commit eae761adbef3b9f471de2645d517114dab43c343 Author: ModelHub XC Date: Tue May 5 00:24:58 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/NeuralOmniBeagleMBX-v3-7B-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..ea606d2 --- /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 +imatrix.dat filter=lfs diff=lfs merge=lfs -text +NeuralOmniBeagleMBX-v3-7B.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +NeuralOmniBeagleMBX-v3-7B.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +NeuralOmniBeagleMBX-v3-7B.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +NeuralOmniBeagleMBX-v3-7B.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +NeuralOmniBeagleMBX-v3-7B.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +NeuralOmniBeagleMBX-v3-7B.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +NeuralOmniBeagleMBX-v3-7B.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +NeuralOmniBeagleMBX-v3-7B.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +NeuralOmniBeagleMBX-v3-7B.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +NeuralOmniBeagleMBX-v3-7B.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +NeuralOmniBeagleMBX-v3-7B.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +NeuralOmniBeagleMBX-v3-7B.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +NeuralOmniBeagleMBX-v3-7B.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +NeuralOmniBeagleMBX-v3-7B.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +NeuralOmniBeagleMBX-v3-7B.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +NeuralOmniBeagleMBX-v3-7B.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +NeuralOmniBeagleMBX-v3-7B.i1-Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text +NeuralOmniBeagleMBX-v3-7B.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +NeuralOmniBeagleMBX-v3-7B.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +NeuralOmniBeagleMBX-v3-7B.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +NeuralOmniBeagleMBX-v3-7B.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +NeuralOmniBeagleMBX-v3-7B.i1-Q4_0_8_8.gguf filter=lfs diff=lfs merge=lfs -text +NeuralOmniBeagleMBX-v3-7B.i1-Q4_0_4_8.gguf filter=lfs diff=lfs merge=lfs -text +NeuralOmniBeagleMBX-v3-7B.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/NeuralOmniBeagleMBX-v3-7B.i1-IQ1_M.gguf b/NeuralOmniBeagleMBX-v3-7B.i1-IQ1_M.gguf new file mode 100644 index 0000000..fe7da58 --- /dev/null +++ b/NeuralOmniBeagleMBX-v3-7B.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad0e692d46bcf205fbef22f228ca4cfc4d2aa8a84d7dc46e049128ad8edb56d5 +size 1754447232 diff --git a/NeuralOmniBeagleMBX-v3-7B.i1-IQ1_S.gguf b/NeuralOmniBeagleMBX-v3-7B.i1-IQ1_S.gguf new file mode 100644 index 0000000..1dcfe2a --- /dev/null +++ b/NeuralOmniBeagleMBX-v3-7B.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c72a09ec4e65d518b43115df99b2f8a8bd7a5b1c9b2fb9777ecd1213b382f8d +size 1612103040 diff --git a/NeuralOmniBeagleMBX-v3-7B.i1-IQ2_M.gguf b/NeuralOmniBeagleMBX-v3-7B.i1-IQ2_M.gguf new file mode 100644 index 0000000..c718a3b --- /dev/null +++ b/NeuralOmniBeagleMBX-v3-7B.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d427aa05bc044d979c075c9b3de1ed21323c8ed5ef1a4d677b311e49896b52d6 +size 2500713856 diff --git a/NeuralOmniBeagleMBX-v3-7B.i1-IQ2_S.gguf b/NeuralOmniBeagleMBX-v3-7B.i1-IQ2_S.gguf new file mode 100644 index 0000000..1b23d25 --- /dev/null +++ b/NeuralOmniBeagleMBX-v3-7B.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce662b4193aacfb791c66d5363354124e1f9966885c47516edaef5f424865c83 +size 2310921600 diff --git a/NeuralOmniBeagleMBX-v3-7B.i1-IQ2_XS.gguf b/NeuralOmniBeagleMBX-v3-7B.i1-IQ2_XS.gguf new file mode 100644 index 0000000..a4623b5 --- /dev/null +++ b/NeuralOmniBeagleMBX-v3-7B.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8867ffb476799fec3724090c72c74c29cf648037c9667cc911790420d81475b +size 2198257024 diff --git a/NeuralOmniBeagleMBX-v3-7B.i1-IQ2_XXS.gguf b/NeuralOmniBeagleMBX-v3-7B.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..c408577 --- /dev/null +++ b/NeuralOmniBeagleMBX-v3-7B.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10aa8694811bb92e445fa114229aceaf4601e3caa07b7c8770014a5b9093d013 +size 1991687552 diff --git a/NeuralOmniBeagleMBX-v3-7B.i1-IQ3_M.gguf b/NeuralOmniBeagleMBX-v3-7B.i1-IQ3_M.gguf new file mode 100644 index 0000000..3484a5e --- /dev/null +++ b/NeuralOmniBeagleMBX-v3-7B.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41450c247ddd3a7052518625c26a475b00998536efe91fa9cf5190314e32b574 +size 3284893056 diff --git a/NeuralOmniBeagleMBX-v3-7B.i1-IQ3_S.gguf b/NeuralOmniBeagleMBX-v3-7B.i1-IQ3_S.gguf new file mode 100644 index 0000000..b8dae0b --- /dev/null +++ b/NeuralOmniBeagleMBX-v3-7B.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:706bc73888d78384faeacd82c12b4801149eed69eb4bdef5e84e99a8b707c228 +size 3182394752 diff --git a/NeuralOmniBeagleMBX-v3-7B.i1-IQ3_XS.gguf b/NeuralOmniBeagleMBX-v3-7B.i1-IQ3_XS.gguf new file mode 100644 index 0000000..b2954d1 --- /dev/null +++ b/NeuralOmniBeagleMBX-v3-7B.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37a37b3502d08e72b8a2b10b7faa85b431287ae33c50033267c4ff28765099fa +size 3018816896 diff --git a/NeuralOmniBeagleMBX-v3-7B.i1-IQ3_XXS.gguf b/NeuralOmniBeagleMBX-v3-7B.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..7667781 --- /dev/null +++ b/NeuralOmniBeagleMBX-v3-7B.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0f1494c63044173749aa72577d7346f85ca11ecf2a6d06e322f5211b5a6fd99 +size 2827345280 diff --git a/NeuralOmniBeagleMBX-v3-7B.i1-IQ4_XS.gguf b/NeuralOmniBeagleMBX-v3-7B.i1-IQ4_XS.gguf new file mode 100644 index 0000000..1cb5223 --- /dev/null +++ b/NeuralOmniBeagleMBX-v3-7B.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a35b4bfe88470dd1b8083383db5e5ced75418f59d93ff6af7e36c18f4369c9b3 +size 3907689856 diff --git a/NeuralOmniBeagleMBX-v3-7B.i1-Q2_K.gguf b/NeuralOmniBeagleMBX-v3-7B.i1-Q2_K.gguf new file mode 100644 index 0000000..e888da5 --- /dev/null +++ b/NeuralOmniBeagleMBX-v3-7B.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d497ea0ea0a14228694dd5647f6f2e2724c80f60b30c97b7ec41843061109b75 +size 2719243648 diff --git a/NeuralOmniBeagleMBX-v3-7B.i1-Q3_K_L.gguf b/NeuralOmniBeagleMBX-v3-7B.i1-Q3_K_L.gguf new file mode 100644 index 0000000..3fc6b6b --- /dev/null +++ b/NeuralOmniBeagleMBX-v3-7B.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c23f4fbe87619eeb7ea36e2b82eb115d6a6011a64d99c3a5d02c13e35fe1f80c +size 3822026112 diff --git a/NeuralOmniBeagleMBX-v3-7B.i1-Q3_K_M.gguf b/NeuralOmniBeagleMBX-v3-7B.i1-Q3_K_M.gguf new file mode 100644 index 0000000..69dec38 --- /dev/null +++ b/NeuralOmniBeagleMBX-v3-7B.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:883a0386de787da64b6cdca32b2423d0a81882cbfcfc4f31440110d1e4c87daf +size 3518987648 diff --git a/NeuralOmniBeagleMBX-v3-7B.i1-Q3_K_S.gguf b/NeuralOmniBeagleMBX-v3-7B.i1-Q3_K_S.gguf new file mode 100644 index 0000000..1339216 --- /dev/null +++ b/NeuralOmniBeagleMBX-v3-7B.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd5e4003366e8a84496dda0c7eb7ae8e604d7520e428fb755b4fd0782140f2ec +size 3164568960 diff --git a/NeuralOmniBeagleMBX-v3-7B.i1-Q4_0.gguf b/NeuralOmniBeagleMBX-v3-7B.i1-Q4_0.gguf new file mode 100644 index 0000000..125b3ed --- /dev/null +++ b/NeuralOmniBeagleMBX-v3-7B.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e0122bf11483dba6e1f8f5f294066755ff644df83ff30f9b593a59243e4a019 +size 4123598208 diff --git a/NeuralOmniBeagleMBX-v3-7B.i1-Q4_0_4_4.gguf b/NeuralOmniBeagleMBX-v3-7B.i1-Q4_0_4_4.gguf new file mode 100644 index 0000000..dbe1b63 --- /dev/null +++ b/NeuralOmniBeagleMBX-v3-7B.i1-Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c2f7ef2aa558f939e4789e95bfd801d0268b709d57c91d807cf523ea20820a6 +size 4108918144 diff --git a/NeuralOmniBeagleMBX-v3-7B.i1-Q4_0_4_8.gguf b/NeuralOmniBeagleMBX-v3-7B.i1-Q4_0_4_8.gguf new file mode 100644 index 0000000..7296481 --- /dev/null +++ b/NeuralOmniBeagleMBX-v3-7B.i1-Q4_0_4_8.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25c18ba154e4f2f4ebe43a8cdb8c38de1660c03984b36a13e6cdf56e00ac4586 +size 4108918144 diff --git a/NeuralOmniBeagleMBX-v3-7B.i1-Q4_0_8_8.gguf b/NeuralOmniBeagleMBX-v3-7B.i1-Q4_0_8_8.gguf new file mode 100644 index 0000000..6687967 --- /dev/null +++ b/NeuralOmniBeagleMBX-v3-7B.i1-Q4_0_8_8.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4171e7a184d1b783ddab1ffae08f07d31bd3c0cf17e86afe916a9195837009f +size 4108918144 diff --git a/NeuralOmniBeagleMBX-v3-7B.i1-Q4_K_M.gguf b/NeuralOmniBeagleMBX-v3-7B.i1-Q4_K_M.gguf new file mode 100644 index 0000000..97eb0f8 --- /dev/null +++ b/NeuralOmniBeagleMBX-v3-7B.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15e5499d5fbe82c22b0e7846e2e07a114411083423d97e5b4a6f75fb8c3c7de1 +size 4368440704 diff --git a/NeuralOmniBeagleMBX-v3-7B.i1-Q4_K_S.gguf b/NeuralOmniBeagleMBX-v3-7B.i1-Q4_K_S.gguf new file mode 100644 index 0000000..f8fd4fd --- /dev/null +++ b/NeuralOmniBeagleMBX-v3-7B.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ff37f912c3f40d00df2559d0d17f61e315b56459b6decc1764ea35fea777c08 +size 4140375424 diff --git a/NeuralOmniBeagleMBX-v3-7B.i1-Q5_K_M.gguf b/NeuralOmniBeagleMBX-v3-7B.i1-Q5_K_M.gguf new file mode 100644 index 0000000..9ec4086 --- /dev/null +++ b/NeuralOmniBeagleMBX-v3-7B.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac20304fe0c9b52ebd3ec41ff36050d9e23968eaca5a67ce59314bb8b2d04b0d +size 5131410816 diff --git a/NeuralOmniBeagleMBX-v3-7B.i1-Q5_K_S.gguf b/NeuralOmniBeagleMBX-v3-7B.i1-Q5_K_S.gguf new file mode 100644 index 0000000..fdc521f --- /dev/null +++ b/NeuralOmniBeagleMBX-v3-7B.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:385faa09f294f28193ee9b58326d62eb8057fa597480a1b0b18dadc4312f89aa +size 4997717376 diff --git a/NeuralOmniBeagleMBX-v3-7B.i1-Q6_K.gguf b/NeuralOmniBeagleMBX-v3-7B.i1-Q6_K.gguf new file mode 100644 index 0000000..8d3083c --- /dev/null +++ b/NeuralOmniBeagleMBX-v3-7B.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15638cf289d06261e8d1e5465de2f948f9978f36a09c425d6334ee68edddab52 +size 5942066560 diff --git a/README.md b/README.md new file mode 100644 index 0000000..bde0a1b --- /dev/null +++ b/README.md @@ -0,0 +1,82 @@ +--- +base_model: paulml/NeuralOmniBeagleMBX-v3-7B +language: +- en +library_name: transformers +license: cc-by-nc-4.0 +quantized_by: mradermacher +tags: +- merge +- mergekit +- lazymergekit +- mlabonne/NeuralOmniBeagle-7B +- flemmingmiguel/MBX-7B-v3 +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/paulml/NeuralOmniBeagleMBX-v3-7B + + +static quants are available at https://huggingface.co/mradermacher/NeuralOmniBeagleMBX-v3-7B-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/NeuralOmniBeagleMBX-v3-7B-i1-GGUF/resolve/main/NeuralOmniBeagleMBX-v3-7B.i1-IQ1_S.gguf) | i1-IQ1_S | 1.7 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/NeuralOmniBeagleMBX-v3-7B-i1-GGUF/resolve/main/NeuralOmniBeagleMBX-v3-7B.i1-IQ1_M.gguf) | i1-IQ1_M | 1.9 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/NeuralOmniBeagleMBX-v3-7B-i1-GGUF/resolve/main/NeuralOmniBeagleMBX-v3-7B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.1 | | +| [GGUF](https://huggingface.co/mradermacher/NeuralOmniBeagleMBX-v3-7B-i1-GGUF/resolve/main/NeuralOmniBeagleMBX-v3-7B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/NeuralOmniBeagleMBX-v3-7B-i1-GGUF/resolve/main/NeuralOmniBeagleMBX-v3-7B.i1-IQ2_S.gguf) | i1-IQ2_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/NeuralOmniBeagleMBX-v3-7B-i1-GGUF/resolve/main/NeuralOmniBeagleMBX-v3-7B.i1-IQ2_M.gguf) | i1-IQ2_M | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/NeuralOmniBeagleMBX-v3-7B-i1-GGUF/resolve/main/NeuralOmniBeagleMBX-v3-7B.i1-Q2_K.gguf) | i1-Q2_K | 2.8 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/NeuralOmniBeagleMBX-v3-7B-i1-GGUF/resolve/main/NeuralOmniBeagleMBX-v3-7B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 2.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/NeuralOmniBeagleMBX-v3-7B-i1-GGUF/resolve/main/NeuralOmniBeagleMBX-v3-7B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/NeuralOmniBeagleMBX-v3-7B-i1-GGUF/resolve/main/NeuralOmniBeagleMBX-v3-7B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.3 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/NeuralOmniBeagleMBX-v3-7B-i1-GGUF/resolve/main/NeuralOmniBeagleMBX-v3-7B.i1-IQ3_S.gguf) | i1-IQ3_S | 3.3 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/NeuralOmniBeagleMBX-v3-7B-i1-GGUF/resolve/main/NeuralOmniBeagleMBX-v3-7B.i1-IQ3_M.gguf) | i1-IQ3_M | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/NeuralOmniBeagleMBX-v3-7B-i1-GGUF/resolve/main/NeuralOmniBeagleMBX-v3-7B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 3.6 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/NeuralOmniBeagleMBX-v3-7B-i1-GGUF/resolve/main/NeuralOmniBeagleMBX-v3-7B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 3.9 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/NeuralOmniBeagleMBX-v3-7B-i1-GGUF/resolve/main/NeuralOmniBeagleMBX-v3-7B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/NeuralOmniBeagleMBX-v3-7B-i1-GGUF/resolve/main/NeuralOmniBeagleMBX-v3-7B.i1-Q4_0_4_4.gguf) | i1-Q4_0_4_4 | 4.2 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/NeuralOmniBeagleMBX-v3-7B-i1-GGUF/resolve/main/NeuralOmniBeagleMBX-v3-7B.i1-Q4_0_4_8.gguf) | i1-Q4_0_4_8 | 4.2 | fast on arm+i8mm, low quality | +| [GGUF](https://huggingface.co/mradermacher/NeuralOmniBeagleMBX-v3-7B-i1-GGUF/resolve/main/NeuralOmniBeagleMBX-v3-7B.i1-Q4_0_8_8.gguf) | i1-Q4_0_8_8 | 4.2 | fast on arm+sve, low quality | +| [GGUF](https://huggingface.co/mradermacher/NeuralOmniBeagleMBX-v3-7B-i1-GGUF/resolve/main/NeuralOmniBeagleMBX-v3-7B.i1-Q4_0.gguf) | i1-Q4_0 | 4.2 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/NeuralOmniBeagleMBX-v3-7B-i1-GGUF/resolve/main/NeuralOmniBeagleMBX-v3-7B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.2 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/NeuralOmniBeagleMBX-v3-7B-i1-GGUF/resolve/main/NeuralOmniBeagleMBX-v3-7B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 4.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/NeuralOmniBeagleMBX-v3-7B-i1-GGUF/resolve/main/NeuralOmniBeagleMBX-v3-7B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/NeuralOmniBeagleMBX-v3-7B-i1-GGUF/resolve/main/NeuralOmniBeagleMBX-v3-7B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/NeuralOmniBeagleMBX-v3-7B-i1-GGUF/resolve/main/NeuralOmniBeagleMBX-v3-7B.i1-Q6_K.gguf) | i1-Q6_K | 6.0 | 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/imatrix.dat b/imatrix.dat new file mode 100644 index 0000000..3a401b5 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bafb2bee93a92c9a5d0840f68fdacbcec375c487402196b662ecbab7c7f7512b +size 4988157