commit 07747830d87928564192bcaa95d57c611fbf5a8b Author: ModelHub XC Date: Sat Apr 25 08:50:35 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Deep-Reasoning-Llama-3.2-Enigma-3B-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..c745836 --- /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 +Deep-Reasoning-Llama-3.2-Enigma-3B.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Deep-Reasoning-Llama-3.2-Enigma-3B.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Deep-Reasoning-Llama-3.2-Enigma-3B.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Deep-Reasoning-Llama-3.2-Enigma-3B.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Deep-Reasoning-Llama-3.2-Enigma-3B.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Deep-Reasoning-Llama-3.2-Enigma-3B.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Deep-Reasoning-Llama-3.2-Enigma-3B.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Deep-Reasoning-Llama-3.2-Enigma-3B.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Deep-Reasoning-Llama-3.2-Enigma-3B.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Deep-Reasoning-Llama-3.2-Enigma-3B.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Deep-Reasoning-Llama-3.2-Enigma-3B.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Deep-Reasoning-Llama-3.2-Enigma-3B.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Deep-Reasoning-Llama-3.2-Enigma-3B.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Deep-Reasoning-Llama-3.2-Enigma-3B.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Deep-Reasoning-Llama-3.2-Enigma-3B.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Deep-Reasoning-Llama-3.2-Enigma-3B.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Deep-Reasoning-Llama-3.2-Enigma-3B.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Deep-Reasoning-Llama-3.2-Enigma-3B.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Deep-Reasoning-Llama-3.2-Enigma-3B.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Deep-Reasoning-Llama-3.2-Enigma-3B.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Deep-Reasoning-Llama-3.2-Enigma-3B.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Deep-Reasoning-Llama-3.2-Enigma-3B.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Deep-Reasoning-Llama-3.2-Enigma-3B.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Deep-Reasoning-Llama-3.2-Enigma-3B.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Deep-Reasoning-Llama-3.2-Enigma-3B.i1-IQ1_M.gguf b/Deep-Reasoning-Llama-3.2-Enigma-3B.i1-IQ1_M.gguf new file mode 100644 index 0000000..378e587 --- /dev/null +++ b/Deep-Reasoning-Llama-3.2-Enigma-3B.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9378a77f236e0f7f299e82faa5db5652167643910105939c27383e95f39bab38 +size 924191936 diff --git a/Deep-Reasoning-Llama-3.2-Enigma-3B.i1-IQ1_S.gguf b/Deep-Reasoning-Llama-3.2-Enigma-3B.i1-IQ1_S.gguf new file mode 100644 index 0000000..79d4707 --- /dev/null +++ b/Deep-Reasoning-Llama-3.2-Enigma-3B.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93cdb35e045d0b6ed8565dc66c8ed9e8afc994dc514499d115de076b42baadbe +size 868158656 diff --git a/Deep-Reasoning-Llama-3.2-Enigma-3B.i1-IQ2_M.gguf b/Deep-Reasoning-Llama-3.2-Enigma-3B.i1-IQ2_M.gguf new file mode 100644 index 0000000..de2c8ec --- /dev/null +++ b/Deep-Reasoning-Llama-3.2-Enigma-3B.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:033d40f0c2d9ffe0fa1d1e1eef2b09c877c7e09f2ed92fb0e632391437c6f6d6 +size 1229032640 diff --git a/Deep-Reasoning-Llama-3.2-Enigma-3B.i1-IQ2_S.gguf b/Deep-Reasoning-Llama-3.2-Enigma-3B.i1-IQ2_S.gguf new file mode 100644 index 0000000..e4eeac2 --- /dev/null +++ b/Deep-Reasoning-Llama-3.2-Enigma-3B.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a6d1ed935be1fd9242d3e759069246afbd839ce173d2267ce1e44e452b1f262e +size 1154321600 diff --git a/Deep-Reasoning-Llama-3.2-Enigma-3B.i1-IQ2_XS.gguf b/Deep-Reasoning-Llama-3.2-Enigma-3B.i1-IQ2_XS.gguf new file mode 100644 index 0000000..95a5ada --- /dev/null +++ b/Deep-Reasoning-Llama-3.2-Enigma-3B.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54126fcaa7ec9d665eb729c94b2897ae747744afcff89d685825504211c8c851 +size 1100549312 diff --git a/Deep-Reasoning-Llama-3.2-Enigma-3B.i1-IQ2_XXS.gguf b/Deep-Reasoning-Llama-3.2-Enigma-3B.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..e7a66d6 --- /dev/null +++ b/Deep-Reasoning-Llama-3.2-Enigma-3B.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1da416af48fa3fd808ddd8c225bf4e0acee7299ab364cdcdce6687552baa5c5d +size 1017580736 diff --git a/Deep-Reasoning-Llama-3.2-Enigma-3B.i1-IQ3_M.gguf b/Deep-Reasoning-Llama-3.2-Enigma-3B.i1-IQ3_M.gguf new file mode 100644 index 0000000..32c52be --- /dev/null +++ b/Deep-Reasoning-Llama-3.2-Enigma-3B.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:800882ab65a56abd64bcf6db30dda9011bed3e3a1b75f0ce0640f661a08ae699 +size 1599669440 diff --git a/Deep-Reasoning-Llama-3.2-Enigma-3B.i1-IQ3_S.gguf b/Deep-Reasoning-Llama-3.2-Enigma-3B.i1-IQ3_S.gguf new file mode 100644 index 0000000..cb8bcb1 --- /dev/null +++ b/Deep-Reasoning-Llama-3.2-Enigma-3B.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f29583212b218522bae49fc0c9c5d3f95d485bb811f54996563375df884fa2f1 +size 1542849728 diff --git a/Deep-Reasoning-Llama-3.2-Enigma-3B.i1-IQ3_XS.gguf b/Deep-Reasoning-Llama-3.2-Enigma-3B.i1-IQ3_XS.gguf new file mode 100644 index 0000000..2a2a082 --- /dev/null +++ b/Deep-Reasoning-Llama-3.2-Enigma-3B.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa6756564e1ffa3d9eb4eae4d0cd123203bed24dd6803a3651f1c4fae87a6a2a +size 1476789440 diff --git a/Deep-Reasoning-Llama-3.2-Enigma-3B.i1-IQ3_XXS.gguf b/Deep-Reasoning-Llama-3.2-Enigma-3B.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..542348f --- /dev/null +++ b/Deep-Reasoning-Llama-3.2-Enigma-3B.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57e86426e3dd4eafa8a23313bea104ab49ca1ed248cf0d77859d51297c2a021f +size 1348766912 diff --git a/Deep-Reasoning-Llama-3.2-Enigma-3B.i1-IQ4_NL.gguf b/Deep-Reasoning-Llama-3.2-Enigma-3B.i1-IQ4_NL.gguf new file mode 100644 index 0000000..e7ec30d --- /dev/null +++ b/Deep-Reasoning-Llama-3.2-Enigma-3B.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77a550752c9d1e39cdbae8f9c6ce681346e75b954335596597cab229d1396256 +size 1917191360 diff --git a/Deep-Reasoning-Llama-3.2-Enigma-3B.i1-IQ4_XS.gguf b/Deep-Reasoning-Llama-3.2-Enigma-3B.i1-IQ4_XS.gguf new file mode 100644 index 0000000..8938971 --- /dev/null +++ b/Deep-Reasoning-Llama-3.2-Enigma-3B.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:945a7f0fbe69b5286dc1d412db6c647a983e6ad19fb827a7358e1de8b18cb9e9 +size 1829110976 diff --git a/Deep-Reasoning-Llama-3.2-Enigma-3B.i1-Q2_K.gguf b/Deep-Reasoning-Llama-3.2-Enigma-3B.i1-Q2_K.gguf new file mode 100644 index 0000000..4882638 --- /dev/null +++ b/Deep-Reasoning-Llama-3.2-Enigma-3B.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:815978a5480478b4a5e4245c5f706327c8260ada7f40cc4b14bb63ffbbae83ce +size 1363936448 diff --git a/Deep-Reasoning-Llama-3.2-Enigma-3B.i1-Q2_K_S.gguf b/Deep-Reasoning-Llama-3.2-Enigma-3B.i1-Q2_K_S.gguf new file mode 100644 index 0000000..c4483a7 --- /dev/null +++ b/Deep-Reasoning-Llama-3.2-Enigma-3B.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4314d44bf9683c9b09c7f17e74ff05cff54f446933b67e53bebb404dc8d769f3 +size 1274283200 diff --git a/Deep-Reasoning-Llama-3.2-Enigma-3B.i1-Q3_K_L.gguf b/Deep-Reasoning-Llama-3.2-Enigma-3B.i1-Q3_K_L.gguf new file mode 100644 index 0000000..22ef44d --- /dev/null +++ b/Deep-Reasoning-Llama-3.2-Enigma-3B.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c2ca94a5710770eed7ba3d4a7f549ee79babadbcd5c7c06ccb40b84cfd06b64b +size 1815348416 diff --git a/Deep-Reasoning-Llama-3.2-Enigma-3B.i1-Q3_K_M.gguf b/Deep-Reasoning-Llama-3.2-Enigma-3B.i1-Q3_K_M.gguf new file mode 100644 index 0000000..09dd680 --- /dev/null +++ b/Deep-Reasoning-Llama-3.2-Enigma-3B.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e64c7a3934726774c9ec03781c947aa82e89e0b977b4e62b0de5c0a415737611 +size 1687160000 diff --git a/Deep-Reasoning-Llama-3.2-Enigma-3B.i1-Q3_K_S.gguf b/Deep-Reasoning-Llama-3.2-Enigma-3B.i1-Q3_K_S.gguf new file mode 100644 index 0000000..3a60eb9 --- /dev/null +++ b/Deep-Reasoning-Llama-3.2-Enigma-3B.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4cd94b2da463d715704fea0f3c22a33f8c4fc05d638ea837d12f2e7961676aa2 +size 1542849728 diff --git a/Deep-Reasoning-Llama-3.2-Enigma-3B.i1-Q4_0.gguf b/Deep-Reasoning-Llama-3.2-Enigma-3B.i1-Q4_0.gguf new file mode 100644 index 0000000..2d37521 --- /dev/null +++ b/Deep-Reasoning-Llama-3.2-Enigma-3B.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df319212a817dd295e0b6b176e82a13c2137a392f942ac7eed33fe924bec9fe1 +size 1921909952 diff --git a/Deep-Reasoning-Llama-3.2-Enigma-3B.i1-Q4_1.gguf b/Deep-Reasoning-Llama-3.2-Enigma-3B.i1-Q4_1.gguf new file mode 100644 index 0000000..26df33e --- /dev/null +++ b/Deep-Reasoning-Llama-3.2-Enigma-3B.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f29de846ca41503495fff3e10f981538c9312ca40eaea46ce8a87935a44dbd3 +size 2093352128 diff --git a/Deep-Reasoning-Llama-3.2-Enigma-3B.i1-Q4_K_M.gguf b/Deep-Reasoning-Llama-3.2-Enigma-3B.i1-Q4_K_M.gguf new file mode 100644 index 0000000..8fa7ffb --- /dev/null +++ b/Deep-Reasoning-Llama-3.2-Enigma-3B.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d05400773a4e0cd09c962b85609f1eabd600426b3b552df0475871f784600ca +size 2019378368 diff --git a/Deep-Reasoning-Llama-3.2-Enigma-3B.i1-Q4_K_S.gguf b/Deep-Reasoning-Llama-3.2-Enigma-3B.i1-Q4_K_S.gguf new file mode 100644 index 0000000..bcedfd4 --- /dev/null +++ b/Deep-Reasoning-Llama-3.2-Enigma-3B.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c2a9a757a2783ff94fd745c273f4158f6e81f4257d99b5a388868a9bc26cf9ce +size 1928201408 diff --git a/Deep-Reasoning-Llama-3.2-Enigma-3B.i1-Q5_K_M.gguf b/Deep-Reasoning-Llama-3.2-Enigma-3B.i1-Q5_K_M.gguf new file mode 100644 index 0000000..853c0f3 --- /dev/null +++ b/Deep-Reasoning-Llama-3.2-Enigma-3B.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43821a52214c81aff81fc5a5c2b8883d32d0089511bbeefe0ff601fdee81b046 +size 2322154688 diff --git a/Deep-Reasoning-Llama-3.2-Enigma-3B.i1-Q5_K_S.gguf b/Deep-Reasoning-Llama-3.2-Enigma-3B.i1-Q5_K_S.gguf new file mode 100644 index 0000000..527c5ff --- /dev/null +++ b/Deep-Reasoning-Llama-3.2-Enigma-3B.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09170a0aa1866ae313c4dfddd443ab1dee1674eac89a7c1864f14b60eb3c396d +size 2269512896 diff --git a/Deep-Reasoning-Llama-3.2-Enigma-3B.i1-Q6_K.gguf b/Deep-Reasoning-Llama-3.2-Enigma-3B.i1-Q6_K.gguf new file mode 100644 index 0000000..905b911 --- /dev/null +++ b/Deep-Reasoning-Llama-3.2-Enigma-3B.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3cb00fee3014340d777943128dd06e931220e91a08168192bc9873d9709d81fd +size 2643854528 diff --git a/README.md b/README.md new file mode 100644 index 0000000..1c13dc3 --- /dev/null +++ b/README.md @@ -0,0 +1,85 @@ +--- +base_model: DavidAU/Deep-Reasoning-Llama-3.2-Enigma-3B +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- reasoning +- thinking +- cot +- deepseek +- Llama 3.2 +- 128k context +- fine tune +- llama-3 +- llama-3.2 +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/DavidAU/Deep-Reasoning-Llama-3.2-Enigma-3B + + +static quants are available at https://huggingface.co/mradermacher/Deep-Reasoning-Llama-3.2-Enigma-3B-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/Deep-Reasoning-Llama-3.2-Enigma-3B-i1-GGUF/resolve/main/Deep-Reasoning-Llama-3.2-Enigma-3B.i1-IQ1_S.gguf) | i1-IQ1_S | 1.0 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Deep-Reasoning-Llama-3.2-Enigma-3B-i1-GGUF/resolve/main/Deep-Reasoning-Llama-3.2-Enigma-3B.i1-IQ1_M.gguf) | i1-IQ1_M | 1.0 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Deep-Reasoning-Llama-3.2-Enigma-3B-i1-GGUF/resolve/main/Deep-Reasoning-Llama-3.2-Enigma-3B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/Deep-Reasoning-Llama-3.2-Enigma-3B-i1-GGUF/resolve/main/Deep-Reasoning-Llama-3.2-Enigma-3B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Deep-Reasoning-Llama-3.2-Enigma-3B-i1-GGUF/resolve/main/Deep-Reasoning-Llama-3.2-Enigma-3B.i1-IQ2_S.gguf) | i1-IQ2_S | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/Deep-Reasoning-Llama-3.2-Enigma-3B-i1-GGUF/resolve/main/Deep-Reasoning-Llama-3.2-Enigma-3B.i1-IQ2_M.gguf) | i1-IQ2_M | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/Deep-Reasoning-Llama-3.2-Enigma-3B-i1-GGUF/resolve/main/Deep-Reasoning-Llama-3.2-Enigma-3B.i1-Q2_K_S.gguf) | i1-Q2_K_S | 1.4 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Deep-Reasoning-Llama-3.2-Enigma-3B-i1-GGUF/resolve/main/Deep-Reasoning-Llama-3.2-Enigma-3B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 1.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Deep-Reasoning-Llama-3.2-Enigma-3B-i1-GGUF/resolve/main/Deep-Reasoning-Llama-3.2-Enigma-3B.i1-Q2_K.gguf) | i1-Q2_K | 1.5 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Deep-Reasoning-Llama-3.2-Enigma-3B-i1-GGUF/resolve/main/Deep-Reasoning-Llama-3.2-Enigma-3B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Deep-Reasoning-Llama-3.2-Enigma-3B-i1-GGUF/resolve/main/Deep-Reasoning-Llama-3.2-Enigma-3B.i1-IQ3_S.gguf) | i1-IQ3_S | 1.6 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Deep-Reasoning-Llama-3.2-Enigma-3B-i1-GGUF/resolve/main/Deep-Reasoning-Llama-3.2-Enigma-3B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 1.6 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Deep-Reasoning-Llama-3.2-Enigma-3B-i1-GGUF/resolve/main/Deep-Reasoning-Llama-3.2-Enigma-3B.i1-IQ3_M.gguf) | i1-IQ3_M | 1.7 | | +| [GGUF](https://huggingface.co/mradermacher/Deep-Reasoning-Llama-3.2-Enigma-3B-i1-GGUF/resolve/main/Deep-Reasoning-Llama-3.2-Enigma-3B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 1.8 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Deep-Reasoning-Llama-3.2-Enigma-3B-i1-GGUF/resolve/main/Deep-Reasoning-Llama-3.2-Enigma-3B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 1.9 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Deep-Reasoning-Llama-3.2-Enigma-3B-i1-GGUF/resolve/main/Deep-Reasoning-Llama-3.2-Enigma-3B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Deep-Reasoning-Llama-3.2-Enigma-3B-i1-GGUF/resolve/main/Deep-Reasoning-Llama-3.2-Enigma-3B.i1-IQ4_NL.gguf) | i1-IQ4_NL | 2.0 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/Deep-Reasoning-Llama-3.2-Enigma-3B-i1-GGUF/resolve/main/Deep-Reasoning-Llama-3.2-Enigma-3B.i1-Q4_0.gguf) | i1-Q4_0 | 2.0 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Deep-Reasoning-Llama-3.2-Enigma-3B-i1-GGUF/resolve/main/Deep-Reasoning-Llama-3.2-Enigma-3B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 2.0 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Deep-Reasoning-Llama-3.2-Enigma-3B-i1-GGUF/resolve/main/Deep-Reasoning-Llama-3.2-Enigma-3B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Deep-Reasoning-Llama-3.2-Enigma-3B-i1-GGUF/resolve/main/Deep-Reasoning-Llama-3.2-Enigma-3B.i1-Q4_1.gguf) | i1-Q4_1 | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/Deep-Reasoning-Llama-3.2-Enigma-3B-i1-GGUF/resolve/main/Deep-Reasoning-Llama-3.2-Enigma-3B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Deep-Reasoning-Llama-3.2-Enigma-3B-i1-GGUF/resolve/main/Deep-Reasoning-Llama-3.2-Enigma-3B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Deep-Reasoning-Llama-3.2-Enigma-3B-i1-GGUF/resolve/main/Deep-Reasoning-Llama-3.2-Enigma-3B.i1-Q6_K.gguf) | i1-Q6_K | 2.7 | 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..e01adc3 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a05b91658938ba741da2318ff4942ae6dfcfaacf8d0e1804116f2035aee5d27 +size 2988377