初始化项目，由ModelHub XC社区提供模型

Model: bartowski/Qwen2-VL-7B-Instruct-GGUF
Source: Original Platform

.gitattributes

@@ -0,0 +1,60 @@
+*.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
+Qwen2-VL-7B-Instruct-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2-VL-7B-Instruct-Q6_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2-VL-7B-Instruct-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2-VL-7B-Instruct-Q5_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2-VL-7B-Instruct-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2-VL-7B-Instruct-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2-VL-7B-Instruct-Q4_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2-VL-7B-Instruct-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2-VL-7B-Instruct-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2-VL-7B-Instruct-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2-VL-7B-Instruct-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2-VL-7B-Instruct-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2-VL-7B-Instruct-Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2-VL-7B-Instruct-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2-VL-7B-Instruct-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2-VL-7B-Instruct-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2-VL-7B-Instruct-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2-VL-7B-Instruct-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2-VL-7B-Instruct-Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2-VL-7B-Instruct-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2-VL-7B-Instruct-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2-VL-7B-Instruct-f16.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2-VL-7B-Instruct.imatrix filter=lfs diff=lfs merge=lfs -text
+mmproj-Qwen2-VL-7B-Instruct-f32.gguf filter=lfs diff=lfs merge=lfs -text
+mmproj-Qwen2-VL-7B-Instruct-f16.gguf filter=lfs diff=lfs merge=lfs -text

Qwen2-VL-7B-Instruct-IQ2_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac11fc80432f65ffd6562dc4828efb328838fe73778721c48d3e6c3857df5d13
+size 2780341408

Qwen2-VL-7B-Instruct-IQ3_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10215bddf5a000b5595f8658a75f3b8f252052d4f4e058610652a5a1aca64e09
+size 3574011040

Qwen2-VL-7B-Instruct-IQ3_XS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21a82907aefc500df2e7010b9b705a564ecc2f90bbd2c2f1a7fe106dc6e625a8
+size 3346255008

Qwen2-VL-7B-Instruct-IQ4_NL.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea4b81eb37dd3add98d69441b1fb4fd52ae130606c4cf35b342129d35ad72c79
+size 4437812384

Qwen2-VL-7B-Instruct-IQ4_XS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4e6554b709a4293bc18e993bd6dd765f4a136faaa155447deef74ba4014f85b
+size 4218471584

Qwen2-VL-7B-Instruct-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62ac3535a7c19943449dcb1444af10e824b05772d3c4b91f604f060a4051ef78
+size 3015939232

Qwen2-VL-7B-Instruct-Q2_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a81396e5c215f81339581081ace7b600fd881b0689fcb25f8cfa7fb50022240c
+size 3548163232

Qwen2-VL-7B-Instruct-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02162382afe224e1a7e89a348bd11201a84124e75cdae5a26eda8d3b01bf4110
+size 4088458400

Qwen2-VL-7B-Instruct-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2953834cda296fcf58cf87c807405c0fe911b4edd654747580a6cdf5fc65820
+size 3808390304

Qwen2-VL-7B-Instruct-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb3c141714e48959a1ae9846df25eb1907b6e2c6a953bbca35a8ef7ee58e4ed3
+size 3492367520

Qwen2-VL-7B-Instruct-Q3_K_XL.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abe7a85dfd495c1a96a451f3e5719729b21a9ed9dcea09e5191f904ef4ebaa10
+size 4565331104

Qwen2-VL-7B-Instruct-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0c646b0a43a36d01842cf6f3e592531c0c88f81fd932933fdd181d6281d3a92
+size 4444120224

Qwen2-VL-7B-Instruct-Q4_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fa724bde030f1bc5fd8aa27504b3ed064cefb8606b55ae98773d36950a4df46
+size 5087562912

Qwen2-VL-7B-Instruct-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30f199c2192fce1db0fbbbd484c7b2aa69ccce883890853f9807e1c837405a80
+size 4683072672

Qwen2-VL-7B-Instruct-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bf6013c46073cb73a3aca7a5e60158144d394bb5964b40e7cffcd9a76be95b3
+size 4457768096

Qwen2-VL-7B-Instruct-Q5_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1cad59da9dedcd9cb2941db02a666985e695b13b9e640b522d50a561012dfb0d
+size 5781195936

Qwen2-VL-7B-Instruct-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d039951ea62de6b20f83fc0467ea6c584a9ac93839a8d9459f57d20533204f8b
+size 5444830368

Qwen2-VL-7B-Instruct-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff43f5808e37c218c08bb0a56bc86402a5810dd1c6966555d96f7fd59dab3845
+size 5315175584

Qwen2-VL-7B-Instruct-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a874cbd3a93b140048534bf39d6cdd96db48e476dfdbc2b69866b0600393b159
+size 6254197920

Qwen2-VL-7B-Instruct-Q6_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0a154058a1d4d077ffdfea50167b31000b6eafb2e973613a52443cc9660df56
+size 6518181024

Qwen2-VL-7B-Instruct-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa4c302bfcaa5395718aa6cfa24b0c7faf488e02ee966e29e86b321630ba9774
+size 8098524320

Qwen2-VL-7B-Instruct-f16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:303f4d37bc482209818d50b3e56c03703952d3c788279c593986ac84a6aaabc8
+size 15237852064

Qwen2-VL-7B-Instruct.imatrix

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7478374e889770d8c124f180b892765810c3ceb179536662e78b77c07d3256b6
+size 4536678

README.md

@@ -0,0 +1,185 @@
+---
+quantized_by: bartowski
+pipeline_tag: image-text-to-text
+language:
+- en
+license: apache-2.0
+base_model: Qwen/Qwen2-VL-7B-Instruct
+tags:
+- multimodal
+---
+
+## Llamacpp imatrix Quantizations of Qwen2-VL-7B-Instruct
+
+Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b4327">b4327</a> for quantization.
+
+Original model: https://huggingface.co/Qwen/Qwen2-VL-7B-Instruct
+
+All quants made using imatrix option with dataset from [here](https://gist.github.com/bartowski1182/eb213dccb3571f863da82e99418f81e8)
+
+## How to run
+
+Since this a new vision model, I'll add special instructions this one time
+
+If you've build llama.cpp locally, you'll want to run:
+
+```
+./llama-qwen2vl-cli -m /models/Qwen2-VL-7B-Instruct-Q4_0.gguf --mmproj /models/mmproj-Qwen2-VL-7B-Instruct-f32.gguf -p 'Describe this image.' --image '/models/test_image.jpg'
+```
+
+And the model will output the answer. Very simple stuff, similar to other llava models, just make sure you use the correct binary!
+
+## 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 |
+| -------- | ---------- | --------- | ----- | ----------- |
+| [Qwen2-VL-7B-Instruct-f16.gguf](https://huggingface.co/bartowski/Qwen2-VL-7B-Instruct-GGUF/blob/main/Qwen2-VL-7B-Instruct-f16.gguf) | f16 | 15.24GB | false | Full F16 weights. |
+| [Qwen2-VL-7B-Instruct-Q8_0.gguf](https://huggingface.co/bartowski/Qwen2-VL-7B-Instruct-GGUF/blob/main/Qwen2-VL-7B-Instruct-Q8_0.gguf) | Q8_0 | 8.10GB | false | Extremely high quality, generally unneeded but max available quant. |
+| [Qwen2-VL-7B-Instruct-Q6_K_L.gguf](https://huggingface.co/bartowski/Qwen2-VL-7B-Instruct-GGUF/blob/main/Qwen2-VL-7B-Instruct-Q6_K_L.gguf) | Q6_K_L | 6.52GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. |
+| [Qwen2-VL-7B-Instruct-Q6_K.gguf](https://huggingface.co/bartowski/Qwen2-VL-7B-Instruct-GGUF/blob/main/Qwen2-VL-7B-Instruct-Q6_K.gguf) | Q6_K | 6.25GB | false | Very high quality, near perfect, *recommended*. |
+| [Qwen2-VL-7B-Instruct-Q5_K_L.gguf](https://huggingface.co/bartowski/Qwen2-VL-7B-Instruct-GGUF/blob/main/Qwen2-VL-7B-Instruct-Q5_K_L.gguf) | Q5_K_L | 5.78GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. |
+| [Qwen2-VL-7B-Instruct-Q5_K_M.gguf](https://huggingface.co/bartowski/Qwen2-VL-7B-Instruct-GGUF/blob/main/Qwen2-VL-7B-Instruct-Q5_K_M.gguf) | Q5_K_M | 5.44GB | false | High quality, *recommended*. |
+| [Qwen2-VL-7B-Instruct-Q5_K_S.gguf](https://huggingface.co/bartowski/Qwen2-VL-7B-Instruct-GGUF/blob/main/Qwen2-VL-7B-Instruct-Q5_K_S.gguf) | Q5_K_S | 5.32GB | false | High quality, *recommended*. |
+| [Qwen2-VL-7B-Instruct-Q4_K_L.gguf](https://huggingface.co/bartowski/Qwen2-VL-7B-Instruct-GGUF/blob/main/Qwen2-VL-7B-Instruct-Q4_K_L.gguf) | Q4_K_L | 5.09GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. |
+| [Qwen2-VL-7B-Instruct-Q4_K_M.gguf](https://huggingface.co/bartowski/Qwen2-VL-7B-Instruct-GGUF/blob/main/Qwen2-VL-7B-Instruct-Q4_K_M.gguf) | Q4_K_M | 4.68GB | false | Good quality, default size for most use cases, *recommended*. |
+| [Qwen2-VL-7B-Instruct-Q3_K_XL.gguf](https://huggingface.co/bartowski/Qwen2-VL-7B-Instruct-GGUF/blob/main/Qwen2-VL-7B-Instruct-Q3_K_XL.gguf) | Q3_K_XL | 4.57GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. |
+| [Qwen2-VL-7B-Instruct-Q4_K_S.gguf](https://huggingface.co/bartowski/Qwen2-VL-7B-Instruct-GGUF/blob/main/Qwen2-VL-7B-Instruct-Q4_K_S.gguf) | Q4_K_S | 4.46GB | false | Slightly lower quality with more space savings, *recommended*. |
+| [Qwen2-VL-7B-Instruct-Q4_0.gguf](https://huggingface.co/bartowski/Qwen2-VL-7B-Instruct-GGUF/blob/main/Qwen2-VL-7B-Instruct-Q4_0.gguf) | Q4_0 | 4.44GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. |
+| [Qwen2-VL-7B-Instruct-IQ4_NL.gguf](https://huggingface.co/bartowski/Qwen2-VL-7B-Instruct-GGUF/blob/main/Qwen2-VL-7B-Instruct-IQ4_NL.gguf) | IQ4_NL | 4.44GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. |
+| [Qwen2-VL-7B-Instruct-IQ4_XS.gguf](https://huggingface.co/bartowski/Qwen2-VL-7B-Instruct-GGUF/blob/main/Qwen2-VL-7B-Instruct-IQ4_XS.gguf) | IQ4_XS | 4.22GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
+| [Qwen2-VL-7B-Instruct-Q3_K_L.gguf](https://huggingface.co/bartowski/Qwen2-VL-7B-Instruct-GGUF/blob/main/Qwen2-VL-7B-Instruct-Q3_K_L.gguf) | Q3_K_L | 4.09GB | false | Lower quality but usable, good for low RAM availability. |
+| [Qwen2-VL-7B-Instruct-Q3_K_M.gguf](https://huggingface.co/bartowski/Qwen2-VL-7B-Instruct-GGUF/blob/main/Qwen2-VL-7B-Instruct-Q3_K_M.gguf) | Q3_K_M | 3.81GB | false | Low quality. |
+| [Qwen2-VL-7B-Instruct-IQ3_M.gguf](https://huggingface.co/bartowski/Qwen2-VL-7B-Instruct-GGUF/blob/main/Qwen2-VL-7B-Instruct-IQ3_M.gguf) | IQ3_M | 3.57GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
+| [Qwen2-VL-7B-Instruct-Q2_K_L.gguf](https://huggingface.co/bartowski/Qwen2-VL-7B-Instruct-GGUF/blob/main/Qwen2-VL-7B-Instruct-Q2_K_L.gguf) | Q2_K_L | 3.55GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. |
+| [Qwen2-VL-7B-Instruct-Q3_K_S.gguf](https://huggingface.co/bartowski/Qwen2-VL-7B-Instruct-GGUF/blob/main/Qwen2-VL-7B-Instruct-Q3_K_S.gguf) | Q3_K_S | 3.49GB | false | Low quality, not recommended. |
+| [Qwen2-VL-7B-Instruct-IQ3_XS.gguf](https://huggingface.co/bartowski/Qwen2-VL-7B-Instruct-GGUF/blob/main/Qwen2-VL-7B-Instruct-IQ3_XS.gguf) | IQ3_XS | 3.35GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
+| [Qwen2-VL-7B-Instruct-Q2_K.gguf](https://huggingface.co/bartowski/Qwen2-VL-7B-Instruct-GGUF/blob/main/Qwen2-VL-7B-Instruct-Q2_K.gguf) | Q2_K | 3.02GB | false | Very low quality but surprisingly usable. |
+| [Qwen2-VL-7B-Instruct-IQ2_M.gguf](https://huggingface.co/bartowski/Qwen2-VL-7B-Instruct-GGUF/blob/main/Qwen2-VL-7B-Instruct-IQ2_M.gguf) | IQ2_M | 2.78GB | 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/Qwen2-VL-7B-Instruct-GGUF --include "Qwen2-VL-7B-Instruct-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/Qwen2-VL-7B-Instruct-GGUF --include "Qwen2-VL-7B-Instruct-Q8_0/*" --local-dir ./
+```
+
+You can either specify a new local-dir (Qwen2-VL-7B-Instruct-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/ggerganov/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/ggerganov/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/ggerganov/llama.cpp/pull/10541) which will also repack the weights for ARM, though only the 4_4 for now. The loading time may be slower but it will result in an overall speed incrase.
+
+<details>
+  <summary>Click to view Q4_0_X_X information</summary>
+These are *NOT* for Metal (Apple) or GPU (nvidia/AMD/intel) offloading, only ARM chips (and certain AVX2/AVX512 CPUs).
+
+If you're using an ARM chip, the Q4_0_X_X quants will have a substantial speedup. Check out Q4_0_4_4 speed comparisons [on the original pull request](https://github.com/ggerganov/llama.cpp/pull/5780#pullrequestreview-21657544660)
+
+To check which one would work best for your ARM chip, you can check [AArch64 SoC features](https://gpages.juszkiewicz.com.pl/arm-socs-table/arm-socs.html) (thanks EloyOn!).
+
+If you're using a CPU that supports AVX2 or AVX512 (typically server CPUs and AMD's latest Zen5 CPUs) and are not offloading to a GPU, the Q4_0_8_8 may offer a nice speed as well:
+
+<details>
+  <summary>Click to view benchmarks on an AVX2 system (EPYC7702)</summary>
+
+| model                          |       size |     params | backend    | threads |          test |                  t/s |  % (vs Q4_0)  |
+| ------------------------------ | ---------: | ---------: | ---------- | ------: | ------------: | -------------------: |-------------: |
+| qwen2 3B Q4_0                  |   1.70 GiB |     3.09 B | CPU        |      64 |         pp512 |        204.03 ± 1.03 |          100% |
+| qwen2 3B Q4_0                  |   1.70 GiB |     3.09 B | CPU        |      64 |        pp1024 |        282.92 ± 0.19 |          100% |
+| qwen2 3B Q4_0                  |   1.70 GiB |     3.09 B | CPU        |      64 |        pp2048 |        259.49 ± 0.44 |          100% |
+| qwen2 3B Q4_0                  |   1.70 GiB |     3.09 B | CPU        |      64 |         tg128 |         39.12 ± 0.27 |          100% |
+| qwen2 3B Q4_0                  |   1.70 GiB |     3.09 B | CPU        |      64 |         tg256 |         39.31 ± 0.69 |          100% |
+| qwen2 3B Q4_0                  |   1.70 GiB |     3.09 B | CPU        |      64 |         tg512 |         40.52 ± 0.03 |          100% |
+| qwen2 3B Q4_K_M                |   1.79 GiB |     3.09 B | CPU        |      64 |         pp512 |        301.02 ± 1.74 |          147% |
+| qwen2 3B Q4_K_M                |   1.79 GiB |     3.09 B | CPU        |      64 |        pp1024 |        287.23 ± 0.20 |          101% |
+| qwen2 3B Q4_K_M                |   1.79 GiB |     3.09 B | CPU        |      64 |        pp2048 |        262.77 ± 1.81 |          101% |
+| qwen2 3B Q4_K_M                |   1.79 GiB |     3.09 B | CPU        |      64 |         tg128 |         18.80 ± 0.99 |           48% |
+| qwen2 3B Q4_K_M                |   1.79 GiB |     3.09 B | CPU        |      64 |         tg256 |         24.46 ± 3.04 |           83% |
+| qwen2 3B Q4_K_M                |   1.79 GiB |     3.09 B | CPU        |      64 |         tg512 |         36.32 ± 3.59 |           90% |
+| qwen2 3B Q4_0_8_8              |   1.69 GiB |     3.09 B | CPU        |      64 |         pp512 |        271.71 ± 3.53 |          133% |
+| qwen2 3B Q4_0_8_8              |   1.69 GiB |     3.09 B | CPU        |      64 |        pp1024 |       279.86 ± 45.63 |          100% |
+| qwen2 3B Q4_0_8_8              |   1.69 GiB |     3.09 B | CPU        |      64 |        pp2048 |        320.77 ± 5.00 |          124% |
+| qwen2 3B Q4_0_8_8              |   1.69 GiB |     3.09 B | CPU        |      64 |         tg128 |         43.51 ± 0.05 |          111% |
+| qwen2 3B Q4_0_8_8              |   1.69 GiB |     3.09 B | CPU        |      64 |         tg256 |         43.35 ± 0.09 |          110% |
+| qwen2 3B Q4_0_8_8              |   1.69 GiB |     3.09 B | CPU        |      64 |         tg512 |         42.60 ± 0.31 |          105% |
+
+Q4_0_8_8 offers a nice bump to prompt processing and a small bump to text generation
+
+</details>
+
+</details>
+
+## Which file should I choose?
+
+<details>
+  <summary>Click here for details</summary>
+
+A great write up with charts showing various performances is provided by Artefact2 [here](https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9)
+
+The first thing to figure out is how big a model you can run. To do this, you'll need to figure out how much RAM and/or VRAM you have.
+
+If you want your model running as FAST as possible, you'll want to fit the whole thing on your GPU's VRAM. Aim for a quant with a file size 1-2GB smaller than your GPU's total VRAM.
+
+If you want the absolute maximum quality, add both your system RAM and your GPU's VRAM together, then similarly grab a quant with a file size 1-2GB Smaller than that total.
+
+Next, you'll need to decide if you want to use an 'I-quant' or a 'K-quant'.
+
+If you don't want to think too much, grab one of the K-quants. These are in format 'QX_K_X', like Q5_K_M.
+
+If you want to get more into the weeds, you can check out this extremely useful feature chart:
+
+[llama.cpp feature matrix](https://github.com/ggerganov/llama.cpp/wiki/Feature-matrix)
+
+But basically, if you're aiming for below Q4, and you're running cuBLAS (Nvidia) or rocBLAS (AMD), you should look towards the I-quants. These are in format IQX_X, like IQ3_M. These are newer and offer better performance for their size.
+
+These I-quants can also be used on CPU and Apple Metal, but will be slower than their K-quant equivalent, so speed vs performance is a tradeoff you'll have to decide.
+
+The I-quants are *not* compatible with Vulcan, which is also AMD, so if you have an AMD card double check if you're using the rocBLAS build or the Vulcan build. At the time of writing this, LM Studio has a preview with ROCm support, and other inference engines have specific builds for ROCm.
+
+</details>
+
+## Credits
+
+Thank you kalomaze and Dampf for assistance in creating the imatrix calibration dataset.
+
+Thank you ZeroWw for the inspiration to experiment with embed/output.
+
+Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski

configuration.json

@@ -0,0 +1 @@
+{"framework": "pytorch", "task": "image-text-to-text", "allow_remote": true}

mmproj-Qwen2-VL-7B-Instruct-f16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8f920894800b821a31a76540f14fde9dc1671003721509fc256e285e055c25d
+size 1352635904

mmproj-Qwen2-VL-7B-Instruct-f32.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e315ed7aea5d835dd1dbee376b4f89478c240f56957901081d27e636a029e88b
+size 2703066624