commit c2f148c30b7784b770f4540b4169f92db4bfadab Author: ModelHub XC Date: Mon Sep 28 10:11:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Whale-4B-Thinking-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..0bebfc4 --- /dev/null +++ b/.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 +Whale-4B-Thinking.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +Whale-4B-Thinking.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Whale-4B-Thinking.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Whale-4B-Thinking.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Whale-4B-Thinking.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Whale-4B-Thinking.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Whale-4B-Thinking.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Whale-4B-Thinking.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Whale-4B-Thinking.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Whale-4B-Thinking.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Whale-4B-Thinking.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Whale-4B-Thinking.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Whale-4B-Thinking.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Whale-4B-Thinking.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Whale-4B-Thinking.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Whale-4B-Thinking.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Whale-4B-Thinking.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Whale-4B-Thinking.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Whale-4B-Thinking.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Whale-4B-Thinking.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Whale-4B-Thinking.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Whale-4B-Thinking.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Whale-4B-Thinking.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Whale-4B-Thinking.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Whale-4B-Thinking.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..bbbe68d --- /dev/null +++ b/README.md @@ -0,0 +1,97 @@ +--- +base_model: roskosmos19/Orca-4B-Thinking +language: +- en +- de +- es +- fr +- zh +library_name: transformers +license: apache-2.0 +license_link: https://huggingface.co/Whale-AI/Whale-4B-Thinking/blob/main/LICENSE +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- reasoning +- chain-of-thought +- deepseek-r1 +- thinking +- qwen3 +- whale +--- +## About + + + + + + + + + +weighted/imatrix quants of https://huggingface.co/roskosmos19/Orca-4B-Thinking + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Whale-4B-Thinking-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/Whale-4B-Thinking-GGUF +## 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/Whale-4B-Thinking-i1-GGUF/resolve/main/Whale-4B-Thinking.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/Whale-4B-Thinking-i1-GGUF/resolve/main/Whale-4B-Thinking.i1-IQ1_S.gguf) | i1-IQ1_S | 1.2 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Whale-4B-Thinking-i1-GGUF/resolve/main/Whale-4B-Thinking.i1-IQ1_M.gguf) | i1-IQ1_M | 1.2 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Whale-4B-Thinking-i1-GGUF/resolve/main/Whale-4B-Thinking.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/Whale-4B-Thinking-i1-GGUF/resolve/main/Whale-4B-Thinking.i1-IQ2_XS.gguf) | i1-IQ2_XS | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Whale-4B-Thinking-i1-GGUF/resolve/main/Whale-4B-Thinking.i1-IQ2_S.gguf) | i1-IQ2_S | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Whale-4B-Thinking-i1-GGUF/resolve/main/Whale-4B-Thinking.i1-IQ2_M.gguf) | i1-IQ2_M | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Whale-4B-Thinking-i1-GGUF/resolve/main/Whale-4B-Thinking.i1-Q2_K_S.gguf) | i1-Q2_K_S | 1.7 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Whale-4B-Thinking-i1-GGUF/resolve/main/Whale-4B-Thinking.i1-Q2_K.gguf) | i1-Q2_K | 1.8 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Whale-4B-Thinking-i1-GGUF/resolve/main/Whale-4B-Thinking.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Whale-4B-Thinking-i1-GGUF/resolve/main/Whale-4B-Thinking.i1-IQ3_XS.gguf) | i1-IQ3_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Whale-4B-Thinking-i1-GGUF/resolve/main/Whale-4B-Thinking.i1-Q3_K_S.gguf) | i1-Q3_K_S | 2.0 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Whale-4B-Thinking-i1-GGUF/resolve/main/Whale-4B-Thinking.i1-IQ3_S.gguf) | i1-IQ3_S | 2.0 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Whale-4B-Thinking-i1-GGUF/resolve/main/Whale-4B-Thinking.i1-IQ3_M.gguf) | i1-IQ3_M | 2.1 | | +| [GGUF](https://huggingface.co/mradermacher/Whale-4B-Thinking-i1-GGUF/resolve/main/Whale-4B-Thinking.i1-Q3_K_M.gguf) | i1-Q3_K_M | 2.2 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Whale-4B-Thinking-i1-GGUF/resolve/main/Whale-4B-Thinking.i1-Q3_K_L.gguf) | i1-Q3_K_L | 2.3 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Whale-4B-Thinking-i1-GGUF/resolve/main/Whale-4B-Thinking.i1-IQ4_XS.gguf) | i1-IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Whale-4B-Thinking-i1-GGUF/resolve/main/Whale-4B-Thinking.i1-Q4_0.gguf) | i1-Q4_0 | 2.5 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Whale-4B-Thinking-i1-GGUF/resolve/main/Whale-4B-Thinking.i1-IQ4_NL.gguf) | i1-IQ4_NL | 2.5 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/Whale-4B-Thinking-i1-GGUF/resolve/main/Whale-4B-Thinking.i1-Q4_K_S.gguf) | i1-Q4_K_S | 2.5 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Whale-4B-Thinking-i1-GGUF/resolve/main/Whale-4B-Thinking.i1-Q4_K_M.gguf) | i1-Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Whale-4B-Thinking-i1-GGUF/resolve/main/Whale-4B-Thinking.i1-Q4_1.gguf) | i1-Q4_1 | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/Whale-4B-Thinking-i1-GGUF/resolve/main/Whale-4B-Thinking.i1-Q5_K_S.gguf) | i1-Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Whale-4B-Thinking-i1-GGUF/resolve/main/Whale-4B-Thinking.i1-Q5_K_M.gguf) | i1-Q5_K_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Whale-4B-Thinking-i1-GGUF/resolve/main/Whale-4B-Thinking.i1-Q6_K.gguf) | i1-Q6_K | 3.4 | practically like static Q6_K | + +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. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. + + diff --git a/Whale-4B-Thinking.i1-IQ1_M.gguf b/Whale-4B-Thinking.i1-IQ1_M.gguf new file mode 100644 index 0000000..264c5ec --- /dev/null +++ b/Whale-4B-Thinking.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31cf11c1951697527ac93ee26348b9b9a273343892c5880f6ac942ee063f152d +size 1127018656 diff --git a/Whale-4B-Thinking.i1-IQ1_S.gguf b/Whale-4B-Thinking.i1-IQ1_S.gguf new file mode 100644 index 0000000..50d4efb --- /dev/null +++ b/Whale-4B-Thinking.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f3a8b224c3f02ac613629653edac8520c423f4a5cf3254b5b39f1ae0b8440d5 +size 1055256736 diff --git a/Whale-4B-Thinking.i1-IQ2_M.gguf b/Whale-4B-Thinking.i1-IQ2_M.gguf new file mode 100644 index 0000000..fe7f58d --- /dev/null +++ b/Whale-4B-Thinking.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60b1e10f0618cdb0ad4c421c871b919dd42fbd2dc0418cbbc424474a322d3a98 +size 1512984736 diff --git a/Whale-4B-Thinking.i1-IQ2_S.gguf b/Whale-4B-Thinking.i1-IQ2_S.gguf new file mode 100644 index 0000000..8d2e1b0 --- /dev/null +++ b/Whale-4B-Thinking.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5400dbdf6b70487f2ece6fee60f9f975208c7afc213c39a490ffb550bb19285 +size 1417302176 diff --git a/Whale-4B-Thinking.i1-IQ2_XS.gguf b/Whale-4B-Thinking.i1-IQ2_XS.gguf new file mode 100644 index 0000000..e918b6d --- /dev/null +++ b/Whale-4B-Thinking.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bec317f9450e2fcb2fddad15f54f414f7d45022504e26d00d4cd49e658ddcfbb +size 1354100896 diff --git a/Whale-4B-Thinking.i1-IQ2_XXS.gguf b/Whale-4B-Thinking.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..411f89d --- /dev/null +++ b/Whale-4B-Thinking.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd9c854d73efc103dbc2fde84c372569cf908e8ff2096a9efce186105709bd48 +size 1246621856 diff --git a/Whale-4B-Thinking.i1-IQ3_M.gguf b/Whale-4B-Thinking.i1-IQ3_M.gguf new file mode 100644 index 0000000..594a409 --- /dev/null +++ b/Whale-4B-Thinking.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2cebc5a4cc7038b3837b6338caaf6c3b30fc42bd98c6c2f7159111f33cdc7977 +size 1962897056 diff --git a/Whale-4B-Thinking.i1-IQ3_S.gguf b/Whale-4B-Thinking.i1-IQ3_S.gguf new file mode 100644 index 0000000..29c7361 --- /dev/null +++ b/Whale-4B-Thinking.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83238012c655cf3f0043c89e3cdb15b242cf3598ca1706b07e209b29ea0f17bc +size 1899531936 diff --git a/Whale-4B-Thinking.i1-IQ3_XS.gguf b/Whale-4B-Thinking.i1-IQ3_XS.gguf new file mode 100644 index 0000000..77d003a --- /dev/null +++ b/Whale-4B-Thinking.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:788d957a9227f7008ccdc70d6dc8e6e88995f382a7713b65f50d398d2ec4cc3a +size 1814376096 diff --git a/Whale-4B-Thinking.i1-IQ3_XXS.gguf b/Whale-4B-Thinking.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..0d07736 --- /dev/null +++ b/Whale-4B-Thinking.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:29658f72d0c2620e46c2c7882cc32ef34eca02af4812c110c92383d261fe4d0d +size 1670189216 diff --git a/Whale-4B-Thinking.i1-IQ4_NL.gguf b/Whale-4B-Thinking.i1-IQ4_NL.gguf new file mode 100644 index 0000000..e835ff9 --- /dev/null +++ b/Whale-4B-Thinking.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34d250628b336729353c75ddc3bd19eaa0b4fff8b6c24950585b5401f9ea2789 +size 2381344416 diff --git a/Whale-4B-Thinking.i1-IQ4_XS.gguf b/Whale-4B-Thinking.i1-IQ4_XS.gguf new file mode 100644 index 0000000..072a0b0 --- /dev/null +++ b/Whale-4B-Thinking.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31d57a915e039c916ccf04e3398c73caffa20f34dc7c0a0a3885b4674974c570 +size 2270752416 diff --git a/Whale-4B-Thinking.i1-Q2_K.gguf b/Whale-4B-Thinking.i1-Q2_K.gguf new file mode 100644 index 0000000..4ae85a0 --- /dev/null +++ b/Whale-4B-Thinking.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab46afae4355f352a37d5cc4f677bde94fad9e7e95fdd73fbf9e239df280b398 +size 1669500576 diff --git a/Whale-4B-Thinking.i1-Q2_K_S.gguf b/Whale-4B-Thinking.i1-Q2_K_S.gguf new file mode 100644 index 0000000..f4b343d --- /dev/null +++ b/Whale-4B-Thinking.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f71b5fdec417606582cb2ffff2db2fb14e9bdaaea2300549cd080df3d448c8e +size 1563455136 diff --git a/Whale-4B-Thinking.i1-Q3_K_L.gguf b/Whale-4B-Thinking.i1-Q3_K_L.gguf new file mode 100644 index 0000000..82afaf4 --- /dev/null +++ b/Whale-4B-Thinking.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa8c48fba1910a6083597f014b3bbf141a18a911588c7d067b7ff63bb94d8bd8 +size 2239786656 diff --git a/Whale-4B-Thinking.i1-Q3_K_M.gguf b/Whale-4B-Thinking.i1-Q3_K_M.gguf new file mode 100644 index 0000000..c57c667 --- /dev/null +++ b/Whale-4B-Thinking.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31d3f242043ae988936458927a77b05af82979f9959a702a3b75cf01da84bc74 +size 2075618976 diff --git a/Whale-4B-Thinking.i1-Q3_K_S.gguf b/Whale-4B-Thinking.i1-Q3_K_S.gguf new file mode 100644 index 0000000..5a722ab --- /dev/null +++ b/Whale-4B-Thinking.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9099a538c5677193cb50a3d4e011428a88cec4d98154cfbcabf6083641686881 +size 1886998176 diff --git a/Whale-4B-Thinking.i1-Q4_0.gguf b/Whale-4B-Thinking.i1-Q4_0.gguf new file mode 100644 index 0000000..a23186b --- /dev/null +++ b/Whale-4B-Thinking.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53b58e118162e72ad11c4bf508d24497109034f8d3867388e1b4c890a891532f +size 2375773856 diff --git a/Whale-4B-Thinking.i1-Q4_1.gguf b/Whale-4B-Thinking.i1-Q4_1.gguf new file mode 100644 index 0000000..82789f1 --- /dev/null +++ b/Whale-4B-Thinking.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af316e8a88761edafcdbc65331f5314d1c7bec1b94587e37a0f38a23bfca1ac1 +size 2596630176 diff --git a/Whale-4B-Thinking.i1-Q4_K_M.gguf b/Whale-4B-Thinking.i1-Q4_K_M.gguf new file mode 100644 index 0000000..a1d7adb --- /dev/null +++ b/Whale-4B-Thinking.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f578c370ed2716b9ece96b928ae504906abbd3c46b99d0157afb250cbee1c68f +size 2497281696 diff --git a/Whale-4B-Thinking.i1-Q4_K_S.gguf b/Whale-4B-Thinking.i1-Q4_K_S.gguf new file mode 100644 index 0000000..087e60f --- /dev/null +++ b/Whale-4B-Thinking.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ddd9de50156990055e0c7e70fe7bf2a4226bb75855c0191e9481de35bc95a976 +size 2383310496 diff --git a/Whale-4B-Thinking.i1-Q5_K_M.gguf b/Whale-4B-Thinking.i1-Q5_K_M.gguf new file mode 100644 index 0000000..93545ce --- /dev/null +++ b/Whale-4B-Thinking.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04b2a7a0b458c91d61f3e0075ffa3fa0bbd1cb73095abdc6a615de17c7dce98a +size 2889514656 diff --git a/Whale-4B-Thinking.i1-Q5_K_S.gguf b/Whale-4B-Thinking.i1-Q5_K_S.gguf new file mode 100644 index 0000000..996c749 --- /dev/null +++ b/Whale-4B-Thinking.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ccae84aee24a9bcce10931aedf86e4e7eda264b1edda1cc14858b9e17ed0c165 +size 2823712416 diff --git a/Whale-4B-Thinking.i1-Q6_K.gguf b/Whale-4B-Thinking.i1-Q6_K.gguf new file mode 100644 index 0000000..c374992 --- /dev/null +++ b/Whale-4B-Thinking.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ad4d78ce26a35ae7aa157eabeb54f18e3a93af94c1e830be45e57c5461e9c99 +size 3306262176 diff --git a/Whale-4B-Thinking.imatrix.gguf b/Whale-4B-Thinking.imatrix.gguf new file mode 100644 index 0000000..48b5a64 --- /dev/null +++ b/Whale-4B-Thinking.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2650dee31b7a7379d22ab822cf6eff0872c76aa43d339c8486bde37974b6be37 +size 3872640