commit c121b731d1c4724a13e64dd1ee5a542d194c8cc5 Author: ModelHub XC Date: Fri May 22 09:04:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Marco-LLM-AR-V3-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..07728f6 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,59 @@ +*.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 +Marco-LLM-AR-V3.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Marco-LLM-AR-V3.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Marco-LLM-AR-V3.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Marco-LLM-AR-V3.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Marco-LLM-AR-V3.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Marco-LLM-AR-V3.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Marco-LLM-AR-V3.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Marco-LLM-AR-V3.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Marco-LLM-AR-V3.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Marco-LLM-AR-V3.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Marco-LLM-AR-V3.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Marco-LLM-AR-V3.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Marco-LLM-AR-V3.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Marco-LLM-AR-V3.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Marco-LLM-AR-V3.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Marco-LLM-AR-V3.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Marco-LLM-AR-V3.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Marco-LLM-AR-V3.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Marco-LLM-AR-V3.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Marco-LLM-AR-V3.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Marco-LLM-AR-V3.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Marco-LLM-AR-V3.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Marco-LLM-AR-V3.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Marco-LLM-AR-V3.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Marco-LLM-AR-V3.i1-IQ1_M.gguf b/Marco-LLM-AR-V3.i1-IQ1_M.gguf new file mode 100644 index 0000000..1ad9dfe --- /dev/null +++ b/Marco-LLM-AR-V3.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15d42fecb169ec4904a39a80080ec514141f6903ee0077322ba6b8daeb6b29e4 +size 2042196864 diff --git a/Marco-LLM-AR-V3.i1-IQ1_S.gguf b/Marco-LLM-AR-V3.i1-IQ1_S.gguf new file mode 100644 index 0000000..fb7699e --- /dev/null +++ b/Marco-LLM-AR-V3.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:abd597b1f5dd692eae0e7ba3ef67aca75ac88cfc2bb8e7314781e6af458c9e11 +size 1903668096 diff --git a/Marco-LLM-AR-V3.i1-IQ2_M.gguf b/Marco-LLM-AR-V3.i1-IQ2_M.gguf new file mode 100644 index 0000000..037f384 --- /dev/null +++ b/Marco-LLM-AR-V3.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:179bd82396d367f334622aab5b570d9456e8464490afa3a781329f2f65837134 +size 2780343168 diff --git a/Marco-LLM-AR-V3.i1-IQ2_S.gguf b/Marco-LLM-AR-V3.i1-IQ2_S.gguf new file mode 100644 index 0000000..5574688 --- /dev/null +++ b/Marco-LLM-AR-V3.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f476966092536c6de81d1b5ea4aa8ebf1ce024d848e688c84f91ce0e5e861d9c +size 2595638144 diff --git a/Marco-LLM-AR-V3.i1-IQ2_XS.gguf b/Marco-LLM-AR-V3.i1-IQ2_XS.gguf new file mode 100644 index 0000000..673b611 --- /dev/null +++ b/Marco-LLM-AR-V3.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed88ecef22f0f09afe816df759b2b6c5defbc3c0b2e95f33ea8671af72458c31 +size 2469022592 diff --git a/Marco-LLM-AR-V3.i1-IQ2_XXS.gguf b/Marco-LLM-AR-V3.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..2e90f7b --- /dev/null +++ b/Marco-LLM-AR-V3.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5828e52befc48a4e069f8fb0f000ef2bad94bec58fe41599566cd5081637e031 +size 2273078144 diff --git a/Marco-LLM-AR-V3.i1-IQ3_M.gguf b/Marco-LLM-AR-V3.i1-IQ3_M.gguf new file mode 100644 index 0000000..38a42ce --- /dev/null +++ b/Marco-LLM-AR-V3.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7766a7cd743b6a1222b414500c31cc03a4e0d34ffb10d9dc3446975daf81f36a +size 3574012800 diff --git a/Marco-LLM-AR-V3.i1-IQ3_S.gguf b/Marco-LLM-AR-V3.i1-IQ3_S.gguf new file mode 100644 index 0000000..d425671 --- /dev/null +++ b/Marco-LLM-AR-V3.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28ab4d24b2521c50a82ef77152e08fb9b2e9da99d6ec0e3f0524869b7b78f4ff +size 3499193216 diff --git a/Marco-LLM-AR-V3.i1-IQ3_XS.gguf b/Marco-LLM-AR-V3.i1-IQ3_XS.gguf new file mode 100644 index 0000000..c8b1363 --- /dev/null +++ b/Marco-LLM-AR-V3.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6efe52b582fbc214fd9c655596cb5a1c6618c68bb120f4f9a86fb77ec0d3a9f +size 3346256768 diff --git a/Marco-LLM-AR-V3.i1-IQ3_XXS.gguf b/Marco-LLM-AR-V3.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..482fc17 --- /dev/null +++ b/Marco-LLM-AR-V3.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d5d8f0c7c40c53a65038a4d534d66af65850ee0bc7a68af44f10e555e5d6eac +size 3114515328 diff --git a/Marco-LLM-AR-V3.i1-IQ4_NL.gguf b/Marco-LLM-AR-V3.i1-IQ4_NL.gguf new file mode 100644 index 0000000..2e445da --- /dev/null +++ b/Marco-LLM-AR-V3.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0de6397414cb8c1620819f50c175c55b24cd5a62f3eb50fe0102043c1d386195 +size 4437814144 diff --git a/Marco-LLM-AR-V3.i1-IQ4_XS.gguf b/Marco-LLM-AR-V3.i1-IQ4_XS.gguf new file mode 100644 index 0000000..db579e5 --- /dev/null +++ b/Marco-LLM-AR-V3.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e66b283ad72f6c2545a76fa91120a5a30108e4a8a7a98e01fbef17cb5e26d3a0 +size 4218473344 diff --git a/Marco-LLM-AR-V3.i1-Q2_K.gguf b/Marco-LLM-AR-V3.i1-Q2_K.gguf new file mode 100644 index 0000000..d31a53b --- /dev/null +++ b/Marco-LLM-AR-V3.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6dc72af5a5db9cb2bdf0543e7b7fa40da339ba344b369644f155420b315ae4f7 +size 3015940992 diff --git a/Marco-LLM-AR-V3.i1-Q2_K_S.gguf b/Marco-LLM-AR-V3.i1-Q2_K_S.gguf new file mode 100644 index 0000000..454a5bc --- /dev/null +++ b/Marco-LLM-AR-V3.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ae62540897226324f0a4c8685a4bbfc2807b002bbbb329743060c3460e060c1 +size 2834074496 diff --git a/Marco-LLM-AR-V3.i1-Q3_K_L.gguf b/Marco-LLM-AR-V3.i1-Q3_K_L.gguf new file mode 100644 index 0000000..4873760 --- /dev/null +++ b/Marco-LLM-AR-V3.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af8bb2c5a613232d5169f2fa10e0fb8de828664abefb5fa0f802fe9d6f771180 +size 4088460160 diff --git a/Marco-LLM-AR-V3.i1-Q3_K_M.gguf b/Marco-LLM-AR-V3.i1-Q3_K_M.gguf new file mode 100644 index 0000000..2be7b34 --- /dev/null +++ b/Marco-LLM-AR-V3.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:396f44e2c031d57b44336a9d521992c09cd193fe82f30f0706f49cacdb762299 +size 3808392064 diff --git a/Marco-LLM-AR-V3.i1-Q3_K_S.gguf b/Marco-LLM-AR-V3.i1-Q3_K_S.gguf new file mode 100644 index 0000000..f617934 --- /dev/null +++ b/Marco-LLM-AR-V3.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e9137b0fe445e7a02a9f2d73d680022b65cab3f320c7f9689197e39f63493ff +size 3492369280 diff --git a/Marco-LLM-AR-V3.i1-Q4_0.gguf b/Marco-LLM-AR-V3.i1-Q4_0.gguf new file mode 100644 index 0000000..ea4abb5 --- /dev/null +++ b/Marco-LLM-AR-V3.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:280343533d829c519c4d585fe3ad4458695e97ba8663bc2543335dc07f20242e +size 4444121984 diff --git a/Marco-LLM-AR-V3.i1-Q4_1.gguf b/Marco-LLM-AR-V3.i1-Q4_1.gguf new file mode 100644 index 0000000..4634a41 --- /dev/null +++ b/Marco-LLM-AR-V3.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5517ecefb6e6526434c4d06b961309e2d471d2ebb29cd0a360917be5d420104 +size 4873284480 diff --git a/Marco-LLM-AR-V3.i1-Q4_K_M.gguf b/Marco-LLM-AR-V3.i1-Q4_K_M.gguf new file mode 100644 index 0000000..fc460e0 --- /dev/null +++ b/Marco-LLM-AR-V3.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:064d515b8d23760344c0392c607cb5ca6af27216712bdeed36b46b97410a2151 +size 4683074432 diff --git a/Marco-LLM-AR-V3.i1-Q4_K_S.gguf b/Marco-LLM-AR-V3.i1-Q4_K_S.gguf new file mode 100644 index 0000000..036d20c --- /dev/null +++ b/Marco-LLM-AR-V3.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea567cd5c350d6949cfbeab36d3416a678478d5a6895302c9ba9cfd1dc2c9faf +size 4457769856 diff --git a/Marco-LLM-AR-V3.i1-Q5_K_M.gguf b/Marco-LLM-AR-V3.i1-Q5_K_M.gguf new file mode 100644 index 0000000..8245476 --- /dev/null +++ b/Marco-LLM-AR-V3.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6eae7f84adc6714c1983232cb67445426560228c60d01e7d21b2b12688530988 +size 5444832128 diff --git a/Marco-LLM-AR-V3.i1-Q5_K_S.gguf b/Marco-LLM-AR-V3.i1-Q5_K_S.gguf new file mode 100644 index 0000000..aefa74e --- /dev/null +++ b/Marco-LLM-AR-V3.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f701a7eed8ee4b0c00dfd8d2b7299e8eb6ba24233ce1fde048403b0054f05607 +size 5315177344 diff --git a/Marco-LLM-AR-V3.i1-Q6_K.gguf b/Marco-LLM-AR-V3.i1-Q6_K.gguf new file mode 100644 index 0000000..00383ec --- /dev/null +++ b/Marco-LLM-AR-V3.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8ff8dc4b6c5e461093b5ed7cd4bbcbbfc629adb9bcba17394c6bc7c1fe0727e +size 6254199680 diff --git a/README.md b/README.md new file mode 100644 index 0000000..a92850f --- /dev/null +++ b/README.md @@ -0,0 +1,78 @@ +--- +base_model: AIDC-AI/Marco-LLM-AR-V4 +language: +- ar +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- pretrained +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/AIDC-AI/Marco-LLM-AR-V4 + + +static quants are available at https://huggingface.co/mradermacher/Marco-LLM-AR-V3-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/Marco-LLM-AR-V3-i1-GGUF/resolve/main/Marco-LLM-AR-V3.i1-IQ1_S.gguf) | i1-IQ1_S | 2.0 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Marco-LLM-AR-V3-i1-GGUF/resolve/main/Marco-LLM-AR-V3.i1-IQ1_M.gguf) | i1-IQ1_M | 2.1 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Marco-LLM-AR-V3-i1-GGUF/resolve/main/Marco-LLM-AR-V3.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Marco-LLM-AR-V3-i1-GGUF/resolve/main/Marco-LLM-AR-V3.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/Marco-LLM-AR-V3-i1-GGUF/resolve/main/Marco-LLM-AR-V3.i1-IQ2_S.gguf) | i1-IQ2_S | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/Marco-LLM-AR-V3-i1-GGUF/resolve/main/Marco-LLM-AR-V3.i1-IQ2_M.gguf) | i1-IQ2_M | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Marco-LLM-AR-V3-i1-GGUF/resolve/main/Marco-LLM-AR-V3.i1-Q2_K_S.gguf) | i1-Q2_K_S | 2.9 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Marco-LLM-AR-V3-i1-GGUF/resolve/main/Marco-LLM-AR-V3.i1-Q2_K.gguf) | i1-Q2_K | 3.1 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Marco-LLM-AR-V3-i1-GGUF/resolve/main/Marco-LLM-AR-V3.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Marco-LLM-AR-V3-i1-GGUF/resolve/main/Marco-LLM-AR-V3.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/Marco-LLM-AR-V3-i1-GGUF/resolve/main/Marco-LLM-AR-V3.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.6 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Marco-LLM-AR-V3-i1-GGUF/resolve/main/Marco-LLM-AR-V3.i1-IQ3_S.gguf) | i1-IQ3_S | 3.6 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Marco-LLM-AR-V3-i1-GGUF/resolve/main/Marco-LLM-AR-V3.i1-IQ3_M.gguf) | i1-IQ3_M | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/Marco-LLM-AR-V3-i1-GGUF/resolve/main/Marco-LLM-AR-V3.i1-Q3_K_M.gguf) | i1-Q3_K_M | 3.9 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Marco-LLM-AR-V3-i1-GGUF/resolve/main/Marco-LLM-AR-V3.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.2 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Marco-LLM-AR-V3-i1-GGUF/resolve/main/Marco-LLM-AR-V3.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.3 | | +| [GGUF](https://huggingface.co/mradermacher/Marco-LLM-AR-V3-i1-GGUF/resolve/main/Marco-LLM-AR-V3.i1-IQ4_NL.gguf) | i1-IQ4_NL | 4.5 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/Marco-LLM-AR-V3-i1-GGUF/resolve/main/Marco-LLM-AR-V3.i1-Q4_0.gguf) | i1-Q4_0 | 4.5 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Marco-LLM-AR-V3-i1-GGUF/resolve/main/Marco-LLM-AR-V3.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.6 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Marco-LLM-AR-V3-i1-GGUF/resolve/main/Marco-LLM-AR-V3.i1-Q4_K_M.gguf) | i1-Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Marco-LLM-AR-V3-i1-GGUF/resolve/main/Marco-LLM-AR-V3.i1-Q4_1.gguf) | i1-Q4_1 | 5.0 | | +| [GGUF](https://huggingface.co/mradermacher/Marco-LLM-AR-V3-i1-GGUF/resolve/main/Marco-LLM-AR-V3.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/Marco-LLM-AR-V3-i1-GGUF/resolve/main/Marco-LLM-AR-V3.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/Marco-LLM-AR-V3-i1-GGUF/resolve/main/Marco-LLM-AR-V3.i1-Q6_K.gguf) | i1-Q6_K | 6.4 | practically like static Q6_K | + +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. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. + +