commit f776cd3fade147fe1b2fad67a0a8c6a11f39aa3a Author: ModelHub XC Date: Tue Jun 2 01:08:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Quantum-X-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..dd4dc6f --- /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 +Quantum-X.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Quantum-X.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Quantum-X.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Quantum-X.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Quantum-X.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Quantum-X.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Quantum-X.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Quantum-X.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Quantum-X.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Quantum-X.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Quantum-X.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Quantum-X.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Quantum-X.IQ4_XS.gguf b/Quantum-X.IQ4_XS.gguf new file mode 100644 index 0000000..b95b776 --- /dev/null +++ b/Quantum-X.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98ee55c7a2b4c7d5aaf53136e2ea287f96efcc54211679c3c36b17b930fb6ee1 +size 351445664 diff --git a/Quantum-X.Q2_K.gguf b/Quantum-X.Q2_K.gguf new file mode 100644 index 0000000..d15da49 --- /dev/null +++ b/Quantum-X.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f88fa7517b27183baad9963e268e5942bd4724608377132a1bc0bcffb6a7b09a +size 338607776 diff --git a/Quantum-X.Q3_K_L.gguf b/Quantum-X.Q3_K_L.gguf new file mode 100644 index 0000000..564f543 --- /dev/null +++ b/Quantum-X.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a21ea906feb4b08fbc321a28c75ce12e7213220bedb414cf230e31a41e1ac98e +size 369358496 diff --git a/Quantum-X.Q3_K_M.gguf b/Quantum-X.Q3_K_M.gguf new file mode 100644 index 0000000..df1dc2e --- /dev/null +++ b/Quantum-X.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f23bb861601897ca45fd09a584535931e2cc0e6d3003a898c44658f780fb488c +size 355466912 diff --git a/Quantum-X.Q3_K_S.gguf b/Quantum-X.Q3_K_S.gguf new file mode 100644 index 0000000..1199fa6 --- /dev/null +++ b/Quantum-X.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:924fe294396cea6090a13f19ad9d8081e22849621601edd6008c23440c98192e +size 338263712 diff --git a/Quantum-X.Q4_K_M.gguf b/Quantum-X.Q4_K_M.gguf new file mode 100644 index 0000000..f9d4bf4 --- /dev/null +++ b/Quantum-X.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ce10fad13beb9eca60545ffc3a15c356e6cd5cd3b6310f8e2a6fd4413daa55d +size 397808288 diff --git a/Quantum-X.Q4_K_S.gguf b/Quantum-X.Q4_K_S.gguf new file mode 100644 index 0000000..52b3e00 --- /dev/null +++ b/Quantum-X.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6572943458841a27e61bb87a344128952fb0326d6fd45427b45f4c52f508acb5 +size 385472160 diff --git a/Quantum-X.Q5_K_M.gguf b/Quantum-X.Q5_K_M.gguf new file mode 100644 index 0000000..cfd72d7 --- /dev/null +++ b/Quantum-X.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b8e07534768a1175e9441e9b2e75266a50bcef174bc83ce915458f6db196bca +size 420086432 diff --git a/Quantum-X.Q5_K_S.gguf b/Quantum-X.Q5_K_S.gguf new file mode 100644 index 0000000..7b18e1f --- /dev/null +++ b/Quantum-X.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e99b556f55cecb5e547eb8494fe8eb345ff3235a922351e4656015476082a96c +size 412710560 diff --git a/Quantum-X.Q6_K.gguf b/Quantum-X.Q6_K.gguf new file mode 100644 index 0000000..f3c3df7 --- /dev/null +++ b/Quantum-X.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e3b532bc76deb3639683ee74597dca099a23d4ff69bcc0b077e569b0e1629757 +size 505736864 diff --git a/Quantum-X.Q8_0.gguf b/Quantum-X.Q8_0.gguf new file mode 100644 index 0000000..200401e --- /dev/null +++ b/Quantum-X.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d60de7249fe00b20e9e9dd94bafe461ee732a72f5612c248fb24ad4578405a4 +size 531068576 diff --git a/Quantum-X.f16.gguf b/Quantum-X.f16.gguf new file mode 100644 index 0000000..c7be248 --- /dev/null +++ b/Quantum-X.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae552bd9d891405bd3fba089c90345ee08a2892264a77c7aa95edf1245b6924d +size 994157216 diff --git a/README.md b/README.md new file mode 100644 index 0000000..261a561 --- /dev/null +++ b/README.md @@ -0,0 +1,79 @@ +--- +base_model: QuantaSparkLabs/Quantum-X +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- qwen2.5 +- 0.5B +- conversational +- fast +- lightweight +- quantsaparklabs +--- +## About + + + + + + + + + +static quants of https://huggingface.co/QuantaSparkLabs/Quantum-X + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Quantum-X-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Quantum-X-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/Quantum-X-GGUF/resolve/main/Quantum-X.Q3_K_S.gguf) | Q3_K_S | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Quantum-X-GGUF/resolve/main/Quantum-X.Q2_K.gguf) | Q2_K | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Quantum-X-GGUF/resolve/main/Quantum-X.IQ4_XS.gguf) | IQ4_XS | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Quantum-X-GGUF/resolve/main/Quantum-X.Q3_K_M.gguf) | Q3_K_M | 0.5 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Quantum-X-GGUF/resolve/main/Quantum-X.Q3_K_L.gguf) | Q3_K_L | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Quantum-X-GGUF/resolve/main/Quantum-X.Q4_K_S.gguf) | Q4_K_S | 0.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Quantum-X-GGUF/resolve/main/Quantum-X.Q4_K_M.gguf) | Q4_K_M | 0.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Quantum-X-GGUF/resolve/main/Quantum-X.Q5_K_S.gguf) | Q5_K_S | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Quantum-X-GGUF/resolve/main/Quantum-X.Q5_K_M.gguf) | Q5_K_M | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Quantum-X-GGUF/resolve/main/Quantum-X.Q6_K.gguf) | Q6_K | 0.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Quantum-X-GGUF/resolve/main/Quantum-X.Q8_0.gguf) | Q8_0 | 0.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Quantum-X-GGUF/resolve/main/Quantum-X.f16.gguf) | f16 | 1.1 | 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. + +