commit eb5112441fdc58c9618cae0de4c6f126be7f5b37 Author: ModelHub XC Date: Mon Oct 5 14:35:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Nexus-IKM-Mistral-7B-MLX-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..27d9d2f --- /dev/null +++ b/.gitattributes @@ -0,0 +1,47 @@ +*.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 +Nexus-IKM-Mistral-7B-MLX.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Nexus-IKM-Mistral-7B-MLX.f16.gguf filter=lfs diff=lfs merge=lfs -text +Nexus-IKM-Mistral-7B-MLX.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Nexus-IKM-Mistral-7B-MLX.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Nexus-IKM-Mistral-7B-MLX.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Nexus-IKM-Mistral-7B-MLX.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Nexus-IKM-Mistral-7B-MLX.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Nexus-IKM-Mistral-7B-MLX.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Nexus-IKM-Mistral-7B-MLX.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Nexus-IKM-Mistral-7B-MLX.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Nexus-IKM-Mistral-7B-MLX.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Nexus-IKM-Mistral-7B-MLX.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Nexus-IKM-Mistral-7B-MLX.IQ4_XS.gguf b/Nexus-IKM-Mistral-7B-MLX.IQ4_XS.gguf new file mode 100644 index 0000000..556d7b8 --- /dev/null +++ b/Nexus-IKM-Mistral-7B-MLX.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5554824644196ff527d5d43596e937ecded42a6f8c8fe32973f76fbd9678808c +size 3944389888 diff --git a/Nexus-IKM-Mistral-7B-MLX.Q2_K.gguf b/Nexus-IKM-Mistral-7B-MLX.Q2_K.gguf new file mode 100644 index 0000000..ba89d5b --- /dev/null +++ b/Nexus-IKM-Mistral-7B-MLX.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70ccf19417a97debc55dbf9e936bceb355821fa5e0b655dbdd16f7411ca8f562 +size 2719243520 diff --git a/Nexus-IKM-Mistral-7B-MLX.Q3_K_L.gguf b/Nexus-IKM-Mistral-7B-MLX.Q3_K_L.gguf new file mode 100644 index 0000000..36fd38c --- /dev/null +++ b/Nexus-IKM-Mistral-7B-MLX.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5673433a20ca69e4a97f376750a732c80355bc11e35168cdaa643daa1ea38838 +size 3822025984 diff --git a/Nexus-IKM-Mistral-7B-MLX.Q3_K_M.gguf b/Nexus-IKM-Mistral-7B-MLX.Q3_K_M.gguf new file mode 100644 index 0000000..82ad091 --- /dev/null +++ b/Nexus-IKM-Mistral-7B-MLX.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac7c298ba88053e60c833f914ea2e7e2c4ead5c7312ad96e145a1b0945a016aa +size 3518987520 diff --git a/Nexus-IKM-Mistral-7B-MLX.Q3_K_S.gguf b/Nexus-IKM-Mistral-7B-MLX.Q3_K_S.gguf new file mode 100644 index 0000000..ea5e342 --- /dev/null +++ b/Nexus-IKM-Mistral-7B-MLX.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8097e226918a7d1cda27425db9924986f6f51bbb5151a0a867ec2c848c18a009 +size 3164568832 diff --git a/Nexus-IKM-Mistral-7B-MLX.Q4_K_M.gguf b/Nexus-IKM-Mistral-7B-MLX.Q4_K_M.gguf new file mode 100644 index 0000000..354abf3 --- /dev/null +++ b/Nexus-IKM-Mistral-7B-MLX.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3cbd39cae6064339a7cbf96e5e6ffba48c1f978cc7720e305e3530e6a020f18e +size 4368440576 diff --git a/Nexus-IKM-Mistral-7B-MLX.Q4_K_S.gguf b/Nexus-IKM-Mistral-7B-MLX.Q4_K_S.gguf new file mode 100644 index 0000000..ffbd362 --- /dev/null +++ b/Nexus-IKM-Mistral-7B-MLX.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1cce2a5da1f1f8aeb48ad37dbc7ae76087e18aeee3580ab0970842614969e23d +size 4140375296 diff --git a/Nexus-IKM-Mistral-7B-MLX.Q5_K_M.gguf b/Nexus-IKM-Mistral-7B-MLX.Q5_K_M.gguf new file mode 100644 index 0000000..1436cc8 --- /dev/null +++ b/Nexus-IKM-Mistral-7B-MLX.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:789ec1ca3fc73fa3a2d17b0a0b26bcebbf889deeb567c5c32d6e749df861a770 +size 5131410688 diff --git a/Nexus-IKM-Mistral-7B-MLX.Q5_K_S.gguf b/Nexus-IKM-Mistral-7B-MLX.Q5_K_S.gguf new file mode 100644 index 0000000..36fd757 --- /dev/null +++ b/Nexus-IKM-Mistral-7B-MLX.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e380eaeea94ff9bb92452670f1a0c52bb976e3145c1f5db8d73ee2ee623e5923 +size 4997717248 diff --git a/Nexus-IKM-Mistral-7B-MLX.Q6_K.gguf b/Nexus-IKM-Mistral-7B-MLX.Q6_K.gguf new file mode 100644 index 0000000..21bd0c1 --- /dev/null +++ b/Nexus-IKM-Mistral-7B-MLX.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ffe7bdd40c45889b6ed4c0aa6838f71c8b49c4cda3ecce9457381102bc727efd +size 5942066432 diff --git a/Nexus-IKM-Mistral-7B-MLX.Q8_0.gguf b/Nexus-IKM-Mistral-7B-MLX.Q8_0.gguf new file mode 100644 index 0000000..7e6d431 --- /dev/null +++ b/Nexus-IKM-Mistral-7B-MLX.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d48a2731f4836c0dd7afd9a4db20fb7f45e9d98ac85c5d11020c900234cf90a +size 7695858944 diff --git a/Nexus-IKM-Mistral-7B-MLX.f16.gguf b/Nexus-IKM-Mistral-7B-MLX.f16.gguf new file mode 100644 index 0000000..f51f92f --- /dev/null +++ b/Nexus-IKM-Mistral-7B-MLX.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c6a46581fba47b7bd1374425228b350138188ee6f35fec18386914d8ebab993 +size 14484733184 diff --git a/README.md b/README.md new file mode 100644 index 0000000..15035a1 --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: Severian/Nexus-IKM-Mistral-7B-MLX +datasets: +- Severian/Internal-Knowledge-Map +language: +- en +library_name: transformers +license: mit +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/Severian/Nexus-IKM-Mistral-7B-MLX + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Nexus-IKM-Mistral-7B-MLX-i1-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/Nexus-IKM-Mistral-7B-MLX-GGUF/resolve/main/Nexus-IKM-Mistral-7B-MLX.Q2_K.gguf) | Q2_K | 2.8 | | +| [GGUF](https://huggingface.co/mradermacher/Nexus-IKM-Mistral-7B-MLX-GGUF/resolve/main/Nexus-IKM-Mistral-7B-MLX.Q3_K_S.gguf) | Q3_K_S | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Nexus-IKM-Mistral-7B-MLX-GGUF/resolve/main/Nexus-IKM-Mistral-7B-MLX.Q3_K_M.gguf) | Q3_K_M | 3.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Nexus-IKM-Mistral-7B-MLX-GGUF/resolve/main/Nexus-IKM-Mistral-7B-MLX.Q3_K_L.gguf) | Q3_K_L | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Nexus-IKM-Mistral-7B-MLX-GGUF/resolve/main/Nexus-IKM-Mistral-7B-MLX.IQ4_XS.gguf) | IQ4_XS | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/Nexus-IKM-Mistral-7B-MLX-GGUF/resolve/main/Nexus-IKM-Mistral-7B-MLX.Q4_K_S.gguf) | Q4_K_S | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Nexus-IKM-Mistral-7B-MLX-GGUF/resolve/main/Nexus-IKM-Mistral-7B-MLX.Q4_K_M.gguf) | Q4_K_M | 4.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Nexus-IKM-Mistral-7B-MLX-GGUF/resolve/main/Nexus-IKM-Mistral-7B-MLX.Q5_K_S.gguf) | Q5_K_S | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/Nexus-IKM-Mistral-7B-MLX-GGUF/resolve/main/Nexus-IKM-Mistral-7B-MLX.Q5_K_M.gguf) | Q5_K_M | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/Nexus-IKM-Mistral-7B-MLX-GGUF/resolve/main/Nexus-IKM-Mistral-7B-MLX.Q6_K.gguf) | Q6_K | 6.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Nexus-IKM-Mistral-7B-MLX-GGUF/resolve/main/Nexus-IKM-Mistral-7B-MLX.Q8_0.gguf) | Q8_0 | 7.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Nexus-IKM-Mistral-7B-MLX-GGUF/resolve/main/Nexus-IKM-Mistral-7B-MLX.f16.gguf) | f16 | 14.6 | 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. + +