commit 41f57ed164e59c83983b17760e69334ef606840b Author: ModelHub XC Date: Fri Jun 12 06:38:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/llama4-dolphin-8B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..be9cd5b --- /dev/null +++ b/.gitattributes @@ -0,0 +1,50 @@ +*.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 +llama4-dolphin-8B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +llama4-dolphin-8B.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +llama4-dolphin-8B.f16.gguf filter=lfs diff=lfs merge=lfs -text +llama4-dolphin-8B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama4-dolphin-8B.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +llama4-dolphin-8B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llama4-dolphin-8B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llama4-dolphin-8B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama4-dolphin-8B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama4-dolphin-8B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llama4-dolphin-8B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama4-dolphin-8B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama4-dolphin-8B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama4-dolphin-8B.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +llama4-dolphin-8B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..0cb69b1 --- /dev/null +++ b/README.md @@ -0,0 +1,65 @@ +--- +base_model: Manavshah/llama4-dolphin-8B +language: +- en +library_name: transformers +quantized_by: mradermacher +--- +## About + + + + + +static quants of https://huggingface.co/Manavshah/llama4-dolphin-8B + + +weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. +## Usage + +If you are unsure how to use GGUF files, refer to one of [TheBloke's +READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for +more details, including on how to concatenate multi-part files. + +## Provided Quants + +(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) + +| Link | Type | Size/GB | Notes | +|:-----|:-----|--------:|:------| +| [GGUF](https://huggingface.co/mradermacher/llama4-dolphin-8B-GGUF/resolve/main/llama4-dolphin-8B.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/llama4-dolphin-8B-GGUF/resolve/main/llama4-dolphin-8B.IQ3_XS.gguf) | IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama4-dolphin-8B-GGUF/resolve/main/llama4-dolphin-8B.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama4-dolphin-8B-GGUF/resolve/main/llama4-dolphin-8B.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/llama4-dolphin-8B-GGUF/resolve/main/llama4-dolphin-8B.IQ3_M.gguf) | IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/llama4-dolphin-8B-GGUF/resolve/main/llama4-dolphin-8B.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/llama4-dolphin-8B-GGUF/resolve/main/llama4-dolphin-8B.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/llama4-dolphin-8B-GGUF/resolve/main/llama4-dolphin-8B.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama4-dolphin-8B-GGUF/resolve/main/llama4-dolphin-8B.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama4-dolphin-8B-GGUF/resolve/main/llama4-dolphin-8B.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama4-dolphin-8B-GGUF/resolve/main/llama4-dolphin-8B.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama4-dolphin-8B-GGUF/resolve/main/llama4-dolphin-8B.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama4-dolphin-8B-GGUF/resolve/main/llama4-dolphin-8B.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/llama4-dolphin-8B-GGUF/resolve/main/llama4-dolphin-8B.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/llama4-dolphin-8B-GGUF/resolve/main/llama4-dolphin-8B.f16.gguf) | f16 | 16.2 | 16 bpw, overkill | + +Here is a handy graph by ikawrakow comparing some lower-quality quant +types (lower is better): + +![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) + +And here are Artefact2's thoughts on the matter: +https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 + +## FAQ / Model Request + +See https://huggingface.co/mradermacher/model_requests for some answers to +questions you might have and/or if you want some other model quantized. + +## Thanks + +I thank my company, [nethype GmbH](https://www.nethype.de/), for letting +me use its servers and providing upgrades to my workstation to enable +this work in my free time. + + diff --git a/llama4-dolphin-8B.IQ3_M.gguf b/llama4-dolphin-8B.IQ3_M.gguf new file mode 100644 index 0000000..34e172e --- /dev/null +++ b/llama4-dolphin-8B.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a5877df1076eb3a92eddfb18478940431c051ea95e1e8f9da6ac6282f3b9836 +size 3785346720 diff --git a/llama4-dolphin-8B.IQ3_S.gguf b/llama4-dolphin-8B.IQ3_S.gguf new file mode 100644 index 0000000..0132f67 --- /dev/null +++ b/llama4-dolphin-8B.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2ee79f0a7b2cfb51fde051db60f3dea0337f586841cff6c9e31c435f565e463 +size 3682848416 diff --git a/llama4-dolphin-8B.IQ3_XS.gguf b/llama4-dolphin-8B.IQ3_XS.gguf new file mode 100644 index 0000000..c700d66 --- /dev/null +++ b/llama4-dolphin-8B.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45374af9e0234e9aed08460613524588d3cdfe02c43e4fb2d4fb3c3873b8c845 +size 3519270560 diff --git a/llama4-dolphin-8B.IQ4_XS.gguf b/llama4-dolphin-8B.IQ4_XS.gguf new file mode 100644 index 0000000..33e9cd3 --- /dev/null +++ b/llama4-dolphin-8B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a108a832ca43303e5862a479fb281847f6095930a44fa5c001206578ef3dce75 +size 4484887008 diff --git a/llama4-dolphin-8B.Q2_K.gguf b/llama4-dolphin-8B.Q2_K.gguf new file mode 100644 index 0000000..c573696 --- /dev/null +++ b/llama4-dolphin-8B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55e87a09511845119ea13c4f43490d32addd4918a8baa5be32f4a6083e5d5dcb +size 3179653984 diff --git a/llama4-dolphin-8B.Q3_K_L.gguf b/llama4-dolphin-8B.Q3_K_L.gguf new file mode 100644 index 0000000..5f85909 --- /dev/null +++ b/llama4-dolphin-8B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0b06d40cbd833bcff75b6c9e09f4fb084db9d8adcd812956720d3426e298cc9 +size 4322479776 diff --git a/llama4-dolphin-8B.Q3_K_M.gguf b/llama4-dolphin-8B.Q3_K_M.gguf new file mode 100644 index 0000000..060e877 --- /dev/null +++ b/llama4-dolphin-8B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a32feccd2e81fc4045a32fb5fa67f700c9c67569627eecd95596fdfa6c22bc5b +size 4019441312 diff --git a/llama4-dolphin-8B.Q3_K_S.gguf b/llama4-dolphin-8B.Q3_K_S.gguf new file mode 100644 index 0000000..eb5816d --- /dev/null +++ b/llama4-dolphin-8B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da588338a7eb9ac81daf3d1c3d4d5dcc243f304e27d40045f040f49bb287eda6 +size 3665022624 diff --git a/llama4-dolphin-8B.Q4_K_M.gguf b/llama4-dolphin-8B.Q4_K_M.gguf new file mode 100644 index 0000000..09b2253 --- /dev/null +++ b/llama4-dolphin-8B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d09bc1a8974a27581f16f41a57cf974ecd0f3f427f757ebe0d543061f2247b4e +size 4921258720 diff --git a/llama4-dolphin-8B.Q4_K_S.gguf b/llama4-dolphin-8B.Q4_K_S.gguf new file mode 100644 index 0000000..eecc5d7 --- /dev/null +++ b/llama4-dolphin-8B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b366087b7c287bb05673393aba4910873771b43350a3fb0eacfd1243ad9ffb4 +size 4693193440 diff --git a/llama4-dolphin-8B.Q5_K_M.gguf b/llama4-dolphin-8B.Q5_K_M.gguf new file mode 100644 index 0000000..f1337a1 --- /dev/null +++ b/llama4-dolphin-8B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76b360d8ec069bdd629da22c13e70946204e7f3c5de8884f5716863e4fc18035 +size 5733512928 diff --git a/llama4-dolphin-8B.Q5_K_S.gguf b/llama4-dolphin-8B.Q5_K_S.gguf new file mode 100644 index 0000000..09926db --- /dev/null +++ b/llama4-dolphin-8B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39264105d56733dff038866f1a107414093764c4585f9725d3e18cc6a5dc72f5 +size 5599819488 diff --git a/llama4-dolphin-8B.Q6_K.gguf b/llama4-dolphin-8B.Q6_K.gguf new file mode 100644 index 0000000..cab8d35 --- /dev/null +++ b/llama4-dolphin-8B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0158bd327a1e2a2db625668ff4c51b0a11517609d0f8f1e77331f0334170a64e +size 6596533024 diff --git a/llama4-dolphin-8B.Q8_0.gguf b/llama4-dolphin-8B.Q8_0.gguf new file mode 100644 index 0000000..351a558 --- /dev/null +++ b/llama4-dolphin-8B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6beb3f266bc097fe21530ae39c1f0710f43d2a238560adfd88da81412035aa4 +size 8541301408 diff --git a/llama4-dolphin-8B.f16.gguf b/llama4-dolphin-8B.f16.gguf new file mode 100644 index 0000000..6e204dc --- /dev/null +++ b/llama4-dolphin-8B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72b4263b0dfc32d49941df45d807d8b86a2fb3797804e5f7405270b001a9d47a +size 16069437088