commit 2b3069120d8be23b2ede40b49e158b45f42d2456 Author: ModelHub XC Date: Sat Aug 8 00:57:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: liodon-ai/Qwen2.5-14B-Instruct-imatrix-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..55d34ec --- /dev/null +++ b/.gitattributes @@ -0,0 +1,42 @@ +*.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 +Qwen2.5-14B-Instruct-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-14B-Instruct-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-14B-Instruct-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-14B-Instruct-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-14B-Instruct-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-14B-Instruct-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-14B-Instruct-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen2.5-14B-Instruct-IQ2_M.gguf b/Qwen2.5-14B-Instruct-IQ2_M.gguf new file mode 100644 index 0000000..0ec07e8 --- /dev/null +++ b/Qwen2.5-14B-Instruct-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04af879d78fc42b62f06854647021c0e7f2d474d2e38f0be464573e7a1e17ec3 +size 5356147008 diff --git a/Qwen2.5-14B-Instruct-IQ3_M.gguf b/Qwen2.5-14B-Instruct-IQ3_M.gguf new file mode 100644 index 0000000..0eddd47 --- /dev/null +++ b/Qwen2.5-14B-Instruct-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6aacb37697e0370f1cfd447f653c02921b17f833b75e3dc000c42079d09c4713 +size 6916538688 diff --git a/Qwen2.5-14B-Instruct-IQ4_XS.gguf b/Qwen2.5-14B-Instruct-IQ4_XS.gguf new file mode 100644 index 0000000..43f3041 --- /dev/null +++ b/Qwen2.5-14B-Instruct-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4739d07b80d03108419ca74b45767b635452a3278deb53658f603f2b227a8a6a +size 8119841088 diff --git a/Qwen2.5-14B-Instruct-Q4_K_M.gguf b/Qwen2.5-14B-Instruct-Q4_K_M.gguf new file mode 100644 index 0000000..856d0dd --- /dev/null +++ b/Qwen2.5-14B-Instruct-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08a8f61d9e6dcb4bba08514ba2b01592371fc0ae7908142046afabe700c161c3 +size 8988111168 diff --git a/Qwen2.5-14B-Instruct-Q5_K_M.gguf b/Qwen2.5-14B-Instruct-Q5_K_M.gguf new file mode 100644 index 0000000..ccb758c --- /dev/null +++ b/Qwen2.5-14B-Instruct-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b6fe2eb537be156685d1e432ad3065042cf0ac101644f192ea76e383fa6ff84 +size 10508874048 diff --git a/Qwen2.5-14B-Instruct-Q6_K.gguf b/Qwen2.5-14B-Instruct-Q6_K.gguf new file mode 100644 index 0000000..668ebe8 --- /dev/null +++ b/Qwen2.5-14B-Instruct-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c6fa1e1401edc061dff92ebf078ac40c1043ce907df7fd8718a9256529d9575 +size 12124684608 diff --git a/Qwen2.5-14B-Instruct-Q8_0.gguf b/Qwen2.5-14B-Instruct-Q8_0.gguf new file mode 100644 index 0000000..2a25584 --- /dev/null +++ b/Qwen2.5-14B-Instruct-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86ed159e481445c6cd6e7bcf537164a49d698fef5c712e6e9ecaaf62e0215f75 +size 15701598528 diff --git a/README.md b/README.md new file mode 100644 index 0000000..890bcac --- /dev/null +++ b/README.md @@ -0,0 +1,65 @@ +--- +license: other +base_model: unsloth/Qwen2.5-14B-Instruct +pipeline_tag: text-generation +tags: +- gguf +- local-llm +- llama.cpp +- lm-studio +- quantized +- imatrix +- sub-4-bit +- qwen2 +- base_model:Qwen/Qwen2.5-14B-Instruct +--- + +# Qwen2.5-14B-Instruct — iMatrix GGUF + +GGUF imatrix quantizations of [unsloth/Qwen2.5-14B-Instruct](https://huggingface.co/unsloth/Qwen2.5-14B-Instruct), published by [Liodon AI](https://huggingface.co/liodon-ai). + +## Quick Start + +**llama.cpp** +```bash +llama-cli -hf liodon-ai/Qwen2.5-14B-Instruct-imatrix-GGUF:Q4_K_M +``` + +**Ollama** +```bash +ollama run hf.co/liodon-ai/Qwen2.5-14B-Instruct-imatrix-GGUF:Q4_K_M +``` + +**LM Studio / Jan** — search `liodon-ai/Qwen2.5-14B-Instruct-imatrix-GGUF` and pick your quant. + +## Quants + +| Quant | Size | VRAM est. | Notes | +|-------|------|-----------|-------| +| `IQ2_M` | 5.36 GB | ~6 GB | 2-bit, iMatrix — smallest usable | +| `IQ3_M` | 6.92 GB | ~8 GB | 3-bit, iMatrix — great quality/size tradeoff | +| `IQ4_XS` | 8.12 GB | ~9 GB | 4-bit extra-small, iMatrix | +| `Q4_K_M` | 8.99 GB | ~10 GB | 4-bit, iMatrix-calibrated (recommended) | +| `Q5_K_M` | 10.51 GB | ~12 GB | 5-bit, iMatrix-calibrated | +| `Q6_K` | 12.12 GB | ~14 GB | 6-bit, iMatrix-calibrated, near-lossless | +| `Q8_0` | 15.70 GB | ~18 GB | 8-bit, essentially lossless | + + +## What is iMatrix? + +Standard quantization treats all weights equally. iMatrix runs 128 calibration chunks through +the full-precision model to find which weights matter most, then allocates more precision where +it counts. At Q2/Q3/Q4 this means noticeably better coherence and instruction-following — +**same file size, better output**. + +Calibration: 2M tokens of [WikiText-103](https://huggingface.co/datasets/wikitext). + +> Also see plain (non-iMatrix) quants: `liodon-ai/Qwen2.5-14B-Instruct-GGUF` + +## Source + +- **Model**: [unsloth/Qwen2.5-14B-Instruct](https://huggingface.co/unsloth/Qwen2.5-14B-Instruct) +- **License**: other + +--- +*Quantized by [Liodon AI](https://huggingface.co/liodon-ai)*