From 9058ff9a2acd0076cf5a64a89ab01d935c65fd5c Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Fri, 7 Aug 2026 23:57:20 +0800 Subject: [PATCH] =?UTF-8?q?=E5=88=9D=E5=A7=8B=E5=8C=96=E9=A1=B9=E7=9B=AE?= =?UTF-8?q?=EF=BC=8C=E7=94=B1ModelHub=20XC=E7=A4=BE=E5=8C=BA=E6=8F=90?= =?UTF-8?q?=E4=BE=9B=E6=A8=A1=E5=9E=8B?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Model: liodon-ai/LFM2.5-8B-A1B-imatrix-GGUF Source: Original Platform --- .gitattributes | 42 ++++++++++++++++++++++++ LFM2.5-8B-A1B-IQ2_M.gguf | 3 ++ LFM2.5-8B-A1B-IQ3_M.gguf | 3 ++ LFM2.5-8B-A1B-IQ4_XS.gguf | 3 ++ LFM2.5-8B-A1B-Q4_K_M.gguf | 3 ++ LFM2.5-8B-A1B-Q5_K_M.gguf | 3 ++ LFM2.5-8B-A1B-Q6_K.gguf | 3 ++ LFM2.5-8B-A1B-Q8_0.gguf | 3 ++ README.md | 67 +++++++++++++++++++++++++++++++++++++++ 9 files changed, 130 insertions(+) create mode 100644 .gitattributes create mode 100644 LFM2.5-8B-A1B-IQ2_M.gguf create mode 100644 LFM2.5-8B-A1B-IQ3_M.gguf create mode 100644 LFM2.5-8B-A1B-IQ4_XS.gguf create mode 100644 LFM2.5-8B-A1B-Q4_K_M.gguf create mode 100644 LFM2.5-8B-A1B-Q5_K_M.gguf create mode 100644 LFM2.5-8B-A1B-Q6_K.gguf create mode 100644 LFM2.5-8B-A1B-Q8_0.gguf create mode 100644 README.md diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..11f28b0 --- /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 +LFM2.5-8B-A1B-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-8B-A1B-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-8B-A1B-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-8B-A1B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-8B-A1B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-8B-A1B-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-8B-A1B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/LFM2.5-8B-A1B-IQ2_M.gguf b/LFM2.5-8B-A1B-IQ2_M.gguf new file mode 100644 index 0000000..0e6216a --- /dev/null +++ b/LFM2.5-8B-A1B-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a892fb8703c570b39f1a86eba93de0640ff9418ad3f54d419f026cbcb0060f0 +size 2843274816 diff --git a/LFM2.5-8B-A1B-IQ3_M.gguf b/LFM2.5-8B-A1B-IQ3_M.gguf new file mode 100644 index 0000000..2fa8c16 --- /dev/null +++ b/LFM2.5-8B-A1B-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e04847dd766b30bb510e9a80af47cff97393eac8b55a1d4cc3e17d93eff7ece8 +size 3778752064 diff --git a/LFM2.5-8B-A1B-IQ4_XS.gguf b/LFM2.5-8B-A1B-IQ4_XS.gguf new file mode 100644 index 0000000..8822e9f --- /dev/null +++ b/LFM2.5-8B-A1B-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2237675ffa1c2d5a277db4ef02b79e613fc172d4b63511ae8cbcb8c3d75d1148 +size 4588301888 diff --git a/LFM2.5-8B-A1B-Q4_K_M.gguf b/LFM2.5-8B-A1B-Q4_K_M.gguf new file mode 100644 index 0000000..329387e --- /dev/null +++ b/LFM2.5-8B-A1B-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a74e6ea603b48db084c9ee49e56c59e8ab86b4189c4c7ea6a25dcedbbfc2fcd +size 5155565120 diff --git a/LFM2.5-8B-A1B-Q5_K_M.gguf b/LFM2.5-8B-A1B-Q5_K_M.gguf new file mode 100644 index 0000000..7e6f3ec --- /dev/null +++ b/LFM2.5-8B-A1B-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc8cde558bcc56ff10e085a07c3c200608a7b097556a4d4073e1db4da7492a0d +size 6030339648 diff --git a/LFM2.5-8B-A1B-Q6_K.gguf b/LFM2.5-8B-A1B-Q6_K.gguf new file mode 100644 index 0000000..d39f341 --- /dev/null +++ b/LFM2.5-8B-A1B-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2068b01ff7a7961ceee28cf95ba6f7853dbf3d727ae5e214b5cedf52def6ad19 +size 6959787584 diff --git a/LFM2.5-8B-A1B-Q8_0.gguf b/LFM2.5-8B-A1B-Q8_0.gguf new file mode 100644 index 0000000..eed9327 --- /dev/null +++ b/LFM2.5-8B-A1B-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17747800f8f7a91aab73399c82391752c152ca2c1a342a205a47d7388f5f7348 +size 9010196032 diff --git a/README.md b/README.md new file mode 100644 index 0000000..5d2a250 --- /dev/null +++ b/README.md @@ -0,0 +1,67 @@ +--- +license: other +base_model: LiquidAI/LFM2.5-8B-A1B +base_model_relation: quantized +pipeline_tag: text-generation +library_name: gguf +tags: +- gguf +- ollama +- local-llm +- llama.cpp +- lm-studio +- quantized +- imatrix +- sub-4-bit +quantized_by: liodon-ai +--- + +# LFM2.5-8B-A1B — iMatrix GGUF + +GGUF quantizations of [LiquidAI/LFM2.5-8B-A1B](https://huggingface.co/LiquidAI/LFM2.5-8B-A1B), published by [Liodon AI](https://huggingface.co/liodon-ai). + +## Quick Start + +**llama.cpp** +```bash +llama-cli -hf liodon-ai/LFM2.5-8B-A1B-imatrix-GGUF:Q4_K_M +``` + +**Ollama** +```bash +ollama run hf.co/liodon-ai/LFM2.5-8B-A1B-imatrix-GGUF:Q4_K_M +``` + +**LM Studio / Jan** — search `liodon-ai/LFM2.5-8B-A1B-imatrix-GGUF` and pick your quant. + +## Quants + +| Quant | Size | VRAM est. | Notes | +|-------|------|-----------|-------| +| `IQ2_M` | 2.84 GB | ~3 GB | 2-bit, iMatrix — smallest usable | +| `IQ3_M` | 3.78 GB | ~4 GB | 3-bit, iMatrix — great quality/size tradeoff | +| `IQ4_XS` | 4.59 GB | ~5 GB | 4-bit extra-small, iMatrix | +| `Q4_K_M` | 5.16 GB | ~6 GB | 4-bit, iMatrix-calibrated (recommended) | +| `Q5_K_M` | 6.03 GB | ~7 GB | 5-bit, iMatrix-calibrated | +| `Q6_K` | 6.96 GB | ~8 GB | 6-bit, iMatrix-calibrated, near-lossless | +| `Q8_0` | 9.01 GB | ~10 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/LFM2.5-8B-A1B-GGUF` + +## Source + +- **Model**: [LiquidAI/LFM2.5-8B-A1B](https://huggingface.co/LiquidAI/LFM2.5-8B-A1B) +- **License**: other + +--- +*Quantized by [Liodon AI](https://huggingface.co/liodon-ai)*