bartowski/OpenGVLab_InternVL3_5-2B-GGUF
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: bartowski/OpenGVLab_InternVL3_5-2B-GGUF
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-16 05:52:29 +08:00
commit 2192860328
29 changed files with 307 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

62
.gitattributes vendored Normal file
View 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_5-2B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
OpenGVLab_InternVL3_5-2B-Q6_K_L.gguf filter=lfs diff=lfs merge=lfs -text
OpenGVLab_InternVL3_5-2B-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
OpenGVLab_InternVL3_5-2B-Q5_K_L.gguf filter=lfs diff=lfs merge=lfs -text
OpenGVLab_InternVL3_5-2B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
OpenGVLab_InternVL3_5-2B-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
OpenGVLab_InternVL3_5-2B-Q4_K_L.gguf filter=lfs diff=lfs merge=lfs -text
OpenGVLab_InternVL3_5-2B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
OpenGVLab_InternVL3_5-2B-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
OpenGVLab_InternVL3_5-2B-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text
OpenGVLab_InternVL3_5-2B-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
OpenGVLab_InternVL3_5-2B-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text
OpenGVLab_InternVL3_5-2B-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
OpenGVLab_InternVL3_5-2B-Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
OpenGVLab_InternVL3_5-2B-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
OpenGVLab_InternVL3_5-2B-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
OpenGVLab_InternVL3_5-2B-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
OpenGVLab_InternVL3_5-2B-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
OpenGVLab_InternVL3_5-2B-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
OpenGVLab_InternVL3_5-2B-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text
OpenGVLab_InternVL3_5-2B-Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text
OpenGVLab_InternVL3_5-2B-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
OpenGVLab_InternVL3_5-2B-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text
OpenGVLab_InternVL3_5-2B-bf16.gguf filter=lfs diff=lfs merge=lfs -text
OpenGVLab_InternVL3_5-2B-imatrix.gguf filter=lfs diff=lfs merge=lfs -text
mmproj-OpenGVLab_InternVL3_5-2B-f16.gguf filter=lfs diff=lfs merge=lfs -text
mmproj-OpenGVLab_InternVL3_5-2B-bf16.gguf filter=lfs diff=lfs merge=lfs -text

3
OpenGVLab_InternVL3_5-2B-IQ2_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:54cbcfb2c8cd74c9cb099698a91e0ae3a6fbf6a318bf7d750b06fe448021c7e5
size 828882016

3
OpenGVLab_InternVL3_5-2B-IQ3_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2407bf211b26e08f9b8286673e4bdbef7a1198b279d77a2b261bf751bd7d4539
size 1029362784

3
OpenGVLab_InternVL3_5-2B-IQ3_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e62f90aa68104a2b693edf1e1a97c43f1bc91ed15a0663585045f6db68e47ec0
size 967922784

3
OpenGVLab_InternVL3_5-2B-IQ3_XXS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:6a38a023cd4631282fa2580b2d1e9f13b948f24dfb74d30176343edc71dec3b5
size 888061024

3
OpenGVLab_InternVL3_5-2B-IQ4_NL.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1d1a441cb41455a1f7ef9b2a67c6d8513a64651a7c9815ea51b51336f5c89a0b
size 1229450336

3
OpenGVLab_InternVL3_5-2B-IQ4_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d423514c9bef006ad1fbb24b104b9d4ebe8035f608f8b1d834175d351ee3bef7
size 1175686240

3
OpenGVLab_InternVL3_5-2B-Q2_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:da5ad8e26dcffa91fd835ba5c6ecfe456deaddf820c7e77b5749a965c487c244
size 879893600

3
OpenGVLab_InternVL3_5-2B-Q2_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:20584b15846582ef678f5a1fe837c6fd09c7baf23a08dc3612e4f541869d6319
size 1183765600

3
OpenGVLab_InternVL3_5-2B-Q3_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0f01c4ccb3d3bfee010f8dbcd81c44514af340c99e636f6f94632f8ff2bea1cc
size 1137202272

3
OpenGVLab_InternVL3_5-2B-Q3_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b4294da1cb43d2baf137c374f68d04aba2782358c9fbda5b38ffe1d6cd663333
size 1073239136

3
OpenGVLab_InternVL3_5-2B-Q3_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c1743405157b8adf2a3249a5847b6fb182dc4c2ab0376645ee95f2466329868d
size 1000952928

3
OpenGVLab_InternVL3_5-2B-Q3_K_XL.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:991f6bc19ea578ebe8dae0a18b826c7eb16b111e863abf5b2367a168f2d8b2d0
size 1409471584

3
OpenGVLab_InternVL3_5-2B-Q4_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:fcf353755941aa8598d807e2b3f4613be6dca2fc4cd78235c1f95da1113045de
size 1231809632

3
OpenGVLab_InternVL3_5-2B-Q4_1.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a735d4df0b2a6adf06a55f3cdcecbfadb6c6f1383658f4452a64983ba72eba7c
size 1336978528

3
OpenGVLab_InternVL3_5-2B-Q4_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:55d4d0b5b7360ac8a0605e618ccc614188519523b40542f1ec9642c9c759cdfa
size 1513378912

3
OpenGVLab_InternVL3_5-2B-Q4_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1a3605d32ecc4464ccd8451414fc9458a4b6cd12232d8ba6762af91c2dc897e0
size 1282436192

3
OpenGVLab_InternVL3_5-2B-Q4_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0c01534ee916f727b0fa6bf2752045415949718284931872fb6e93b542f373fe
size 1235217504

3
OpenGVLab_InternVL3_5-2B-Q5_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:fbdc2919122f517ab92b03abb6780ef25c911cf1111decfb98b5b10932221a14
size 1663849568

3
OpenGVLab_InternVL3_5-2B-Q5_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b2ca2701bd867bded93a947f8a2d415ed466d58a33d09a97cfa0bf981ab94d17
size 1471802464

3
OpenGVLab_InternVL3_5-2B-Q5_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:53ac3a9e72c939e7dca32b6c82694f94fbc144364453b5ecd3b99e497b6d557a
size 1444506720

3
OpenGVLab_InternVL3_5-2B-Q6_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:016fe056fe65425cc6eec74a07d16144100ffb90455fee52080df0a69edc95ea
size 1673004128

3
OpenGVLab_InternVL3_5-2B-Q6_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0ec9b0d7422cfe35798559c06fc5f9bcb6ebc09b2936b96d157f6ee601141983
size 1823724640

3
OpenGVLab_InternVL3_5-2B-Q8_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:6997c6e3a1fe5920ac1429a21a3ec15d545e14eb695ee3656834859e617800b5
size 2165036128

3
OpenGVLab_InternVL3_5-2B-bf16.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c52cd755735fb06538f1ecb87fe0540a48a3c38c73aeb98032e2228589537e86
size 4069675840

3
OpenGVLab_InternVL3_5-2B-imatrix.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:fa5a0ab4ca6b02bd847e61d6e7de763446ecb6698b1a16ce1660ee5592b36cad
size 2094560

164
README.md Normal file
View File

@@ -0,0 +1,164 @@
---
quantized_by: bartowski
pipeline_tag: image-text-to-text
base_model: OpenGVLab/InternVL3_5-2B
base_model_relation: quantized
---
## Llamacpp imatrix Quantizations of InternVL3_5-2B 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_5-2B
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_5-2B-bf16.gguf](https://huggingface.co/bartowski/OpenGVLab_InternVL3_5-2B-GGUF/blob/main/OpenGVLab_InternVL3_5-2B-bf16.gguf) | bf16 | 4.07GB | false | Full BF16 weights. |
| [InternVL3_5-2B-Q8_0.gguf](https://huggingface.co/bartowski/OpenGVLab_InternVL3_5-2B-GGUF/blob/main/OpenGVLab_InternVL3_5-2B-Q8_0.gguf) | Q8_0 | 2.17GB | false | Extremely high quality, generally unneeded but max available quant. |
| [InternVL3_5-2B-Q6_K_L.gguf](https://huggingface.co/bartowski/OpenGVLab_InternVL3_5-2B-GGUF/blob/main/OpenGVLab_InternVL3_5-2B-Q6_K_L.gguf) | Q6_K_L | 1.82GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. |
| [InternVL3_5-2B-Q6_K.gguf](https://huggingface.co/bartowski/OpenGVLab_InternVL3_5-2B-GGUF/blob/main/OpenGVLab_InternVL3_5-2B-Q6_K.gguf) | Q6_K | 1.67GB | false | Very high quality, near perfect, *recommended*. |
| [InternVL3_5-2B-Q5_K_L.gguf](https://huggingface.co/bartowski/OpenGVLab_InternVL3_5-2B-GGUF/blob/main/OpenGVLab_InternVL3_5-2B-Q5_K_L.gguf) | Q5_K_L | 1.66GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. |
| [InternVL3_5-2B-Q4_K_L.gguf](https://huggingface.co/bartowski/OpenGVLab_InternVL3_5-2B-GGUF/blob/main/OpenGVLab_InternVL3_5-2B-Q4_K_L.gguf) | Q4_K_L | 1.51GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. |
| [InternVL3_5-2B-Q5_K_M.gguf](https://huggingface.co/bartowski/OpenGVLab_InternVL3_5-2B-GGUF/blob/main/OpenGVLab_InternVL3_5-2B-Q5_K_M.gguf) | Q5_K_M | 1.47GB | false | High quality, *recommended*. |
| [InternVL3_5-2B-Q5_K_S.gguf](https://huggingface.co/bartowski/OpenGVLab_InternVL3_5-2B-GGUF/blob/main/OpenGVLab_InternVL3_5-2B-Q5_K_S.gguf) | Q5_K_S | 1.44GB | false | High quality, *recommended*. |
| [InternVL3_5-2B-Q3_K_XL.gguf](https://huggingface.co/bartowski/OpenGVLab_InternVL3_5-2B-GGUF/blob/main/OpenGVLab_InternVL3_5-2B-Q3_K_XL.gguf) | Q3_K_XL | 1.41GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. |
| [InternVL3_5-2B-Q4_1.gguf](https://huggingface.co/bartowski/OpenGVLab_InternVL3_5-2B-GGUF/blob/main/OpenGVLab_InternVL3_5-2B-Q4_1.gguf) | Q4_1 | 1.34GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. |
| [InternVL3_5-2B-Q4_K_M.gguf](https://huggingface.co/bartowski/OpenGVLab_InternVL3_5-2B-GGUF/blob/main/OpenGVLab_InternVL3_5-2B-Q4_K_M.gguf) | Q4_K_M | 1.28GB | false | Good quality, default size for most use cases, *recommended*. |
| [InternVL3_5-2B-Q4_K_S.gguf](https://huggingface.co/bartowski/OpenGVLab_InternVL3_5-2B-GGUF/blob/main/OpenGVLab_InternVL3_5-2B-Q4_K_S.gguf) | Q4_K_S | 1.24GB | false | Slightly lower quality with more space savings, *recommended*. |
| [InternVL3_5-2B-Q4_0.gguf](https://huggingface.co/bartowski/OpenGVLab_InternVL3_5-2B-GGUF/blob/main/OpenGVLab_InternVL3_5-2B-Q4_0.gguf) | Q4_0 | 1.23GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. |
| [InternVL3_5-2B-IQ4_NL.gguf](https://huggingface.co/bartowski/OpenGVLab_InternVL3_5-2B-GGUF/blob/main/OpenGVLab_InternVL3_5-2B-IQ4_NL.gguf) | IQ4_NL | 1.23GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. |
| [InternVL3_5-2B-IQ4_XS.gguf](https://huggingface.co/bartowski/OpenGVLab_InternVL3_5-2B-GGUF/blob/main/OpenGVLab_InternVL3_5-2B-IQ4_XS.gguf) | IQ4_XS | 1.18GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
| [InternVL3_5-2B-Q2_K_L.gguf](https://huggingface.co/bartowski/OpenGVLab_InternVL3_5-2B-GGUF/blob/main/OpenGVLab_InternVL3_5-2B-Q2_K_L.gguf) | Q2_K_L | 1.18GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. |
| [InternVL3_5-2B-Q3_K_L.gguf](https://huggingface.co/bartowski/OpenGVLab_InternVL3_5-2B-GGUF/blob/main/OpenGVLab_InternVL3_5-2B-Q3_K_L.gguf) | Q3_K_L | 1.14GB | false | Lower quality but usable, good for low RAM availability. |
| [InternVL3_5-2B-Q3_K_M.gguf](https://huggingface.co/bartowski/OpenGVLab_InternVL3_5-2B-GGUF/blob/main/OpenGVLab_InternVL3_5-2B-Q3_K_M.gguf) | Q3_K_M | 1.07GB | false | Low quality. |
| [InternVL3_5-2B-IQ3_M.gguf](https://huggingface.co/bartowski/OpenGVLab_InternVL3_5-2B-GGUF/blob/main/OpenGVLab_InternVL3_5-2B-IQ3_M.gguf) | IQ3_M | 1.03GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
| [InternVL3_5-2B-Q3_K_S.gguf](https://huggingface.co/bartowski/OpenGVLab_InternVL3_5-2B-GGUF/blob/main/OpenGVLab_InternVL3_5-2B-Q3_K_S.gguf) | Q3_K_S | 1.00GB | false | Low quality, not recommended. |
| [InternVL3_5-2B-IQ3_XS.gguf](https://huggingface.co/bartowski/OpenGVLab_InternVL3_5-2B-GGUF/blob/main/OpenGVLab_InternVL3_5-2B-IQ3_XS.gguf) | IQ3_XS | 0.97GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
| [InternVL3_5-2B-IQ3_XXS.gguf](https://huggingface.co/bartowski/OpenGVLab_InternVL3_5-2B-GGUF/blob/main/OpenGVLab_InternVL3_5-2B-IQ3_XXS.gguf) | IQ3_XXS | 0.89GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. |
| [InternVL3_5-2B-Q2_K.gguf](https://huggingface.co/bartowski/OpenGVLab_InternVL3_5-2B-GGUF/blob/main/OpenGVLab_InternVL3_5-2B-Q2_K.gguf) | Q2_K | 0.88GB | false | Very low quality but surprisingly usable. |
| [InternVL3_5-2B-IQ2_M.gguf](https://huggingface.co/bartowski/OpenGVLab_InternVL3_5-2B-GGUF/blob/main/OpenGVLab_InternVL3_5-2B-IQ2_M.gguf) | IQ2_M | 0.83GB | 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_5-2B-GGUF --include "OpenGVLab_InternVL3_5-2B-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_5-2B-GGUF --include "OpenGVLab_InternVL3_5-2B-Q8_0/*" --local-dir ./
```
You can either specify a new local-dir (OpenGVLab_InternVL3_5-2B-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_5-2B-bf16.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d28284c78c232bf8d7b988d07832c6ed512af16414f53aee940b9b1b9a7ad758
size 637310368

3
mmproj-OpenGVLab_InternVL3_5-2B-f16.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e83ba6e675b747f7801557dc24594f43c17a7850b6129d4972d55e3e9b010359
size 636106144