B-Instruct-Agentic-GUI-Q2_K.gguf](https://huggingface.co/bartowski/smolagents_SmolVLM2-2.2B-Instruct-Agentic-GUI-GGUF/blob/main/smolagents_SmolVLM2-2.2B-Instruct-Agentic-GUI-Q2_K.gguf) | Q2_K | 0.71GB | false | Very low quality but surprisingly usable. |
|
||||
| [SmolVLM2-2.2B-Instruct-Agentic-GUI-IQ2_M.gguf](https://huggingface.co/bartowski/smolagents_SmolVLM2-2.2B-Instruct-Agentic-GUI-GGUF/blob/main/smolagents_SmolVLM2-2.2B-Instruct-Agentic-GUI-IQ2_M.gguf) | IQ2_M | 0.66GB | 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/smolagents_SmolVLM2-2.2B-Instruct-Agentic-GUI-GGUF --include "smolagents_SmolVLM2-2.2B-Instruct-Agentic-GUI-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/smolagents_SmolVLM2-2.2B-Instruct-Agentic-GUI-GGUF --include "smolagents_SmolVLM2-2.2B-Instruct-Agentic-GUI-Q8_0/*" --local-dir ./
|
||||
```
|
||||
|
||||
You can either specify a new local-dir (smolagents_SmolVLM2-2.2B-Instruct-Agentic-GUI-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
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:3948ffeaa499d5f9fcdcc62ad697c014819de9b3074e5fdcc14bec6b9e4d4481
|
||||
size 872301152
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:5f477be9e10a76481ebba81f5ee6b23f68facee900cfb31f951a8d368bfb796d
|
||||
size 872301152
|
||||
3
smolagents_SmolVLM2-2.2B-Instruct-Agentic-GUI-IQ2_M.gguf
Normal file
3
smolagents_SmolVLM2-2.2B-Instruct-Agentic-GUI-IQ2_M.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:b26109fdf8604c85693c741a8a46995c0ffc9e2223bf02397868baad6fb3c2fa
|
||||
size 658366336
|
||||
3
smolagents_SmolVLM2-2.2B-Instruct-Agentic-GUI-IQ3_M.gguf
Normal file
3
smolagents_SmolVLM2-2.2B-Instruct-Agentic-GUI-IQ3_M.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:4e4361224d5ee538e597a1e88f708e211d0fa75e4acaf1f6cf3dcab53a7af995
|
||||
size 853829504
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:8c7d742b22e51d870bf7e2a2e1d03261ecd753ebe3b9d42b83e831643b0ae945
|
||||
size 782657408
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:d2e4cab84e669aa93984389340ddde26b943c4669b883ebfbf6979e78c3cde15
|
||||
size 723640192
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:477f20b7463d209b8c108d4acf10d17102b4b199c8642b65440bf4785c600ada
|
||||
size 1047719808
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:b2911be2361a64d455d068c8d5ed26ab3c264c5f6acb40d17c861ca3fb3808a0
|
||||
size 994234240
|
||||
3
smolagents_SmolVLM2-2.2B-Instruct-Agentic-GUI-Q2_K.gguf
Normal file
3
smolagents_SmolVLM2-2.2B-Instruct-Agentic-GUI-Q2_K.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:dee119d72a43020e0c0259f13e23307d8f643fcd07f12bd20786a6cb01f10b4a
|
||||
size 707919744
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:b1c5ed8c913aa416f29c7591d4c787ca0552c005d2fb378642ede11198646755
|
||||
size 806479744
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:cfa25a5b935a3454be5c41df1be12d991142cff17931c1b8e9a30ad1c31aa7b3
|
||||
size 976119680
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:d7f8a1857e042c38fd7c83b0b143f4b19d37aa8f1526d0bb1e49f8156764fd76
|
||||
size 903767936
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:5dbbb21ccea18365710c59142d3bb4a05ae2c0fcdfefb19af409264fcbe5c7a2
|
||||
size 820406144
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:56a02b50389cfe8b0baa8ff23ada7f67b298ae42e731c3b22b8e115e99d7f46f
|
||||
size 1064429440
|
||||
3
smolagents_SmolVLM2-2.2B-Instruct-Agentic-GUI-Q4_0.gguf
Normal file
3
smolagents_SmolVLM2-2.2B-Instruct-Agentic-GUI-Q4_0.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:4a6c9cd468b97521f70c5498ac73ab2e1accd9ff6f557e1174ac1ea90c2801a9
|
||||
size 1050865536
|
||||
3
smolagents_SmolVLM2-2.2B-Instruct-Agentic-GUI-Q4_1.gguf
Normal file
3
smolagents_SmolVLM2-2.2B-Instruct-Agentic-GUI-Q4_1.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:e5f6fc0890e3a0e3c1ca4c135c1418dff86a0b0b6889792ef45c013e7f089ef5
|
||||
size 1154690944
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:beea9551e101fb400fb429a5818182c0ef5b320338767820f88e4978837cfcfc
|
||||
size 1187506048
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:a9e553b743421b711a7b7fa3bfc401b9e429188e470e7e6ba5ee2d22b06ae5e0
|
||||
size 1112600448
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:f796575efd709ae00adf70492649fedaae2d169f5706e498558efcb908409446
|
||||
size 1056108416
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:34c63c144a0c9bf486abaae11514d2a22d99d3268a11da21495c3a6717c87875
|
||||
size 1357375360
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:3a9e9ab69b3103ac762ab91497a04ca4bd44cb3a1314944ceb936d9a7236ce4d
|
||||
size 1295085440
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:0c4b3eca60b3f6d7fd6e93f6d0662ae1cb1ab2dbf903dd4d7de8bbd2ee7c3564
|
||||
size 1261662080
|
||||
3
smolagents_SmolVLM2-2.2B-Instruct-Agentic-GUI-Q6_K.gguf
Normal file
3
smolagents_SmolVLM2-2.2B-Instruct-Agentic-GUI-Q6_K.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:1654561ce95c1b2494f67751aea2af68b88a6ebe7faf512455cbcd8741a36aba
|
||||
size 1488975744
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:14e86eecc437c55b0991d98484ab5584227d697697c3cb57eca3a19bf7b786e8
|
||||
size 1537861504
|
||||
3
smolagents_SmolVLM2-2.2B-Instruct-Agentic-GUI-Q8_0.gguf
Normal file
3
smolagents_SmolVLM2-2.2B-Instruct-Agentic-GUI-Q8_0.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:60a8f44d9ad650b77b54d06bc0341e7a5ab6f24a06d2bb6b764eab4d87435fe6
|
||||
size 1927931776
|
||||
3
smolagents_SmolVLM2-2.2B-Instruct-Agentic-GUI-bf16.gguf
Normal file
3
smolagents_SmolVLM2-2.2B-Instruct-Agentic-GUI-bf16.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:1b8bb4626b1e3166d01961a5c2925ed62c5166b9dfea304bb02c893d66cd75a5
|
||||
size 3627116096
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:d207142aac93c6902edc389c2044b2f6133c2e12661d8e695fc22c019e4e2f4f
|
||||
size 1991968
|
||||
Reference in New Issue
Block a user