commit c982c8168a611995fe788bc49b1cbe5546125d8b Author: ModelHub XC Date: Mon Jun 1 18:08:21 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen3-SG1-256k-ctx-6B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..630eb18 --- /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 +Qwen3-SG1-256k-ctx-6B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-SG1-256k-ctx-6B.f16.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-SG1-256k-ctx-6B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-SG1-256k-ctx-6B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-SG1-256k-ctx-6B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-SG1-256k-ctx-6B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-SG1-256k-ctx-6B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-SG1-256k-ctx-6B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-SG1-256k-ctx-6B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-SG1-256k-ctx-6B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-SG1-256k-ctx-6B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-SG1-256k-ctx-6B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen3-SG1-256k-ctx-6B.IQ4_XS.gguf b/Qwen3-SG1-256k-ctx-6B.IQ4_XS.gguf new file mode 100644 index 0000000..16cc416 --- /dev/null +++ b/Qwen3-SG1-256k-ctx-6B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a07d8505d4c9d2dd77b74f2b87a3ddabc9723d65275f8698beafa009f520049f +size 3527652960 diff --git a/Qwen3-SG1-256k-ctx-6B.Q2_K.gguf b/Qwen3-SG1-256k-ctx-6B.Q2_K.gguf new file mode 100644 index 0000000..e933e44 --- /dev/null +++ b/Qwen3-SG1-256k-ctx-6B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1bcc018531df5db73bdc87acc1142f7f11f1ef68824bf68d067273d41cbed3b +size 2506719840 diff --git a/Qwen3-SG1-256k-ctx-6B.Q3_K_L.gguf b/Qwen3-SG1-256k-ctx-6B.Q3_K_L.gguf new file mode 100644 index 0000000..3d28342 --- /dev/null +++ b/Qwen3-SG1-256k-ctx-6B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59b45bab7bed8e518c931ccc33fcd318a636236add37a9ca02d92adc0ae70111 +size 3417493600 diff --git a/Qwen3-SG1-256k-ctx-6B.Q3_K_M.gguf b/Qwen3-SG1-256k-ctx-6B.Q3_K_M.gguf new file mode 100644 index 0000000..3d8796f --- /dev/null +++ b/Qwen3-SG1-256k-ctx-6B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4305191bf4028ddf845c4127507ca6c8b87ff9bdd113627d28d8db7c5e7568c6 +size 3166163040 diff --git a/Qwen3-SG1-256k-ctx-6B.Q3_K_S.gguf b/Qwen3-SG1-256k-ctx-6B.Q3_K_S.gguf new file mode 100644 index 0000000..b345d9c --- /dev/null +++ b/Qwen3-SG1-256k-ctx-6B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5282042c5a8a1ae751f32f3c10162b3a62334e3fb66ec329ffbb1cdb8ab398e9 +size 2878511200 diff --git a/Qwen3-SG1-256k-ctx-6B.Q4_K_M.gguf b/Qwen3-SG1-256k-ctx-6B.Q4_K_M.gguf new file mode 100644 index 0000000..941844a --- /dev/null +++ b/Qwen3-SG1-256k-ctx-6B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2dac90e1d5c9e0a3288940fb81a85f56c9b5dc4756d84055c62e9d2c061cf784 +size 3858998880 diff --git a/Qwen3-SG1-256k-ctx-6B.Q4_K_S.gguf b/Qwen3-SG1-256k-ctx-6B.Q4_K_S.gguf new file mode 100644 index 0000000..6bd5b5c --- /dev/null +++ b/Qwen3-SG1-256k-ctx-6B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e70cc3ce14d531532e07928a1c8acccbb854d650edfdf3ea91a2476b5f6593b +size 3687386720 diff --git a/Qwen3-SG1-256k-ctx-6B.Q5_K_M.gguf b/Qwen3-SG1-256k-ctx-6B.Q5_K_M.gguf new file mode 100644 index 0000000..83cb76a --- /dev/null +++ b/Qwen3-SG1-256k-ctx-6B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a63e3fcee72ae22db4f1f262b4465cce64155423a0468dab733e66d3616d06fe +size 4508583520 diff --git a/Qwen3-SG1-256k-ctx-6B.Q5_K_S.gguf b/Qwen3-SG1-256k-ctx-6B.Q5_K_S.gguf new file mode 100644 index 0000000..39435ef --- /dev/null +++ b/Qwen3-SG1-256k-ctx-6B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c15b372a6924482a6413f018c7b8de22db07b4754d29a5ecd75d46ca8e57caca +size 4409880160 diff --git a/Qwen3-SG1-256k-ctx-6B.Q6_K.gguf b/Qwen3-SG1-256k-ctx-6B.Q6_K.gguf new file mode 100644 index 0000000..f8828c9 --- /dev/null +++ b/Qwen3-SG1-256k-ctx-6B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6c8447f402879d6d247d493ae58a98352a30a10803f8c32c2eccc95162bf1a5 +size 5198767200 diff --git a/Qwen3-SG1-256k-ctx-6B.Q8_0.gguf b/Qwen3-SG1-256k-ctx-6B.Q8_0.gguf new file mode 100644 index 0000000..6e59422 --- /dev/null +++ b/Qwen3-SG1-256k-ctx-6B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b046e5b74fe02dc4d565a4523fa6e7f45cd50766f2ca430a1fe08e27c824b281 +size 6731526240 diff --git a/Qwen3-SG1-256k-ctx-6B.f16.gguf b/Qwen3-SG1-256k-ctx-6B.f16.gguf new file mode 100644 index 0000000..b906bc6 --- /dev/null +++ b/Qwen3-SG1-256k-ctx-6B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec84a72667f74946b86d21fefd42899af557bdb1d5074fea23e1b43c17688103 +size 12664787040 diff --git a/README.md b/README.md new file mode 100644 index 0000000..1a06327 --- /dev/null +++ b/README.md @@ -0,0 +1,98 @@ +--- +base_model: DavidAU/Qwen3-SG1-256k-ctx-6B +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- programming +- code generation +- code +- coding +- coder +- chat +- code +- chat +- brainstorm +- qwen +- qwen3 +- qwencoder +- brainstorm 20x +- creative +- all uses cases +- Jan-V1 +- Stargate +- SG1 +- horror +- science fiction +- fantasy +- finetune +- thinking +- reasoning +- unsloth +--- +## About + + + + + + + + + +static quants of https://huggingface.co/DavidAU/Qwen3-SG1-256k-ctx-6B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3-SG1-256k-ctx-6B-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Qwen3-SG1-256k-ctx-6B-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/Qwen3-SG1-256k-ctx-6B-GGUF/resolve/main/Qwen3-SG1-256k-ctx-6B.Q2_K.gguf) | Q2_K | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-SG1-256k-ctx-6B-GGUF/resolve/main/Qwen3-SG1-256k-ctx-6B.Q3_K_S.gguf) | Q3_K_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-SG1-256k-ctx-6B-GGUF/resolve/main/Qwen3-SG1-256k-ctx-6B.Q3_K_M.gguf) | Q3_K_M | 3.3 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-SG1-256k-ctx-6B-GGUF/resolve/main/Qwen3-SG1-256k-ctx-6B.Q3_K_L.gguf) | Q3_K_L | 3.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-SG1-256k-ctx-6B-GGUF/resolve/main/Qwen3-SG1-256k-ctx-6B.IQ4_XS.gguf) | IQ4_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-SG1-256k-ctx-6B-GGUF/resolve/main/Qwen3-SG1-256k-ctx-6B.Q4_K_S.gguf) | Q4_K_S | 3.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-SG1-256k-ctx-6B-GGUF/resolve/main/Qwen3-SG1-256k-ctx-6B.Q4_K_M.gguf) | Q4_K_M | 4.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-SG1-256k-ctx-6B-GGUF/resolve/main/Qwen3-SG1-256k-ctx-6B.Q5_K_S.gguf) | Q5_K_S | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-SG1-256k-ctx-6B-GGUF/resolve/main/Qwen3-SG1-256k-ctx-6B.Q5_K_M.gguf) | Q5_K_M | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-SG1-256k-ctx-6B-GGUF/resolve/main/Qwen3-SG1-256k-ctx-6B.Q6_K.gguf) | Q6_K | 5.3 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-SG1-256k-ctx-6B-GGUF/resolve/main/Qwen3-SG1-256k-ctx-6B.Q8_0.gguf) | Q8_0 | 6.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-SG1-256k-ctx-6B-GGUF/resolve/main/Qwen3-SG1-256k-ctx-6B.f16.gguf) | f16 | 12.8 | 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. + +