commit a00bb5d4126804b20cc54605eaa068a4f6f7f62d Author: ModelHub XC Date: Wed Oct 7 08:33:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/L3.1-Phantasmav2-12B-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..abd00b8 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,60 @@ +*.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 +L3.1-Phantasmav2-12B.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Phantasmav2-12B.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Phantasmav2-12B.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Phantasmav2-12B.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Phantasmav2-12B.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Phantasmav2-12B.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Phantasmav2-12B.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Phantasmav2-12B.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Phantasmav2-12B.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Phantasmav2-12B.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Phantasmav2-12B.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Phantasmav2-12B.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Phantasmav2-12B.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Phantasmav2-12B.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Phantasmav2-12B.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Phantasmav2-12B.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Phantasmav2-12B.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Phantasmav2-12B.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Phantasmav2-12B.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Phantasmav2-12B.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Phantasmav2-12B.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Phantasmav2-12B.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Phantasmav2-12B.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Phantasmav2-12B.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Phantasmav2-12B.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/L3.1-Phantasmav2-12B.i1-IQ1_M.gguf b/L3.1-Phantasmav2-12B.i1-IQ1_M.gguf new file mode 100644 index 0000000..01adb9d --- /dev/null +++ b/L3.1-Phantasmav2-12B.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:64084efdeb8f1335a8b6038e45520ebbd14a56b97f1175fef41eeff18a00a881 +size 3072083872 diff --git a/L3.1-Phantasmav2-12B.i1-IQ1_S.gguf b/L3.1-Phantasmav2-12B.i1-IQ1_S.gguf new file mode 100644 index 0000000..dce7e3a --- /dev/null +++ b/L3.1-Phantasmav2-12B.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:121e54a74f68d4f2c5ef2ecab55e4464d6476f6a7ea896c8bb49bb09185e7a5c +size 2849327008 diff --git a/L3.1-Phantasmav2-12B.i1-IQ2_M.gguf b/L3.1-Phantasmav2-12B.i1-IQ2_M.gguf new file mode 100644 index 0000000..0c07c1e --- /dev/null +++ b/L3.1-Phantasmav2-12B.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:397b8b27222f7eaa2e49c44e51f3377ec9bc80ef3985747eb693a41e4614792a +size 4270693280 diff --git a/L3.1-Phantasmav2-12B.i1-IQ2_S.gguf b/L3.1-Phantasmav2-12B.i1-IQ2_S.gguf new file mode 100644 index 0000000..53640c4 --- /dev/null +++ b/L3.1-Phantasmav2-12B.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cbea1d60411910eb2c77ea20038df5e593147ad2fcdf65d65ab207032a37105e +size 3973684128 diff --git a/L3.1-Phantasmav2-12B.i1-IQ2_XS.gguf b/L3.1-Phantasmav2-12B.i1-IQ2_XS.gguf new file mode 100644 index 0000000..37467cf --- /dev/null +++ b/L3.1-Phantasmav2-12B.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7cee17aeceb3f25d0928b9f9e18778e82d67e7e84360321ea988dad3244e668c +size 3766568864 diff --git a/L3.1-Phantasmav2-12B.i1-IQ2_XXS.gguf b/L3.1-Phantasmav2-12B.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..c85c9c0 --- /dev/null +++ b/L3.1-Phantasmav2-12B.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6840053253ac2abd020c218080dbe5798a1c32ce179754dd01c2423edcc49e5 +size 3443345312 diff --git a/L3.1-Phantasmav2-12B.i1-IQ3_M.gguf b/L3.1-Phantasmav2-12B.i1-IQ3_M.gguf new file mode 100644 index 0000000..cde45a1 --- /dev/null +++ b/L3.1-Phantasmav2-12B.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7cb80b82b10c409f1d58ba34e70fc4e8ba9fc2402785527fc7956c85f330508a +size 5538217888 diff --git a/L3.1-Phantasmav2-12B.i1-IQ3_S.gguf b/L3.1-Phantasmav2-12B.i1-IQ3_S.gguf new file mode 100644 index 0000000..03c111f --- /dev/null +++ b/L3.1-Phantasmav2-12B.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e69493df39a6b641e1a8feb207422473036b6bc58e3659d26a2b2a4cec51828 +size 5380013984 diff --git a/L3.1-Phantasmav2-12B.i1-IQ3_XS.gguf b/L3.1-Phantasmav2-12B.i1-IQ3_XS.gguf new file mode 100644 index 0000000..4cad4a9 --- /dev/null +++ b/L3.1-Phantasmav2-12B.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd7cdfd56b61667f1eeb1d85b3034f5467ad51b9662efcd3c714136a31e537f1 +size 5127176096 diff --git a/L3.1-Phantasmav2-12B.i1-IQ3_XXS.gguf b/L3.1-Phantasmav2-12B.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..bda33b5 --- /dev/null +++ b/L3.1-Phantasmav2-12B.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf3df78e29c5a520829ba3bf733abd01f8b1932b6da8d01ee2f7919d8daec668 +size 4782660512 diff --git a/L3.1-Phantasmav2-12B.i1-IQ4_NL.gguf b/L3.1-Phantasmav2-12B.i1-IQ4_NL.gguf new file mode 100644 index 0000000..796892a --- /dev/null +++ b/L3.1-Phantasmav2-12B.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c15f515f9707c7f15aa3beba86d3379567556bd872cbee047d96686012f9168 +size 6896509856 diff --git a/L3.1-Phantasmav2-12B.i1-IQ4_XS.gguf b/L3.1-Phantasmav2-12B.i1-IQ4_XS.gguf new file mode 100644 index 0000000..8edf325 --- /dev/null +++ b/L3.1-Phantasmav2-12B.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e349d9e48ed0e88db7ad7392a3df62e0f38239267b8b7d472baf3ac9d59e7e46 +size 6545855392 diff --git a/L3.1-Phantasmav2-12B.i1-Q2_K.gguf b/L3.1-Phantasmav2-12B.i1-Q2_K.gguf new file mode 100644 index 0000000..90ee622 --- /dev/null +++ b/L3.1-Phantasmav2-12B.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f33c0d8ce8d64d0a2d3ff1f9f4e10bec11a5e2d419bfbc3afe08d767f379a280 +size 4623772576 diff --git a/L3.1-Phantasmav2-12B.i1-Q2_K_S.gguf b/L3.1-Phantasmav2-12B.i1-Q2_K_S.gguf new file mode 100644 index 0000000..e3fe26d --- /dev/null +++ b/L3.1-Phantasmav2-12B.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ca659b61fad6bbd911763b41d249d89e9a23a4e8c87f0196df8c1072c8c4c31 +size 4322962336 diff --git a/L3.1-Phantasmav2-12B.i1-Q3_K_L.gguf b/L3.1-Phantasmav2-12B.i1-Q3_K_L.gguf new file mode 100644 index 0000000..895eb37 --- /dev/null +++ b/L3.1-Phantasmav2-12B.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:503f35b2933871ecb5bdd29b2cda3abbd23946635bb466239239db8ded743f12 +size 6379437984 diff --git a/L3.1-Phantasmav2-12B.i1-Q3_K_M.gguf b/L3.1-Phantasmav2-12B.i1-Q3_K_M.gguf new file mode 100644 index 0000000..eea6e84 --- /dev/null +++ b/L3.1-Phantasmav2-12B.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:29426c61f93b4e42bd4ad43c34b4c494c960ff14d6f34e781646d3160d806eb1 +size 5904433056 diff --git a/L3.1-Phantasmav2-12B.i1-Q3_K_S.gguf b/L3.1-Phantasmav2-12B.i1-Q3_K_S.gguf new file mode 100644 index 0000000..eaef926 --- /dev/null +++ b/L3.1-Phantasmav2-12B.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a71c362e3e4b4c8d9b2e281690efc556703659a955c55346aca44e0e42ea0c3 +size 5352161184 diff --git a/L3.1-Phantasmav2-12B.i1-Q4_0.gguf b/L3.1-Phantasmav2-12B.i1-Q4_0.gguf new file mode 100644 index 0000000..181506e --- /dev/null +++ b/L3.1-Phantasmav2-12B.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e689197bc81acab9b48f135dc52fcf79664a122169cf2d65034f0a715730f830 +size 6892315552 diff --git a/L3.1-Phantasmav2-12B.i1-Q4_1.gguf b/L3.1-Phantasmav2-12B.i1-Q4_1.gguf new file mode 100644 index 0000000..7561a08 --- /dev/null +++ b/L3.1-Phantasmav2-12B.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04b9d90f9c057f826cc8d198fb66f36446db68349c686a55f9c78b448e2aab56 +size 7584711584 diff --git a/L3.1-Phantasmav2-12B.i1-Q4_K_M.gguf b/L3.1-Phantasmav2-12B.i1-Q4_K_M.gguf new file mode 100644 index 0000000..11b79d2 --- /dev/null +++ b/L3.1-Phantasmav2-12B.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6234d5ede3774820740b3adca69e848c1f1b8e2e138fe04ccb616e3072e48d86 +size 7275799456 diff --git a/L3.1-Phantasmav2-12B.i1-Q4_K_S.gguf b/L3.1-Phantasmav2-12B.i1-Q4_K_S.gguf new file mode 100644 index 0000000..2332ae9 --- /dev/null +++ b/L3.1-Phantasmav2-12B.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8382ecd304c6d2b82969ff8f4bd52f99c9179e7474f14b1e384f5bb9e328b7e1 +size 6916432800 diff --git a/L3.1-Phantasmav2-12B.i1-Q5_K_M.gguf b/L3.1-Phantasmav2-12B.i1-Q5_K_M.gguf new file mode 100644 index 0000000..6c42a4d --- /dev/null +++ b/L3.1-Phantasmav2-12B.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44d7cb108ae1e31d1d88139afc5ea80b3ea2256fbc7e3eaebce660a365d02f1e +size 8508023712 diff --git a/L3.1-Phantasmav2-12B.i1-Q5_K_S.gguf b/L3.1-Phantasmav2-12B.i1-Q5_K_S.gguf new file mode 100644 index 0000000..9ebb645 --- /dev/null +++ b/L3.1-Phantasmav2-12B.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d478d6c77e3fdd26bb8215933a88354a39a8b7fbb0df472b90d77acb6714837e +size 8299127712 diff --git a/L3.1-Phantasmav2-12B.i1-Q6_K.gguf b/L3.1-Phantasmav2-12B.i1-Q6_K.gguf new file mode 100644 index 0000000..4938f45 --- /dev/null +++ b/L3.1-Phantasmav2-12B.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8c11799cd298db4d8b9d4a1493e8a4053afc99c930ca9fed635fe0abb2c2673 +size 9817261984 diff --git a/L3.1-Phantasmav2-12B.imatrix.gguf b/L3.1-Phantasmav2-12B.imatrix.gguf new file mode 100644 index 0000000..a50c233 --- /dev/null +++ b/L3.1-Phantasmav2-12B.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a950c269761ec29cb0c369980254900fbfebba699886f9f7630bd61a83d9562 +size 7836224 diff --git a/README.md b/README.md new file mode 100644 index 0000000..466bec6 --- /dev/null +++ b/README.md @@ -0,0 +1,87 @@ +--- +base_model: kromcomp/L3.1-Phantasmav2-12B +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + + + + +weighted/imatrix quants of https://huggingface.co/kromcomp/L3.1-Phantasmav2-12B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#L3.1-Phantasmav2-12B-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/L3.1-Phantasmav2-12B-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/L3.1-Phantasmav2-12B-i1-GGUF/resolve/main/L3.1-Phantasmav2-12B.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Phantasmav2-12B-i1-GGUF/resolve/main/L3.1-Phantasmav2-12B.i1-IQ1_S.gguf) | i1-IQ1_S | 2.9 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Phantasmav2-12B-i1-GGUF/resolve/main/L3.1-Phantasmav2-12B.i1-IQ1_M.gguf) | i1-IQ1_M | 3.2 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Phantasmav2-12B-i1-GGUF/resolve/main/L3.1-Phantasmav2-12B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 3.5 | | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Phantasmav2-12B-i1-GGUF/resolve/main/L3.1-Phantasmav2-12B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Phantasmav2-12B-i1-GGUF/resolve/main/L3.1-Phantasmav2-12B.i1-IQ2_S.gguf) | i1-IQ2_S | 4.1 | | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Phantasmav2-12B-i1-GGUF/resolve/main/L3.1-Phantasmav2-12B.i1-IQ2_M.gguf) | i1-IQ2_M | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Phantasmav2-12B-i1-GGUF/resolve/main/L3.1-Phantasmav2-12B.i1-Q2_K_S.gguf) | i1-Q2_K_S | 4.4 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Phantasmav2-12B-i1-GGUF/resolve/main/L3.1-Phantasmav2-12B.i1-Q2_K.gguf) | i1-Q2_K | 4.7 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Phantasmav2-12B-i1-GGUF/resolve/main/L3.1-Phantasmav2-12B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 4.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Phantasmav2-12B-i1-GGUF/resolve/main/L3.1-Phantasmav2-12B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Phantasmav2-12B-i1-GGUF/resolve/main/L3.1-Phantasmav2-12B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 5.5 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Phantasmav2-12B-i1-GGUF/resolve/main/L3.1-Phantasmav2-12B.i1-IQ3_S.gguf) | i1-IQ3_S | 5.5 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Phantasmav2-12B-i1-GGUF/resolve/main/L3.1-Phantasmav2-12B.i1-IQ3_M.gguf) | i1-IQ3_M | 5.6 | | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Phantasmav2-12B-i1-GGUF/resolve/main/L3.1-Phantasmav2-12B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 6.0 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Phantasmav2-12B-i1-GGUF/resolve/main/L3.1-Phantasmav2-12B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 6.5 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Phantasmav2-12B-i1-GGUF/resolve/main/L3.1-Phantasmav2-12B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 6.6 | | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Phantasmav2-12B-i1-GGUF/resolve/main/L3.1-Phantasmav2-12B.i1-Q4_0.gguf) | i1-Q4_0 | 7.0 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Phantasmav2-12B-i1-GGUF/resolve/main/L3.1-Phantasmav2-12B.i1-IQ4_NL.gguf) | i1-IQ4_NL | 7.0 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Phantasmav2-12B-i1-GGUF/resolve/main/L3.1-Phantasmav2-12B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 7.0 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Phantasmav2-12B-i1-GGUF/resolve/main/L3.1-Phantasmav2-12B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 7.4 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Phantasmav2-12B-i1-GGUF/resolve/main/L3.1-Phantasmav2-12B.i1-Q4_1.gguf) | i1-Q4_1 | 7.7 | | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Phantasmav2-12B-i1-GGUF/resolve/main/L3.1-Phantasmav2-12B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 8.4 | | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Phantasmav2-12B-i1-GGUF/resolve/main/L3.1-Phantasmav2-12B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 8.6 | | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Phantasmav2-12B-i1-GGUF/resolve/main/L3.1-Phantasmav2-12B.i1-Q6_K.gguf) | i1-Q6_K | 9.9 | 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. + +