commit 7c8e662d38ff914b2ac2e64b1de50ff081c9be07 Author: ModelHub XC Date: Mon Jul 20 03:30:10 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen2.5-14B-Instruct-1M-Unalign-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..0079a24 --- /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 +imatrix.dat filter=lfs diff=lfs merge=lfs -text +Qwen2.5-14B-Instruct-1M-Unalign.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-14B-Instruct-1M-Unalign.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-14B-Instruct-1M-Unalign.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-14B-Instruct-1M-Unalign.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-14B-Instruct-1M-Unalign.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-14B-Instruct-1M-Unalign.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-14B-Instruct-1M-Unalign.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-14B-Instruct-1M-Unalign.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-14B-Instruct-1M-Unalign.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-14B-Instruct-1M-Unalign.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-14B-Instruct-1M-Unalign.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-14B-Instruct-1M-Unalign.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-14B-Instruct-1M-Unalign.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-14B-Instruct-1M-Unalign.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-14B-Instruct-1M-Unalign.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-14B-Instruct-1M-Unalign.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-14B-Instruct-1M-Unalign.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-14B-Instruct-1M-Unalign.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-14B-Instruct-1M-Unalign.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-14B-Instruct-1M-Unalign.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-14B-Instruct-1M-Unalign.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-14B-Instruct-1M-Unalign.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-14B-Instruct-1M-Unalign.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-14B-Instruct-1M-Unalign.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen2.5-14B-Instruct-1M-Unalign.i1-IQ1_M.gguf b/Qwen2.5-14B-Instruct-1M-Unalign.i1-IQ1_M.gguf new file mode 100644 index 0000000..5a3586d --- /dev/null +++ b/Qwen2.5-14B-Instruct-1M-Unalign.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2a4238b7fe476ab50d8416cefc2d7ec37a25a07cd49f64f26a760e4eb6cef62 +size 3872309504 diff --git a/Qwen2.5-14B-Instruct-1M-Unalign.i1-IQ1_S.gguf b/Qwen2.5-14B-Instruct-1M-Unalign.i1-IQ1_S.gguf new file mode 100644 index 0000000..6f027a6 --- /dev/null +++ b/Qwen2.5-14B-Instruct-1M-Unalign.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d5b30b648ca540df2cb42f23c333a5ab9e3bed5122f17ac5eff46ad039152cd +size 3607994624 diff --git a/Qwen2.5-14B-Instruct-1M-Unalign.i1-IQ2_M.gguf b/Qwen2.5-14B-Instruct-1M-Unalign.i1-IQ2_M.gguf new file mode 100644 index 0000000..55d0968 --- /dev/null +++ b/Qwen2.5-14B-Instruct-1M-Unalign.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22159aaabb4e1a0bef2a7ed105039463d19d44077f1eb71223379e52b17feaff +size 5356146944 diff --git a/Qwen2.5-14B-Instruct-1M-Unalign.i1-IQ2_S.gguf b/Qwen2.5-14B-Instruct-1M-Unalign.i1-IQ2_S.gguf new file mode 100644 index 0000000..ea7f08a --- /dev/null +++ b/Qwen2.5-14B-Instruct-1M-Unalign.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2f2399d136f823ee65ce56907773af482dd3218d744d0f5da8b8d704372f768 +size 5003727104 diff --git a/Qwen2.5-14B-Instruct-1M-Unalign.i1-IQ2_XS.gguf b/Qwen2.5-14B-Instruct-1M-Unalign.i1-IQ2_XS.gguf new file mode 100644 index 0000000..324523f --- /dev/null +++ b/Qwen2.5-14B-Instruct-1M-Unalign.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d4aa0913a924fef7a018a59e6812af7940cf9e50986e84c367bfd563019effc +size 4704575744 diff --git a/Qwen2.5-14B-Instruct-1M-Unalign.i1-IQ2_XXS.gguf b/Qwen2.5-14B-Instruct-1M-Unalign.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..6d608ea --- /dev/null +++ b/Qwen2.5-14B-Instruct-1M-Unalign.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b04ef0ad3a5dbf03873085d8e2c57fdd190bc133c2b458a015f97ce4904e4a3 +size 4312834304 diff --git a/Qwen2.5-14B-Instruct-1M-Unalign.i1-IQ3_M.gguf b/Qwen2.5-14B-Instruct-1M-Unalign.i1-IQ3_M.gguf new file mode 100644 index 0000000..79895cc --- /dev/null +++ b/Qwen2.5-14B-Instruct-1M-Unalign.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e17cd495df0c21a948b5c7928c562737e8dc0be501e3cfba9d67ad54c4c7858 +size 6916538624 diff --git a/Qwen2.5-14B-Instruct-1M-Unalign.i1-IQ3_S.gguf b/Qwen2.5-14B-Instruct-1M-Unalign.i1-IQ3_S.gguf new file mode 100644 index 0000000..1ff4046 --- /dev/null +++ b/Qwen2.5-14B-Instruct-1M-Unalign.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e0aa1f22b058479db6e2daefe93fe0ed714473b627d10122d319a4b8c9c4b3b +size 6693019904 diff --git a/Qwen2.5-14B-Instruct-1M-Unalign.i1-IQ3_XS.gguf b/Qwen2.5-14B-Instruct-1M-Unalign.i1-IQ3_XS.gguf new file mode 100644 index 0000000..c614923 --- /dev/null +++ b/Qwen2.5-14B-Instruct-1M-Unalign.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b3205e9f08e2c315e0a67a5975823bead9de3d6fc50e5f8e92bbf98128a5bba +size 6383362304 diff --git a/Qwen2.5-14B-Instruct-1M-Unalign.i1-IQ3_XXS.gguf b/Qwen2.5-14B-Instruct-1M-Unalign.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..a753c8a --- /dev/null +++ b/Qwen2.5-14B-Instruct-1M-Unalign.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:870f4a2f0a915d0e32931d9eda13bd0d272f204bfccced5bc95948af37b77cca +size 5946708224 diff --git a/Qwen2.5-14B-Instruct-1M-Unalign.i1-IQ4_NL.gguf b/Qwen2.5-14B-Instruct-1M-Unalign.i1-IQ4_NL.gguf new file mode 100644 index 0000000..29c8942 --- /dev/null +++ b/Qwen2.5-14B-Instruct-1M-Unalign.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd0a8e72a9f888ad3e136cb4b04a596232489c24ef3bdfff697ea674e3453a0d +size 8549183744 diff --git a/Qwen2.5-14B-Instruct-1M-Unalign.i1-IQ4_XS.gguf b/Qwen2.5-14B-Instruct-1M-Unalign.i1-IQ4_XS.gguf new file mode 100644 index 0000000..9c97121 --- /dev/null +++ b/Qwen2.5-14B-Instruct-1M-Unalign.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a70e273345e89e4dc299538a1940dc58418ca416e6b0398f599948afce406b11 +size 8119841024 diff --git a/Qwen2.5-14B-Instruct-1M-Unalign.i1-Q2_K.gguf b/Qwen2.5-14B-Instruct-1M-Unalign.i1-Q2_K.gguf new file mode 100644 index 0000000..2ba33a4 --- /dev/null +++ b/Qwen2.5-14B-Instruct-1M-Unalign.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08ce3979a17e1288277d0fd077ab0b68d79c52c0497f7d338f0533f14764190f +size 5770498304 diff --git a/Qwen2.5-14B-Instruct-1M-Unalign.i1-Q2_K_S.gguf b/Qwen2.5-14B-Instruct-1M-Unalign.i1-Q2_K_S.gguf new file mode 100644 index 0000000..7a73036 --- /dev/null +++ b/Qwen2.5-14B-Instruct-1M-Unalign.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:324842c41b65fb4e073c5a1651ae5a4aecc786ddd9d8ed8f2484197bef706073 +size 5397188864 diff --git a/Qwen2.5-14B-Instruct-1M-Unalign.i1-Q3_K_L.gguf b/Qwen2.5-14B-Instruct-1M-Unalign.i1-Q3_K_L.gguf new file mode 100644 index 0000000..308d603 --- /dev/null +++ b/Qwen2.5-14B-Instruct-1M-Unalign.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bad0218a106df554fa09fc2b31a072b74572b4d195e8538e85b352d939926943 +size 7924769024 diff --git a/Qwen2.5-14B-Instruct-1M-Unalign.i1-Q3_K_M.gguf b/Qwen2.5-14B-Instruct-1M-Unalign.i1-Q3_K_M.gguf new file mode 100644 index 0000000..4a53a31 --- /dev/null +++ b/Qwen2.5-14B-Instruct-1M-Unalign.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed89a10282b93c7f1b3305ce10cc7b97e8af0c81dd8007a7820632396d6580b2 +size 7339204864 diff --git a/Qwen2.5-14B-Instruct-1M-Unalign.i1-Q3_K_S.gguf b/Qwen2.5-14B-Instruct-1M-Unalign.i1-Q3_K_S.gguf new file mode 100644 index 0000000..9cd8dc4 --- /dev/null +++ b/Qwen2.5-14B-Instruct-1M-Unalign.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97362498d00b7489aaf988d81f7be3117adf2f049e4fe16f263b276b45bb0702 +size 6659596544 diff --git a/Qwen2.5-14B-Instruct-1M-Unalign.i1-Q4_0.gguf b/Qwen2.5-14B-Instruct-1M-Unalign.i1-Q4_0.gguf new file mode 100644 index 0000000..d91d7cb --- /dev/null +++ b/Qwen2.5-14B-Instruct-1M-Unalign.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd8594b4e6cc3af751562668f6ac10e315f260efe3fc26be8eb26dfd2d5507b7 +size 8544268544 diff --git a/Qwen2.5-14B-Instruct-1M-Unalign.i1-Q4_1.gguf b/Qwen2.5-14B-Instruct-1M-Unalign.i1-Q4_1.gguf new file mode 100644 index 0000000..be4f3c6 --- /dev/null +++ b/Qwen2.5-14B-Instruct-1M-Unalign.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2aa730dafde285c484f3dbb1c09933460fb82b952939e2ddca3e83792460a40c +size 9392140544 diff --git a/Qwen2.5-14B-Instruct-1M-Unalign.i1-Q4_K_M.gguf b/Qwen2.5-14B-Instruct-1M-Unalign.i1-Q4_K_M.gguf new file mode 100644 index 0000000..90620ac --- /dev/null +++ b/Qwen2.5-14B-Instruct-1M-Unalign.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11b2eb96a8a4d512fceb3344dccc694972801c964cf748d723fdf436bc368915 +size 8988111104 diff --git a/Qwen2.5-14B-Instruct-1M-Unalign.i1-Q4_K_S.gguf b/Qwen2.5-14B-Instruct-1M-Unalign.i1-Q4_K_S.gguf new file mode 100644 index 0000000..0a4fe93 --- /dev/null +++ b/Qwen2.5-14B-Instruct-1M-Unalign.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16d73ec1dfee566f915ab37491755b154036b796fd78580f58566c846ba2d9d5 +size 8573432064 diff --git a/Qwen2.5-14B-Instruct-1M-Unalign.i1-Q5_K_M.gguf b/Qwen2.5-14B-Instruct-1M-Unalign.i1-Q5_K_M.gguf new file mode 100644 index 0000000..2b0dc08 --- /dev/null +++ b/Qwen2.5-14B-Instruct-1M-Unalign.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9777c47630445d82c88f0b7f1d4b6310017171e54550635c1fb6869ec37fe1a +size 10508873984 diff --git a/Qwen2.5-14B-Instruct-1M-Unalign.i1-Q5_K_S.gguf b/Qwen2.5-14B-Instruct-1M-Unalign.i1-Q5_K_S.gguf new file mode 100644 index 0000000..b54e71b --- /dev/null +++ b/Qwen2.5-14B-Instruct-1M-Unalign.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc010fc8c6df1e3134bfcf80eee944078799948e84749245742be8d5885f5002 +size 10266554624 diff --git a/Qwen2.5-14B-Instruct-1M-Unalign.i1-Q6_K.gguf b/Qwen2.5-14B-Instruct-1M-Unalign.i1-Q6_K.gguf new file mode 100644 index 0000000..28632df --- /dev/null +++ b/Qwen2.5-14B-Instruct-1M-Unalign.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45584888c6c1ecbe66d4dbe6318172e0858ccc23b1a0fc39421381eaab69a0e9 +size 12124684544 diff --git a/README.md b/README.md new file mode 100644 index 0000000..3891134 --- /dev/null +++ b/README.md @@ -0,0 +1,75 @@ +--- +base_model: ToastyPigeon/Qwen2.5-14B-Instruct-1M-Unalign +language: +- en +library_name: transformers +quantized_by: mradermacher +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/ToastyPigeon/Qwen2.5-14B-Instruct-1M-Unalign + + +static quants are available at https://huggingface.co/mradermacher/Qwen2.5-14B-Instruct-1M-Unalign-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/Qwen2.5-14B-Instruct-1M-Unalign-i1-GGUF/resolve/main/Qwen2.5-14B-Instruct-1M-Unalign.i1-IQ1_S.gguf) | i1-IQ1_S | 3.7 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Instruct-1M-Unalign-i1-GGUF/resolve/main/Qwen2.5-14B-Instruct-1M-Unalign.i1-IQ1_M.gguf) | i1-IQ1_M | 4.0 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Instruct-1M-Unalign-i1-GGUF/resolve/main/Qwen2.5-14B-Instruct-1M-Unalign.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Instruct-1M-Unalign-i1-GGUF/resolve/main/Qwen2.5-14B-Instruct-1M-Unalign.i1-IQ2_XS.gguf) | i1-IQ2_XS | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Instruct-1M-Unalign-i1-GGUF/resolve/main/Qwen2.5-14B-Instruct-1M-Unalign.i1-IQ2_S.gguf) | i1-IQ2_S | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Instruct-1M-Unalign-i1-GGUF/resolve/main/Qwen2.5-14B-Instruct-1M-Unalign.i1-IQ2_M.gguf) | i1-IQ2_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Instruct-1M-Unalign-i1-GGUF/resolve/main/Qwen2.5-14B-Instruct-1M-Unalign.i1-Q2_K_S.gguf) | i1-Q2_K_S | 5.5 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Instruct-1M-Unalign-i1-GGUF/resolve/main/Qwen2.5-14B-Instruct-1M-Unalign.i1-Q2_K.gguf) | i1-Q2_K | 5.9 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Instruct-1M-Unalign-i1-GGUF/resolve/main/Qwen2.5-14B-Instruct-1M-Unalign.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 6.0 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Instruct-1M-Unalign-i1-GGUF/resolve/main/Qwen2.5-14B-Instruct-1M-Unalign.i1-IQ3_XS.gguf) | i1-IQ3_XS | 6.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Instruct-1M-Unalign-i1-GGUF/resolve/main/Qwen2.5-14B-Instruct-1M-Unalign.i1-Q3_K_S.gguf) | i1-Q3_K_S | 6.8 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Instruct-1M-Unalign-i1-GGUF/resolve/main/Qwen2.5-14B-Instruct-1M-Unalign.i1-IQ3_S.gguf) | i1-IQ3_S | 6.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Instruct-1M-Unalign-i1-GGUF/resolve/main/Qwen2.5-14B-Instruct-1M-Unalign.i1-IQ3_M.gguf) | i1-IQ3_M | 7.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Instruct-1M-Unalign-i1-GGUF/resolve/main/Qwen2.5-14B-Instruct-1M-Unalign.i1-Q3_K_M.gguf) | i1-Q3_K_M | 7.4 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Instruct-1M-Unalign-i1-GGUF/resolve/main/Qwen2.5-14B-Instruct-1M-Unalign.i1-Q3_K_L.gguf) | i1-Q3_K_L | 8.0 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Instruct-1M-Unalign-i1-GGUF/resolve/main/Qwen2.5-14B-Instruct-1M-Unalign.i1-IQ4_XS.gguf) | i1-IQ4_XS | 8.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Instruct-1M-Unalign-i1-GGUF/resolve/main/Qwen2.5-14B-Instruct-1M-Unalign.i1-Q4_0.gguf) | i1-Q4_0 | 8.6 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Instruct-1M-Unalign-i1-GGUF/resolve/main/Qwen2.5-14B-Instruct-1M-Unalign.i1-IQ4_NL.gguf) | i1-IQ4_NL | 8.6 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Instruct-1M-Unalign-i1-GGUF/resolve/main/Qwen2.5-14B-Instruct-1M-Unalign.i1-Q4_K_S.gguf) | i1-Q4_K_S | 8.7 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Instruct-1M-Unalign-i1-GGUF/resolve/main/Qwen2.5-14B-Instruct-1M-Unalign.i1-Q4_K_M.gguf) | i1-Q4_K_M | 9.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Instruct-1M-Unalign-i1-GGUF/resolve/main/Qwen2.5-14B-Instruct-1M-Unalign.i1-Q4_1.gguf) | i1-Q4_1 | 9.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Instruct-1M-Unalign-i1-GGUF/resolve/main/Qwen2.5-14B-Instruct-1M-Unalign.i1-Q5_K_S.gguf) | i1-Q5_K_S | 10.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Instruct-1M-Unalign-i1-GGUF/resolve/main/Qwen2.5-14B-Instruct-1M-Unalign.i1-Q5_K_M.gguf) | i1-Q5_K_M | 10.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Instruct-1M-Unalign-i1-GGUF/resolve/main/Qwen2.5-14B-Instruct-1M-Unalign.i1-Q6_K.gguf) | i1-Q6_K | 12.2 | 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. + + diff --git a/imatrix.dat b/imatrix.dat new file mode 100644 index 0000000..3f61239 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c2e33f7ec15e5520e264509342e0e767b9c4c44ee5d8264440e57ce71d111c5 +size 8563597