初始化项目，由ModelHub XC社区提供模型
Model: bartowski/Qwen_Qwen3-VL-4B-Instruct-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
|
||||
Qwen_Qwen3-VL-4B-Instruct-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Qwen_Qwen3-VL-4B-Instruct-Q6_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Qwen_Qwen3-VL-4B-Instruct-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Qwen_Qwen3-VL-4B-Instruct-Q5_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Qwen_Qwen3-VL-4B-Instruct-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Qwen_Qwen3-VL-4B-Instruct-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Qwen_Qwen3-VL-4B-Instruct-Q4_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Qwen_Qwen3-VL-4B-Instruct-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Qwen_Qwen3-VL-4B-Instruct-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Qwen_Qwen3-VL-4B-Instruct-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Qwen_Qwen3-VL-4B-Instruct-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Qwen_Qwen3-VL-4B-Instruct-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Qwen_Qwen3-VL-4B-Instruct-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Qwen_Qwen3-VL-4B-Instruct-Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Qwen_Qwen3-VL-4B-Instruct-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Qwen_Qwen3-VL-4B-Instruct-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Qwen_Qwen3-VL-4B-Instruct-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Qwen_Qwen3-VL-4B-Instruct-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Qwen_Qwen3-VL-4B-Instruct-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Qwen_Qwen3-VL-4B-Instruct-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Qwen_Qwen3-VL-4B-Instruct-Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Qwen_Qwen3-VL-4B-Instruct-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Qwen_Qwen3-VL-4B-Instruct-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Qwen_Qwen3-VL-4B-Instruct-bf16.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Qwen_Qwen3-VL-4B-Instruct-imatrix.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
mmproj-Qwen_Qwen3-VL-4B-Instruct-f16.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
mmproj-Qwen_Qwen3-VL-4B-Instruct-bf16.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
3
Qwen_Qwen3-VL-4B-Instruct-IQ2_M.gguf
Normal file
3
Qwen_Qwen3-VL-4B-Instruct-IQ2_M.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:34f34a8f3915eba1c73135b6410e5800f6b34151b0d07dd630ba482515b0463e
|
||||
size 1512984992
|
||||
3
Qwen_Qwen3-VL-4B-Instruct-IQ3_M.gguf
Normal file
3
Qwen_Qwen3-VL-4B-Instruct-IQ3_M.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:ed9bac8de221d35061e97289ce5e02d72caa3e4547e91c8a3343cc542d1d1a5e
|
||||
size 1962897312
|
||||
3
Qwen_Qwen3-VL-4B-Instruct-IQ3_XS.gguf
Normal file
3
Qwen_Qwen3-VL-4B-Instruct-IQ3_XS.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:47cb1b2a95488562a163945688e502506f0033e64c18fa570f6fc193c8a83428
|
||||
size 1814376352
|
||||
3
Qwen_Qwen3-VL-4B-Instruct-IQ3_XXS.gguf
Normal file
3
Qwen_Qwen3-VL-4B-Instruct-IQ3_XXS.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:7f0a2e5c819ce82e026cd51c6b61ae6e90b67edd42c9c6c5ab166fae03b5123f
|
||||
size 1670189472
|
||||
3
Qwen_Qwen3-VL-4B-Instruct-IQ4_NL.gguf
Normal file
3
Qwen_Qwen3-VL-4B-Instruct-IQ4_NL.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:c78d6fd7f94fd5fd20d810e86f4d31ff61b9d33dc48853a08c68ab4136a35e4a
|
||||
size 2381344672
|
||||
3
Qwen_Qwen3-VL-4B-Instruct-IQ4_XS.gguf
Normal file
3
Qwen_Qwen3-VL-4B-Instruct-IQ4_XS.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:dd6a6672d12121c4a5a8962dde2d8e253f21770974da7cf694cbc9b9f80e0996
|
||||
size 2270752672
|
||||
3
Qwen_Qwen3-VL-4B-Instruct-Q2_K.gguf
Normal file
3
Qwen_Qwen3-VL-4B-Instruct-Q2_K.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:3136b45fef1d64c359fd4934eea5db1bd9113919e872f2f1e556a6d6291fe357
|
||||
size 1669500832
|
||||
3
Qwen_Qwen3-VL-4B-Instruct-Q2_K_L.gguf
Normal file
3
Qwen_Qwen3-VL-4B-Instruct-Q2_K_L.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:e7b54acdf7c0765112f459ecd88641eb916954be3f00352a20fbeaf338416899
|
||||
size 1763701152
|
||||
3
Qwen_Qwen3-VL-4B-Instruct-Q3_K_L.gguf
Normal file
3
Qwen_Qwen3-VL-4B-Instruct-Q3_K_L.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:c63c54c65145523d35bfb9de677a858f43210bf4078137fcbe60c4c6843542dd
|
||||
size 2239786912
|
||||
3
Qwen_Qwen3-VL-4B-Instruct-Q3_K_M.gguf
Normal file
3
Qwen_Qwen3-VL-4B-Instruct-Q3_K_M.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:ed78f134bf3bd0af41c28e8c5d0d92b986653939efdeba3b7ef1435b0d05d702
|
||||
size 2075619232
|
||||
3
Qwen_Qwen3-VL-4B-Instruct-Q3_K_S.gguf
Normal file
3
Qwen_Qwen3-VL-4B-Instruct-Q3_K_S.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:941f4349ad3e8287b80d0c8c2efce50645498389a5f04aa6229f6a4737a8a63c
|
||||
size 1886998432
|
||||
3
Qwen_Qwen3-VL-4B-Instruct-Q3_K_XL.gguf
Normal file
3
Qwen_Qwen3-VL-4B-Instruct-Q3_K_XL.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:f2d13ad473a587c607fcba797b447628abd89a331857a770e70b7317b9c3ff20
|
||||
size 2333987232
|
||||
3
Qwen_Qwen3-VL-4B-Instruct-Q4_0.gguf
Normal file
3
Qwen_Qwen3-VL-4B-Instruct-Q4_0.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:e3cd49fa176a75aa91c01dc1922aec7cbb69d83e6e7b0c954aca3758ad32d094
|
||||
size 2375774112
|
||||
3
Qwen_Qwen3-VL-4B-Instruct-Q4_1.gguf
Normal file
3
Qwen_Qwen3-VL-4B-Instruct-Q4_1.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:a81c365cb27e7456a036029bf766d1786ad956d769d35dc9b6ac7f3e0647c601
|
||||
size 2596630432
|
||||
3
Qwen_Qwen3-VL-4B-Instruct-Q4_K_L.gguf
Normal file
3
Qwen_Qwen3-VL-4B-Instruct-Q4_K_L.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:c8c5bb6f9820af7f66484473b5346ec6535459a4a27b6beaee3332e24e2a02ac
|
||||
size 2591482272
|
||||
3
Qwen_Qwen3-VL-4B-Instruct-Q4_K_M.gguf
Normal file
3
Qwen_Qwen3-VL-4B-Instruct-Q4_K_M.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:ceb08f2fd0bae71733c552d42bd79e08a6335328e295a486b50640a8d573ab51
|
||||
size 2497281952
|
||||
3
Qwen_Qwen3-VL-4B-Instruct-Q4_K_S.gguf
Normal file
3
Qwen_Qwen3-VL-4B-Instruct-Q4_K_S.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:43dfb82b7d14a8894de6fe94cc6a785471270b3d3fe9fcb1b7e3e639ac00838a
|
||||
size 2383310752
|
||||
3
Qwen_Qwen3-VL-4B-Instruct-Q5_K_L.gguf
Normal file
3
Qwen_Qwen3-VL-4B-Instruct-Q5_K_L.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:3b0a2fa4a112e822c447ecfdee51bab84107776f2a159147449c21e7880c257b
|
||||
size 2983715232
|
||||
3
Qwen_Qwen3-VL-4B-Instruct-Q5_K_M.gguf
Normal file
3
Qwen_Qwen3-VL-4B-Instruct-Q5_K_M.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:026ad07482ca4a1121349fbb7b77abf9b81c0cbc156e3cf52ee7bb8d0229cde4
|
||||
size 2889514912
|
||||
3
Qwen_Qwen3-VL-4B-Instruct-Q5_K_S.gguf
Normal file
3
Qwen_Qwen3-VL-4B-Instruct-Q5_K_S.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:b2b2dc55bfa346486e5b75ddedd5c2573d241b2e29175d4470692f1e98813944
|
||||
size 2823712672
|
||||
3
Qwen_Qwen3-VL-4B-Instruct-Q6_K.gguf
Normal file
3
Qwen_Qwen3-VL-4B-Instruct-Q6_K.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:27e3089402499416c730b5e4bc1a6763d0cbd37b4ad33748778c6e1bec0811dd
|
||||
size 3306262432
|
||||
3
Qwen_Qwen3-VL-4B-Instruct-Q6_K_L.gguf
Normal file
3
Qwen_Qwen3-VL-4B-Instruct-Q6_K_L.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:bc49bd3a2e74d3e645f50b924fd63d04b57bf405c8bd82190622b1ce6777bb5a
|
||||
size 3400462752
|
||||
3
Qwen_Qwen3-VL-4B-Instruct-Q8_0.gguf
Normal file
3
Qwen_Qwen3-VL-4B-Instruct-Q8_0.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:e825bf42274cbcdea1d817a3ba1a3066fe9b779a3e9bfad46a396ed9a72e4611
|
||||
size 4280406432
|
||||
3
Qwen_Qwen3-VL-4B-Instruct-bf16.gguf
Normal file
3
Qwen_Qwen3-VL-4B-Instruct-bf16.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:b2ca346f351b2086ba88d2a075610aed5fc33dd1d976fd9cd975cd042b9584ad
|
||||
size 8051286144
|
||||
3
Qwen_Qwen3-VL-4B-Instruct-imatrix.gguf
Normal file
3
Qwen_Qwen3-VL-4B-Instruct-imatrix.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:d51dd4d8c7183c30c334a8493f848fe9f8da39d6c1b282651fdcb0624cec7877
|
||||
size 3872640
|
||||
170
README.md
Normal file
170
README.md
Normal file
@@ -0,0 +1,170 @@
|
||||
---
|
||||
quantized_by: bartowski
|
||||
pipeline_tag: image-text-to-text
|
||||
base_model_relation: quantized
|
||||
base_model: Qwen/Qwen3-VL-4B-Instruct
|
||||
---
|
||||
|
||||
## Llamacpp imatrix Quantizations of Qwen3-VL-4B-Instruct by Qwen
|
||||
|
||||
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/b6888">b6888</a> for quantization.
|
||||
|
||||
Original model: https://huggingface.co/Qwen/Qwen3-VL-4B-Instruct
|
||||
|
||||
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
|
||||
|
||||
```
|
||||
<|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 |
|
||||
| -------- | ---------- | --------- | ----- | ----------- |
|
||||
| [Qwen3-VL-4B-Instruct-bf16.gguf](https://huggingface.co/bartowski/Qwen_Qwen3-VL-4B-Instruct-GGUF/blob/main/Qwen_Qwen3-VL-4B-Instruct-bf16.gguf) | bf16 | 8.05GB | false | Full BF16 weights. |
|
||||
| [Qwen3-VL-4B-Instruct-Q8_0.gguf](https://huggingface.co/bartowski/Qwen_Qwen3-VL-4B-Instruct-GGUF/blob/main/Qwen_Qwen3-VL-4B-Instruct-Q8_0.gguf) | Q8_0 | 4.28GB | false | Extremely high quality, generally unneeded but max available quant. |
|
||||
| [Qwen3-VL-4B-Instruct-Q6_K_L.gguf](https://huggingface.co/bartowski/Qwen_Qwen3-VL-4B-Instruct-GGUF/blob/main/Qwen_Qwen3-VL-4B-Instruct-Q6_K_L.gguf) | Q6_K_L | 3.40GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. |
|
||||
| [Qwen3-VL-4B-Instruct-Q6_K.gguf](https://huggingface.co/bartowski/Qwen_Qwen3-VL-4B-Instruct-GGUF/blob/main/Qwen_Qwen3-VL-4B-Instruct-Q6_K.gguf) | Q6_K | 3.31GB | false | Very high quality, near perfect, *recommended*. |
|
||||
| [Qwen3-VL-4B-Instruct-Q5_K_L.gguf](https://huggingface.co/bartowski/Qwen_Qwen3-VL-4B-Instruct-GGUF/blob/main/Qwen_Qwen3-VL-4B-Instruct-Q5_K_L.gguf) | Q5_K_L | 2.98GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. |
|
||||
| [Qwen3-VL-4B-Instruct-Q5_K_M.gguf](https://huggingface.co/bartowski/Qwen_Qwen3-VL-4B-Instruct-GGUF/blob/main/Qwen_Qwen3-VL-4B-Instruct-Q5_K_M.gguf) | Q5_K_M | 2.89GB | false | High quality, *recommended*. |
|
||||
| [Qwen3-VL-4B-Instruct-Q5_K_S.gguf](https://huggingface.co/bartowski/Qwen_Qwen3-VL-4B-Instruct-GGUF/blob/main/Qwen_Qwen3-VL-4B-Instruct-Q5_K_S.gguf) | Q5_K_S | 2.82GB | false | High quality, *recommended*. |
|
||||
| [Qwen3-VL-4B-Instruct-Q4_1.gguf](https://huggingface.co/bartowski/Qwen_Qwen3-VL-4B-Instruct-GGUF/blob/main/Qwen_Qwen3-VL-4B-Instruct-Q4_1.gguf) | Q4_1 | 2.60GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. |
|
||||
| [Qwen3-VL-4B-Instruct-Q4_K_L.gguf](https://huggingface.co/bartowski/Qwen_Qwen3-VL-4B-Instruct-GGUF/blob/main/Qwen_Qwen3-VL-4B-Instruct-Q4_K_L.gguf) | Q4_K_L | 2.59GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. |
|
||||
| [Qwen3-VL-4B-Instruct-Q4_K_M.gguf](https://huggingface.co/bartowski/Qwen_Qwen3-VL-4B-Instruct-GGUF/blob/main/Qwen_Qwen3-VL-4B-Instruct-Q4_K_M.gguf) | Q4_K_M | 2.50GB | false | Good quality, default size for most use cases, *recommended*. |
|
||||
| [Qwen3-VL-4B-Instruct-Q4_K_S.gguf](https://huggingface.co/bartowski/Qwen_Qwen3-VL-4B-Instruct-GGUF/blob/main/Qwen_Qwen3-VL-4B-Instruct-Q4_K_S.gguf) | Q4_K_S | 2.38GB | false | Slightly lower quality with more space savings, *recommended*. |
|
||||
| [Qwen3-VL-4B-Instruct-Q4_0.gguf](https://huggingface.co/bartowski/Qwen_Qwen3-VL-4B-Instruct-GGUF/blob/main/Qwen_Qwen3-VL-4B-Instruct-Q4_0.gguf) | Q4_0 | 2.38GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. |
|
||||
| [Qwen3-VL-4B-Instruct-IQ4_NL.gguf](https://huggingface.co/bartowski/Qwen_Qwen3-VL-4B-Instruct-GGUF/blob/main/Qwen_Qwen3-VL-4B-Instruct-IQ4_NL.gguf) | IQ4_NL | 2.38GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. |
|
||||
| [Qwen3-VL-4B-Instruct-Q3_K_XL.gguf](https://huggingface.co/bartowski/Qwen_Qwen3-VL-4B-Instruct-GGUF/blob/main/Qwen_Qwen3-VL-4B-Instruct-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. |
|
||||
| [Qwen3-VL-4B-Instruct-IQ4_XS.gguf](https://huggingface.co/bartowski/Qwen_Qwen3-VL-4B-Instruct-GGUF/blob/main/Qwen_Qwen3-VL-4B-Instruct-IQ4_XS.gguf) | IQ4_XS | 2.27GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
|
||||
| [Qwen3-VL-4B-Instruct-Q3_K_L.gguf](https://huggingface.co/bartowski/Qwen_Qwen3-VL-4B-Instruct-GGUF/blob/main/Qwen_Qwen3-VL-4B-Instruct-Q3_K_L.gguf) | Q3_K_L | 2.24GB | false | Lower quality but usable, good for low RAM availability. |
|
||||
| [Qwen3-VL-4B-Instruct-Q3_K_M.gguf](https://huggingface.co/bartowski/Qwen_Qwen3-VL-4B-Instruct-GGUF/blob/main/Qwen_Qwen3-VL-4B-Instruct-Q3_K_M.gguf) | Q3_K_M | 2.08GB | false | Low quality. |
|
||||
| [Qwen3-VL-4B-Instruct-IQ3_M.gguf](https://huggingface.co/bartowski/Qwen_Qwen3-VL-4B-Instruct-GGUF/blob/main/Qwen_Qwen3-VL-4B-Instruct-IQ3_M.gguf) | IQ3_M | 1.96GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
|
||||
| [Qwen3-VL-4B-Instruct-Q3_K_S.gguf](https://huggingface.co/bartowski/Qwen_Qwen3-VL-4B-Instruct-GGUF/blob/main/Qwen_Qwen3-VL-4B-Instruct-Q3_K_S.gguf) | Q3_K_S | 1.89GB | false | Low quality, not recommended. |
|
||||
| [Qwen3-VL-4B-Instruct-IQ3_XS.gguf](https://huggingface.co/bartowski/Qwen_Qwen3-VL-4B-Instruct-GGUF/blob/main/Qwen_Qwen3-VL-4B-Instruct-IQ3_XS.gguf) | IQ3_XS | 1.81GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
|
||||
| [Qwen3-VL-4B-Instruct-Q2_K_L.gguf](https://huggingface.co/bartowski/Qwen_Qwen3-VL-4B-Instruct-GGUF/blob/main/Qwen_Qwen3-VL-4B-Instruct-Q2_K_L.gguf) | Q2_K_L | 1.76GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. |
|
||||
| [Qwen3-VL-4B-Instruct-IQ3_XXS.gguf](https://huggingface.co/bartowski/Qwen_Qwen3-VL-4B-Instruct-GGUF/blob/main/Qwen_Qwen3-VL-4B-Instruct-IQ3_XXS.gguf) | IQ3_XXS | 1.67GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. |
|
||||
| [Qwen3-VL-4B-Instruct-Q2_K.gguf](https://huggingface.co/bartowski/Qwen_Qwen3-VL-4B-Instruct-GGUF/blob/main/Qwen_Qwen3-VL-4B-Instruct-Q2_K.gguf) | Q2_K | 1.67GB | false | Very low quality but surprisingly usable. |
|
||||
| [Qwen3-VL-4B-Instruct-IQ2_M.gguf](https://huggingface.co/bartowski/Qwen_Qwen3-VL-4B-Instruct-GGUF/blob/main/Qwen_Qwen3-VL-4B-Instruct-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/Qwen_Qwen3-VL-4B-Instruct-GGUF --include "Qwen_Qwen3-VL-4B-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/Qwen_Qwen3-VL-4B-Instruct-GGUF --include "Qwen_Qwen3-VL-4B-Instruct-Q8_0/*" --local-dir ./
|
||||
```
|
||||
|
||||
You can either specify a new local-dir (Qwen_Qwen3-VL-4B-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/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
|
||||
3
mmproj-Qwen_Qwen3-VL-4B-Instruct-bf16.gguf
Normal file
3
mmproj-Qwen_Qwen3-VL-4B-Instruct-bf16.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:f8178bbf582305017843c53396cc5e0ed0b867855f25e0b15ae48311cc379f08
|
||||
size 839325984
|
||||
3
mmproj-Qwen_Qwen3-VL-4B-Instruct-f16.gguf
Normal file
3
mmproj-Qwen_Qwen3-VL-4B-Instruct-f16.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:5d5e698305f6e092c682d3e8e8deb1db88915e69a7dd66c0279e7ce810bfee48
|
||||
size 836180256
|
||||
Reference in New Issue
Block a user