初始化项目，由ModelHub XC社区提供模型
Model: bartowski/OpenGVLab_InternVL3_5-4B-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
|
||||||
|
OpenGVLab_InternVL3_5-4B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
||||||
|
OpenGVLab_InternVL3_5-4B-Q6_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
||||||
|
OpenGVLab_InternVL3_5-4B-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
||||||
|
OpenGVLab_InternVL3_5-4B-Q5_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
||||||
|
OpenGVLab_InternVL3_5-4B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||||
|
OpenGVLab_InternVL3_5-4B-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
||||||
|
OpenGVLab_InternVL3_5-4B-Q4_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
||||||
|
OpenGVLab_InternVL3_5-4B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||||
|
OpenGVLab_InternVL3_5-4B-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
||||||
|
OpenGVLab_InternVL3_5-4B-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text
|
||||||
|
OpenGVLab_InternVL3_5-4B-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
||||||
|
OpenGVLab_InternVL3_5-4B-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text
|
||||||
|
OpenGVLab_InternVL3_5-4B-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
|
||||||
|
OpenGVLab_InternVL3_5-4B-Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
|
||||||
|
OpenGVLab_InternVL3_5-4B-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
||||||
|
OpenGVLab_InternVL3_5-4B-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||||
|
OpenGVLab_InternVL3_5-4B-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||||
|
OpenGVLab_InternVL3_5-4B-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
||||||
|
OpenGVLab_InternVL3_5-4B-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
|
||||||
|
OpenGVLab_InternVL3_5-4B-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text
|
||||||
|
OpenGVLab_InternVL3_5-4B-Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
||||||
|
OpenGVLab_InternVL3_5-4B-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
||||||
|
OpenGVLab_InternVL3_5-4B-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||||
|
OpenGVLab_InternVL3_5-4B-bf16.gguf filter=lfs diff=lfs merge=lfs -text
|
||||||
|
OpenGVLab_InternVL3_5-4B-imatrix.gguf filter=lfs diff=lfs merge=lfs -text
|
||||||
|
mmproj-OpenGVLab_InternVL3_5-4B-f16.gguf filter=lfs diff=lfs merge=lfs -text
|
||||||
|
mmproj-OpenGVLab_InternVL3_5-4B-bf16.gguf filter=lfs diff=lfs merge=lfs -text
|
||||||
3
OpenGVLab_InternVL3_5-4B-IQ2_M.gguf
Normal file
3
OpenGVLab_InternVL3_5-4B-IQ2_M.gguf
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:bf127546725e5514c70f3f75671dedc5cfc4389f08bacb37197d49cace632404
|
||||||
|
size 1680110272
|
||||||
3
OpenGVLab_InternVL3_5-4B-IQ3_M.gguf
Normal file
3
OpenGVLab_InternVL3_5-4B-IQ3_M.gguf
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:3fb94a495c4aaf43b0310fcbd3e8fe85a488e07f1542d5ca8b913f21080ad6b4
|
||||||
|
size 2130022592
|
||||||
3
OpenGVLab_InternVL3_5-4B-IQ3_XS.gguf
Normal file
3
OpenGVLab_InternVL3_5-4B-IQ3_XS.gguf
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:aa39f972adfef041143506b1e5b465b52d8a00027cd7f2bd9a07d09cd8d892ce
|
||||||
|
size 1981501632
|
||||||
3
OpenGVLab_InternVL3_5-4B-IQ3_XXS.gguf
Normal file
3
OpenGVLab_InternVL3_5-4B-IQ3_XXS.gguf
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:ce461603aa42bdf8f53338d715c326d6bc0fee19f6d530cca1ae6561ba1dba6c
|
||||||
|
size 1837314752
|
||||||
3
OpenGVLab_InternVL3_5-4B-IQ4_NL.gguf
Normal file
3
OpenGVLab_InternVL3_5-4B-IQ4_NL.gguf
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:739f16dac7e7f05f620432bf8d495797843302d145fe94c2e9361a1a825065fe
|
||||||
|
size 2600128192
|
||||||
3
OpenGVLab_InternVL3_5-4B-IQ4_XS.gguf
Normal file
3
OpenGVLab_InternVL3_5-4B-IQ4_XS.gguf
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:6a4b93b338ec2ef737a968a65f4b9ff6f20604d24f6feb8d139fc180330e0f03
|
||||||
|
size 2477381312
|
||||||
3
OpenGVLab_InternVL3_5-4B-Q2_K.gguf
Normal file
3
OpenGVLab_InternVL3_5-4B-Q2_K.gguf
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:aa5cb96774e811bdc67a13f42d00e1ab5487993a964dcfa58766d299f0319fbc
|
||||||
|
size 1797122752
|
||||||
3
OpenGVLab_InternVL3_5-4B-Q2_K_L.gguf
Normal file
3
OpenGVLab_InternVL3_5-4B-Q2_K_L.gguf
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:42be0fef12262a4f33bb554c9f725f1cd60ff9681671b1f57174dfff0476e49b
|
||||||
|
size 2176962752
|
||||||
3
OpenGVLab_InternVL3_5-4B-Q3_K_L.gguf
Normal file
3
OpenGVLab_InternVL3_5-4B-Q3_K_L.gguf
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:1153547dc5d7e68f9b5bf574dda342fedab3d5b964f4c90fb3be4bc0c3246967
|
||||||
|
size 2406912192
|
||||||
3
OpenGVLab_InternVL3_5-4B-Q3_K_M.gguf
Normal file
3
OpenGVLab_InternVL3_5-4B-Q3_K_M.gguf
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:05c42d941c43082bf8a4d42e0ae9d347f7a499ca42996237314f24f0904d2896
|
||||||
|
size 2242744512
|
||||||
3
OpenGVLab_InternVL3_5-4B-Q3_K_S.gguf
Normal file
3
OpenGVLab_InternVL3_5-4B-Q3_K_S.gguf
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:2a541f59081cd34e339b97a6961e14e98e62b698796b456ca933c33934e82b5d
|
||||||
|
size 2054123712
|
||||||
3
OpenGVLab_InternVL3_5-4B-Q3_K_XL.gguf
Normal file
3
OpenGVLab_InternVL3_5-4B-Q3_K_XL.gguf
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:1c57fac71f6a2ce1540449e14de38293daec6d218ba84fa274cce06ad1934454
|
||||||
|
size 2747248832
|
||||||
3
OpenGVLab_InternVL3_5-4B-Q4_0.gguf
Normal file
3
OpenGVLab_InternVL3_5-4B-Q4_0.gguf
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:eb10e53ae463d0d0e54b666aefefce35293d1b7696dcecf12c546c0d0c021337
|
||||||
|
size 2594557632
|
||||||
3
OpenGVLab_InternVL3_5-4B-Q4_1.gguf
Normal file
3
OpenGVLab_InternVL3_5-4B-Q4_1.gguf
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:7330efa1818892af481c6a9cb0b279a9d90ff8f24fcb9522072a8c6e76032aa3
|
||||||
|
size 2839723712
|
||||||
3
OpenGVLab_InternVL3_5-4B-Q4_K_L.gguf
Normal file
3
OpenGVLab_InternVL3_5-4B-Q4_K_L.gguf
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:afa6b06307244f651ebdb2eb527cc85580161d7d0f65e1726e502c6324809d35
|
||||||
|
size 3004743872
|
||||||
3
OpenGVLab_InternVL3_5-4B-Q4_K_M.gguf
Normal file
3
OpenGVLab_InternVL3_5-4B-Q4_K_M.gguf
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:7c1612b6896ad14caa501238e72afa17a600651d0984225e3ff78b39de86099c
|
||||||
|
size 2716065472
|
||||||
3
OpenGVLab_InternVL3_5-4B-Q4_K_S.gguf
Normal file
3
OpenGVLab_InternVL3_5-4B-Q4_K_S.gguf
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:c6b2918021b959a51b6a76a42b2c262903f477082d57eec8c8effaf61ca57a7b
|
||||||
|
size 2602094272
|
||||||
3
OpenGVLab_InternVL3_5-4B-Q5_K_L.gguf
Normal file
3
OpenGVLab_InternVL3_5-4B-Q5_K_L.gguf
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:edc1dc20d9a674c228139238e60840896b5494d05372d70ee1086e3a2bd3962e
|
||||||
|
size 3396976832
|
||||||
3
OpenGVLab_InternVL3_5-4B-Q5_K_M.gguf
Normal file
3
OpenGVLab_InternVL3_5-4B-Q5_K_M.gguf
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:cc820484268ac0060471787e882f159af15f30952dc7adfadc04f08996bc8af4
|
||||||
|
size 3156917952
|
||||||
3
OpenGVLab_InternVL3_5-4B-Q5_K_S.gguf
Normal file
3
OpenGVLab_InternVL3_5-4B-Q5_K_S.gguf
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:65e21353eb29293d9c4d752db84ba3eaefe6e0e0df3ef2bad7d976079b21b68f
|
||||||
|
size 3091115712
|
||||||
3
OpenGVLab_InternVL3_5-4B-Q6_K.gguf
Normal file
3
OpenGVLab_InternVL3_5-4B-Q6_K.gguf
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:a9d3fac3267f214152762bc74911808b34e1c60c24b4c63d3b76ac1e1dbebbb4
|
||||||
|
size 3625323712
|
||||||
3
OpenGVLab_InternVL3_5-4B-Q6_K_L.gguf
Normal file
3
OpenGVLab_InternVL3_5-4B-Q6_K_L.gguf
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:157ad29bf7c7a9fa5ea778e207e77e21a12e1644231822741aae3c01604b77f2
|
||||||
|
size 3813724352
|
||||||
3
OpenGVLab_InternVL3_5-4B-Q8_0.gguf
Normal file
3
OpenGVLab_InternVL3_5-4B-Q8_0.gguf
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:ece87031e20486b1a4b86a0ba0f06b8b3b6eed676c8c6842e31041524489992d
|
||||||
|
size 4693668032
|
||||||
3
OpenGVLab_InternVL3_5-4B-bf16.gguf
Normal file
3
OpenGVLab_InternVL3_5-4B-bf16.gguf
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:161ff4491525e55d64ef9191b7226566f74e03c848aed0eb0a39d39aea9a63f0
|
||||||
|
size 8829194144
|
||||||
3
OpenGVLab_InternVL3_5-4B-imatrix.gguf
Normal file
3
OpenGVLab_InternVL3_5-4B-imatrix.gguf
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:0a967cf43c649250cfa2c5dfc0653abd7bc39ae3862562f32adf4245b82834e3
|
||||||
|
size 3872640
|
||||||
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: OpenGVLab/InternVL3_5-4B
|
||||||
|
base_model_relation: quantized
|
||||||
|
---
|
||||||
|
|
||||||
|
## Llamacpp imatrix Quantizations of InternVL3_5-4B by OpenGVLab
|
||||||
|
|
||||||
|
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/b6258">b6258</a> for quantization.
|
||||||
|
|
||||||
|
Original model: https://huggingface.co/OpenGVLab/InternVL3_5-4B
|
||||||
|
|
||||||
|
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 |
|
||||||
|
| -------- | ---------- | --------- | ----- | ----------- |
|
||||||
|
| [InternVL3_5-4B-bf16.gguf](https://huggingface.co/bartowski/OpenGVLab_InternVL3_5-4B-GGUF/blob/main/OpenGVLab_InternVL3_5-4B-bf16.gguf) | bf16 | 8.83GB | false | Full BF16 weights. |
|
||||||
|
| [InternVL3_5-4B-Q8_0.gguf](https://huggingface.co/bartowski/OpenGVLab_InternVL3_5-4B-GGUF/blob/main/OpenGVLab_InternVL3_5-4B-Q8_0.gguf) | Q8_0 | 4.69GB | false | Extremely high quality, generally unneeded but max available quant. |
|
||||||
|
| [InternVL3_5-4B-Q6_K_L.gguf](https://huggingface.co/bartowski/OpenGVLab_InternVL3_5-4B-GGUF/blob/main/OpenGVLab_InternVL3_5-4B-Q6_K_L.gguf) | Q6_K_L | 3.81GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. |
|
||||||
|
| [InternVL3_5-4B-Q6_K.gguf](https://huggingface.co/bartowski/OpenGVLab_InternVL3_5-4B-GGUF/blob/main/OpenGVLab_InternVL3_5-4B-Q6_K.gguf) | Q6_K | 3.63GB | false | Very high quality, near perfect, *recommended*. |
|
||||||
|
| [InternVL3_5-4B-Q5_K_L.gguf](https://huggingface.co/bartowski/OpenGVLab_InternVL3_5-4B-GGUF/blob/main/OpenGVLab_InternVL3_5-4B-Q5_K_L.gguf) | Q5_K_L | 3.40GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. |
|
||||||
|
| [InternVL3_5-4B-Q5_K_M.gguf](https://huggingface.co/bartowski/OpenGVLab_InternVL3_5-4B-GGUF/blob/main/OpenGVLab_InternVL3_5-4B-Q5_K_M.gguf) | Q5_K_M | 3.16GB | false | High quality, *recommended*. |
|
||||||
|
| [InternVL3_5-4B-Q5_K_S.gguf](https://huggingface.co/bartowski/OpenGVLab_InternVL3_5-4B-GGUF/blob/main/OpenGVLab_InternVL3_5-4B-Q5_K_S.gguf) | Q5_K_S | 3.09GB | false | High quality, *recommended*. |
|
||||||
|
| [InternVL3_5-4B-Q4_K_L.gguf](https://huggingface.co/bartowski/OpenGVLab_InternVL3_5-4B-GGUF/blob/main/OpenGVLab_InternVL3_5-4B-Q4_K_L.gguf) | Q4_K_L | 3.00GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. |
|
||||||
|
| [InternVL3_5-4B-Q4_1.gguf](https://huggingface.co/bartowski/OpenGVLab_InternVL3_5-4B-GGUF/blob/main/OpenGVLab_InternVL3_5-4B-Q4_1.gguf) | Q4_1 | 2.84GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. |
|
||||||
|
| [InternVL3_5-4B-Q3_K_XL.gguf](https://huggingface.co/bartowski/OpenGVLab_InternVL3_5-4B-GGUF/blob/main/OpenGVLab_InternVL3_5-4B-Q3_K_XL.gguf) | Q3_K_XL | 2.75GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. |
|
||||||
|
| [InternVL3_5-4B-Q4_K_M.gguf](https://huggingface.co/bartowski/OpenGVLab_InternVL3_5-4B-GGUF/blob/main/OpenGVLab_InternVL3_5-4B-Q4_K_M.gguf) | Q4_K_M | 2.72GB | false | Good quality, default size for most use cases, *recommended*. |
|
||||||
|
| [InternVL3_5-4B-Q4_K_S.gguf](https://huggingface.co/bartowski/OpenGVLab_InternVL3_5-4B-GGUF/blob/main/OpenGVLab_InternVL3_5-4B-Q4_K_S.gguf) | Q4_K_S | 2.60GB | false | Slightly lower quality with more space savings, *recommended*. |
|
||||||
|
| [InternVL3_5-4B-IQ4_NL.gguf](https://huggingface.co/bartowski/OpenGVLab_InternVL3_5-4B-GGUF/blob/main/OpenGVLab_InternVL3_5-4B-IQ4_NL.gguf) | IQ4_NL | 2.60GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. |
|
||||||
|
| [InternVL3_5-4B-Q4_0.gguf](https://huggingface.co/bartowski/OpenGVLab_InternVL3_5-4B-GGUF/blob/main/OpenGVLab_InternVL3_5-4B-Q4_0.gguf) | Q4_0 | 2.59GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. |
|
||||||
|
| [InternVL3_5-4B-IQ4_XS.gguf](https://huggingface.co/bartowski/OpenGVLab_InternVL3_5-4B-GGUF/blob/main/OpenGVLab_InternVL3_5-4B-IQ4_XS.gguf) | IQ4_XS | 2.48GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
|
||||||
|
| [InternVL3_5-4B-Q3_K_L.gguf](https://huggingface.co/bartowski/OpenGVLab_InternVL3_5-4B-GGUF/blob/main/OpenGVLab_InternVL3_5-4B-Q3_K_L.gguf) | Q3_K_L | 2.41GB | false | Lower quality but usable, good for low RAM availability. |
|
||||||
|
| [InternVL3_5-4B-Q3_K_M.gguf](https://huggingface.co/bartowski/OpenGVLab_InternVL3_5-4B-GGUF/blob/main/OpenGVLab_InternVL3_5-4B-Q3_K_M.gguf) | Q3_K_M | 2.24GB | false | Low quality. |
|
||||||
|
| [InternVL3_5-4B-Q2_K_L.gguf](https://huggingface.co/bartowski/OpenGVLab_InternVL3_5-4B-GGUF/blob/main/OpenGVLab_InternVL3_5-4B-Q2_K_L.gguf) | Q2_K_L | 2.18GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. |
|
||||||
|
| [InternVL3_5-4B-IQ3_M.gguf](https://huggingface.co/bartowski/OpenGVLab_InternVL3_5-4B-GGUF/blob/main/OpenGVLab_InternVL3_5-4B-IQ3_M.gguf) | IQ3_M | 2.13GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
|
||||||
|
| [InternVL3_5-4B-Q3_K_S.gguf](https://huggingface.co/bartowski/OpenGVLab_InternVL3_5-4B-GGUF/blob/main/OpenGVLab_InternVL3_5-4B-Q3_K_S.gguf) | Q3_K_S | 2.05GB | false | Low quality, not recommended. |
|
||||||
|
| [InternVL3_5-4B-IQ3_XS.gguf](https://huggingface.co/bartowski/OpenGVLab_InternVL3_5-4B-GGUF/blob/main/OpenGVLab_InternVL3_5-4B-IQ3_XS.gguf) | IQ3_XS | 1.98GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
|
||||||
|
| [InternVL3_5-4B-IQ3_XXS.gguf](https://huggingface.co/bartowski/OpenGVLab_InternVL3_5-4B-GGUF/blob/main/OpenGVLab_InternVL3_5-4B-IQ3_XXS.gguf) | IQ3_XXS | 1.84GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. |
|
||||||
|
| [InternVL3_5-4B-Q2_K.gguf](https://huggingface.co/bartowski/OpenGVLab_InternVL3_5-4B-GGUF/blob/main/OpenGVLab_InternVL3_5-4B-Q2_K.gguf) | Q2_K | 1.80GB | false | Very low quality but surprisingly usable. |
|
||||||
|
| [InternVL3_5-4B-IQ2_M.gguf](https://huggingface.co/bartowski/OpenGVLab_InternVL3_5-4B-GGUF/blob/main/OpenGVLab_InternVL3_5-4B-IQ2_M.gguf) | IQ2_M | 1.68GB | 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/OpenGVLab_InternVL3_5-4B-GGUF --include "OpenGVLab_InternVL3_5-4B-Q4_K_M.gguf" --local-dir ./
|
||||||
|
```
|
||||||
|
|
||||||
|
If the model is bigger than 50GB, it will have been split into multiple files. In order to download them all to a local folder, run:
|
||||||
|
|
||||||
|
```
|
||||||
|
huggingface-cli download bartowski/OpenGVLab_InternVL3_5-4B-GGUF --include "OpenGVLab_InternVL3_5-4B-Q8_0/*" --local-dir ./
|
||||||
|
```
|
||||||
|
|
||||||
|
You can either specify a new local-dir (OpenGVLab_InternVL3_5-4B-Q8_0) or download them all in place (./)
|
||||||
|
|
||||||
|
</details>
|
||||||
|
|
||||||
|
## ARM/AVX information
|
||||||
|
|
||||||
|
Previously, you would download Q4_0_4_4/4_8/8_8, and these would have their weights interleaved in memory in order to improve performance on ARM and AVX machines by loading up more data in one pass.
|
||||||
|
|
||||||
|
Now, however, there is something called "online repacking" for weights. details in [this PR](https://github.com/ggml-org/llama.cpp/pull/9921). If you use Q4_0 and your hardware would benefit from repacking weights, it will do it automatically on the fly.
|
||||||
|
|
||||||
|
As of llama.cpp build [b4282](https://github.com/ggml-org/llama.cpp/releases/tag/b4282) you will not be able to run the Q4_0_X_X files and will instead need to use Q4_0.
|
||||||
|
|
||||||
|
Additionally, if you want to get slightly better quality for , you can use IQ4_NL thanks to [this PR](https://github.com/ggml-org/llama.cpp/pull/10541) which will also repack the weights for ARM, though only the 4_4 for now. The loading time may be slower but it will result in an overall speed incrase.
|
||||||
|
|
||||||
|
<details>
|
||||||
|
<summary>Click to view Q4_0_X_X information (deprecated</summary>
|
||||||
|
|
||||||
|
I'm keeping this section to show the potential theoretical uplift in performance from using the Q4_0 with online repacking.
|
||||||
|
|
||||||
|
<details>
|
||||||
|
<summary>Click to view benchmarks on an AVX2 system (EPYC7702)</summary>
|
||||||
|
|
||||||
|
| model | size | params | backend | threads | test | t/s | % (vs Q4_0) |
|
||||||
|
| ------------------------------ | ---------: | ---------: | ---------- | ------: | ------------: | -------------------: |-------------: |
|
||||||
|
| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | pp512 | 204.03 ± 1.03 | 100% |
|
||||||
|
| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | pp1024 | 282.92 ± 0.19 | 100% |
|
||||||
|
| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | pp2048 | 259.49 ± 0.44 | 100% |
|
||||||
|
| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | tg128 | 39.12 ± 0.27 | 100% |
|
||||||
|
| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | tg256 | 39.31 ± 0.69 | 100% |
|
||||||
|
| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | tg512 | 40.52 ± 0.03 | 100% |
|
||||||
|
| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | pp512 | 301.02 ± 1.74 | 147% |
|
||||||
|
| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | pp1024 | 287.23 ± 0.20 | 101% |
|
||||||
|
| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | pp2048 | 262.77 ± 1.81 | 101% |
|
||||||
|
| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | tg128 | 18.80 ± 0.99 | 48% |
|
||||||
|
| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | tg256 | 24.46 ± 3.04 | 83% |
|
||||||
|
| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | tg512 | 36.32 ± 3.59 | 90% |
|
||||||
|
| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | pp512 | 271.71 ± 3.53 | 133% |
|
||||||
|
| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | pp1024 | 279.86 ± 45.63 | 100% |
|
||||||
|
| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | pp2048 | 320.77 ± 5.00 | 124% |
|
||||||
|
| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | tg128 | 43.51 ± 0.05 | 111% |
|
||||||
|
| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | tg256 | 43.35 ± 0.09 | 110% |
|
||||||
|
| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | tg512 | 42.60 ± 0.31 | 105% |
|
||||||
|
|
||||||
|
Q4_0_8_8 offers a nice bump to prompt processing and a small bump to text generation
|
||||||
|
|
||||||
|
</details>
|
||||||
|
|
||||||
|
</details>
|
||||||
|
|
||||||
|
## Which file should I choose?
|
||||||
|
|
||||||
|
<details>
|
||||||
|
<summary>Click here for details</summary>
|
||||||
|
|
||||||
|
A great write up with charts showing various performances is provided by Artefact2 [here](https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9)
|
||||||
|
|
||||||
|
The first thing to figure out is how big a model you can run. To do this, you'll need to figure out how much RAM and/or VRAM you have.
|
||||||
|
|
||||||
|
If you want your model running as FAST as possible, you'll want to fit the whole thing on your GPU's VRAM. Aim for a quant with a file size 1-2GB smaller than your GPU's total VRAM.
|
||||||
|
|
||||||
|
If you want the absolute maximum quality, add both your system RAM and your GPU's VRAM together, then similarly grab a quant with a file size 1-2GB Smaller than that total.
|
||||||
|
|
||||||
|
Next, you'll need to decide if you want to use an 'I-quant' or a 'K-quant'.
|
||||||
|
|
||||||
|
If you don't want to think too much, grab one of the K-quants. These are in format 'QX_K_X', like Q5_K_M.
|
||||||
|
|
||||||
|
If you want to get more into the weeds, you can check out this extremely useful feature chart:
|
||||||
|
|
||||||
|
[llama.cpp feature matrix](https://github.com/ggml-org/llama.cpp/wiki/Feature-matrix)
|
||||||
|
|
||||||
|
But basically, if you're aiming for below Q4, and you're running cuBLAS (Nvidia) or rocBLAS (AMD), you should look towards the I-quants. These are in format IQX_X, like IQ3_M. These are newer and offer better performance for their size.
|
||||||
|
|
||||||
|
These I-quants can also be used on CPU, but will be slower than their K-quant equivalent, so speed vs performance is a tradeoff you'll have to decide.
|
||||||
|
|
||||||
|
</details>
|
||||||
|
|
||||||
|
## Credits
|
||||||
|
|
||||||
|
Thank you kalomaze and Dampf for assistance in creating the imatrix calibration dataset.
|
||||||
|
|
||||||
|
Thank you ZeroWw for the inspiration to experiment with embed/output.
|
||||||
|
|
||||||
|
Thank you to LM Studio for sponsoring my work.
|
||||||
|
|
||||||
|
Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski
|
||||||
3
mmproj-OpenGVLab_InternVL3_5-4B-bf16.gguf
Normal file
3
mmproj-OpenGVLab_InternVL3_5-4B-bf16.gguf
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:c697d9fb3090cde25cd3c24c1cfad6970ef823e6f3fd072174200034f667d143
|
||||||
|
size 646227360
|
||||||
3
mmproj-OpenGVLab_InternVL3_5-4B-f16.gguf
Normal file
3
mmproj-OpenGVLab_InternVL3_5-4B-f16.gguf
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:0f9704972fcb9cb0a4f2c0f4eb7fe4f58e53ccd4b06ec17cf7a80271aa963eb7
|
||||||
|
size 645023136
|
||||||
Reference in New Issue
Block a user