commit 6d428c7336e92fd837e255aae65393d6400c9cfb Author: ModelHub XC Date: Tue May 19 02:13:35 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/LogicFlow-Llama-3B-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..a9b2cc9 --- /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 +LogicFlow-Llama-3B.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +LogicFlow-Llama-3B.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +LogicFlow-Llama-3B.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +LogicFlow-Llama-3B.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +LogicFlow-Llama-3B.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +LogicFlow-Llama-3B.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +LogicFlow-Llama-3B.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +LogicFlow-Llama-3B.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +LogicFlow-Llama-3B.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +LogicFlow-Llama-3B.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +LogicFlow-Llama-3B.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +LogicFlow-Llama-3B.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +LogicFlow-Llama-3B.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +LogicFlow-Llama-3B.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +LogicFlow-Llama-3B.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LogicFlow-Llama-3B.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +LogicFlow-Llama-3B.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LogicFlow-Llama-3B.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LogicFlow-Llama-3B.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +LogicFlow-Llama-3B.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +LogicFlow-Llama-3B.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LogicFlow-Llama-3B.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LogicFlow-Llama-3B.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LogicFlow-Llama-3B.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LogicFlow-Llama-3B.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/LogicFlow-Llama-3B.i1-IQ1_M.gguf b/LogicFlow-Llama-3B.i1-IQ1_M.gguf new file mode 100644 index 0000000..0aebac9 --- /dev/null +++ b/LogicFlow-Llama-3B.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be709498919eb3c569022e1789a784120f1564a583a6af47a88e87385f99ab46 +size 924192320 diff --git a/LogicFlow-Llama-3B.i1-IQ1_S.gguf b/LogicFlow-Llama-3B.i1-IQ1_S.gguf new file mode 100644 index 0000000..100155a --- /dev/null +++ b/LogicFlow-Llama-3B.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0657b1598164e7f20bab917c1954763b001c50a3e894760b5957e146da8fd2ca +size 868159040 diff --git a/LogicFlow-Llama-3B.i1-IQ2_M.gguf b/LogicFlow-Llama-3B.i1-IQ2_M.gguf new file mode 100644 index 0000000..70ef784 --- /dev/null +++ b/LogicFlow-Llama-3B.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc329ee984b1c5ed0d155b09b14568d8ef844808cd0592315191f5f24888c63b +size 1229033024 diff --git a/LogicFlow-Llama-3B.i1-IQ2_S.gguf b/LogicFlow-Llama-3B.i1-IQ2_S.gguf new file mode 100644 index 0000000..1349910 --- /dev/null +++ b/LogicFlow-Llama-3B.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ffe9b280bba5ff08cc0bdce000e599a91ee24e6b89f719240b744cb75516e573 +size 1154321984 diff --git a/LogicFlow-Llama-3B.i1-IQ2_XS.gguf b/LogicFlow-Llama-3B.i1-IQ2_XS.gguf new file mode 100644 index 0000000..51bbadb --- /dev/null +++ b/LogicFlow-Llama-3B.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6921d3e339f8e2697a680baa4c6f27a663601b94f3d55814392b3f392adab473 +size 1100549696 diff --git a/LogicFlow-Llama-3B.i1-IQ2_XXS.gguf b/LogicFlow-Llama-3B.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..60f4f6e --- /dev/null +++ b/LogicFlow-Llama-3B.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bffd675152fda6cf7b76b4925759a8596d1b7e6f4732088aab6af8a78aa009f4 +size 1017581120 diff --git a/LogicFlow-Llama-3B.i1-IQ3_M.gguf b/LogicFlow-Llama-3B.i1-IQ3_M.gguf new file mode 100644 index 0000000..f1d9453 --- /dev/null +++ b/LogicFlow-Llama-3B.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff1f08d307d7d4254fbe3ee2bbf7d6d2afe5019b004c80ebc874c4f262237bc9 +size 1599669824 diff --git a/LogicFlow-Llama-3B.i1-IQ3_S.gguf b/LogicFlow-Llama-3B.i1-IQ3_S.gguf new file mode 100644 index 0000000..281a724 --- /dev/null +++ b/LogicFlow-Llama-3B.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:42414f0cb0a53b081a144a04d95a1ab8118cc14db6571761c6d28befdb77e376 +size 1542850112 diff --git a/LogicFlow-Llama-3B.i1-IQ3_XS.gguf b/LogicFlow-Llama-3B.i1-IQ3_XS.gguf new file mode 100644 index 0000000..d2e2891 --- /dev/null +++ b/LogicFlow-Llama-3B.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c86112220ead5f475127613898291fed90bf997402491729e1dac3cd0d5f33d7 +size 1476789824 diff --git a/LogicFlow-Llama-3B.i1-IQ3_XXS.gguf b/LogicFlow-Llama-3B.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..bc1132f --- /dev/null +++ b/LogicFlow-Llama-3B.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:037b5a18abc2fe15f99e0f6f0ef7185d1efc5fa19d0fb35ba55b18c574a15a88 +size 1348767296 diff --git a/LogicFlow-Llama-3B.i1-IQ4_NL.gguf b/LogicFlow-Llama-3B.i1-IQ4_NL.gguf new file mode 100644 index 0000000..9196487 --- /dev/null +++ b/LogicFlow-Llama-3B.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1852c9a8324c202a8693716bc644258ad4b1e334a7cced0aa112b938e14daad9 +size 1917191744 diff --git a/LogicFlow-Llama-3B.i1-IQ4_XS.gguf b/LogicFlow-Llama-3B.i1-IQ4_XS.gguf new file mode 100644 index 0000000..e3984b2 --- /dev/null +++ b/LogicFlow-Llama-3B.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ad196fdbc145c60b80bbe0f545e26e322d396939160178e21d4a468445937b4 +size 1829111360 diff --git a/LogicFlow-Llama-3B.i1-Q2_K.gguf b/LogicFlow-Llama-3B.i1-Q2_K.gguf new file mode 100644 index 0000000..7b44238 --- /dev/null +++ b/LogicFlow-Llama-3B.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b127939685affd8997afef9c50b065c30907eb936714e47a3f4173c7f15547c +size 1363936832 diff --git a/LogicFlow-Llama-3B.i1-Q2_K_S.gguf b/LogicFlow-Llama-3B.i1-Q2_K_S.gguf new file mode 100644 index 0000000..fb9528e --- /dev/null +++ b/LogicFlow-Llama-3B.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e90dff1a61a9b528c7dac0349f005f47d825ae4df970e03160761bb1fe0ac3c +size 1274283584 diff --git a/LogicFlow-Llama-3B.i1-Q3_K_L.gguf b/LogicFlow-Llama-3B.i1-Q3_K_L.gguf new file mode 100644 index 0000000..08f9407 --- /dev/null +++ b/LogicFlow-Llama-3B.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77a53f46e0d401bc3032611f8f2f73ababaa36d873b33aa7d3f6b7bf815e4ac8 +size 1815348800 diff --git a/LogicFlow-Llama-3B.i1-Q3_K_M.gguf b/LogicFlow-Llama-3B.i1-Q3_K_M.gguf new file mode 100644 index 0000000..74fba20 --- /dev/null +++ b/LogicFlow-Llama-3B.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0cb8cffddf7d71f596d375d2bda79153398800f1a035a12d57452723f8370a1c +size 1687160384 diff --git a/LogicFlow-Llama-3B.i1-Q3_K_S.gguf b/LogicFlow-Llama-3B.i1-Q3_K_S.gguf new file mode 100644 index 0000000..75c7f4f --- /dev/null +++ b/LogicFlow-Llama-3B.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02de3a3727c57a60a5be2f8d2bc6327c5805182ee2493823f2421767550afe98 +size 1542850112 diff --git a/LogicFlow-Llama-3B.i1-Q4_0.gguf b/LogicFlow-Llama-3B.i1-Q4_0.gguf new file mode 100644 index 0000000..febb612 --- /dev/null +++ b/LogicFlow-Llama-3B.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0fad6fb3598103750065bc2cc540d5b7d5ca7ab036eaeb68d687deac96a6db2 +size 1921910336 diff --git a/LogicFlow-Llama-3B.i1-Q4_1.gguf b/LogicFlow-Llama-3B.i1-Q4_1.gguf new file mode 100644 index 0000000..8121c6c --- /dev/null +++ b/LogicFlow-Llama-3B.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc1d2ce35876e7161d1d8ac5fe481c4ef66774a9bc74df304b69a7d26405ab69 +size 2093352512 diff --git a/LogicFlow-Llama-3B.i1-Q4_K_M.gguf b/LogicFlow-Llama-3B.i1-Q4_K_M.gguf new file mode 100644 index 0000000..76ca9c8 --- /dev/null +++ b/LogicFlow-Llama-3B.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20486c4d4388cf4b9ab6b2489ab47ef6355e372f3a2e45deb4292ad6f80c9928 +size 2019378752 diff --git a/LogicFlow-Llama-3B.i1-Q4_K_S.gguf b/LogicFlow-Llama-3B.i1-Q4_K_S.gguf new file mode 100644 index 0000000..55bc13c --- /dev/null +++ b/LogicFlow-Llama-3B.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ff6c7a8cde18938dd413097dc7cd74201b5e17a5ed145063e91567ea4d8b58f +size 1928201792 diff --git a/LogicFlow-Llama-3B.i1-Q5_K_M.gguf b/LogicFlow-Llama-3B.i1-Q5_K_M.gguf new file mode 100644 index 0000000..8467a47 --- /dev/null +++ b/LogicFlow-Llama-3B.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eac5dc05bc828db0d50bce92770b202cf401ea0d119e48a32aa9750552862168 +size 2322155072 diff --git a/LogicFlow-Llama-3B.i1-Q5_K_S.gguf b/LogicFlow-Llama-3B.i1-Q5_K_S.gguf new file mode 100644 index 0000000..8b14567 --- /dev/null +++ b/LogicFlow-Llama-3B.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72b03788bf617753b39b5434925250bd505cb9cfb9bf3187f1a0ae083d83ed99 +size 2269513280 diff --git a/LogicFlow-Llama-3B.i1-Q6_K.gguf b/LogicFlow-Llama-3B.i1-Q6_K.gguf new file mode 100644 index 0000000..cf8e8ab --- /dev/null +++ b/LogicFlow-Llama-3B.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08f8e3291cd2456cc983feea2424b6def83a0f5a5d98a9e9acc65e45a96d3e15 +size 2643854912 diff --git a/LogicFlow-Llama-3B.imatrix.gguf b/LogicFlow-Llama-3B.imatrix.gguf new file mode 100644 index 0000000..bbb87fc --- /dev/null +++ b/LogicFlow-Llama-3B.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad40a5847efbece5f4330fca26ac6ef802628c9ce403eaba2bfbcd910625652e +size 3012064 diff --git a/README.md b/README.md new file mode 100644 index 0000000..d857d40 --- /dev/null +++ b/README.md @@ -0,0 +1,95 @@ +--- +base_model: RekklesAI/LogicFlow-Llama-3B +datasets: +- open-thoughts/OpenThoughts-114k +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- llama-factory +- lora +- open_thoughts +- chain-of-thought +- cot +- logicflow +- single-gpu-training +--- +## About + + + + + + + + + +weighted/imatrix quants of https://huggingface.co/RekklesAI/LogicFlow-Llama-3B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#LogicFlow-Llama-3B-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/LogicFlow-Llama-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/LogicFlow-Llama-3B-i1-GGUF/resolve/main/LogicFlow-Llama-3B.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/LogicFlow-Llama-3B-i1-GGUF/resolve/main/LogicFlow-Llama-3B.i1-IQ1_S.gguf) | i1-IQ1_S | 1.0 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/LogicFlow-Llama-3B-i1-GGUF/resolve/main/LogicFlow-Llama-3B.i1-IQ1_M.gguf) | i1-IQ1_M | 1.0 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/LogicFlow-Llama-3B-i1-GGUF/resolve/main/LogicFlow-Llama-3B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/LogicFlow-Llama-3B-i1-GGUF/resolve/main/LogicFlow-Llama-3B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/LogicFlow-Llama-3B-i1-GGUF/resolve/main/LogicFlow-Llama-3B.i1-IQ2_S.gguf) | i1-IQ2_S | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/LogicFlow-Llama-3B-i1-GGUF/resolve/main/LogicFlow-Llama-3B.i1-IQ2_M.gguf) | i1-IQ2_M | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/LogicFlow-Llama-3B-i1-GGUF/resolve/main/LogicFlow-Llama-3B.i1-Q2_K_S.gguf) | i1-Q2_K_S | 1.4 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/LogicFlow-Llama-3B-i1-GGUF/resolve/main/LogicFlow-Llama-3B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 1.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/LogicFlow-Llama-3B-i1-GGUF/resolve/main/LogicFlow-Llama-3B.i1-Q2_K.gguf) | i1-Q2_K | 1.5 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/LogicFlow-Llama-3B-i1-GGUF/resolve/main/LogicFlow-Llama-3B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/LogicFlow-Llama-3B-i1-GGUF/resolve/main/LogicFlow-Llama-3B.i1-IQ3_S.gguf) | i1-IQ3_S | 1.6 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/LogicFlow-Llama-3B-i1-GGUF/resolve/main/LogicFlow-Llama-3B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 1.6 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/LogicFlow-Llama-3B-i1-GGUF/resolve/main/LogicFlow-Llama-3B.i1-IQ3_M.gguf) | i1-IQ3_M | 1.7 | | +| [GGUF](https://huggingface.co/mradermacher/LogicFlow-Llama-3B-i1-GGUF/resolve/main/LogicFlow-Llama-3B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 1.8 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/LogicFlow-Llama-3B-i1-GGUF/resolve/main/LogicFlow-Llama-3B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 1.9 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/LogicFlow-Llama-3B-i1-GGUF/resolve/main/LogicFlow-Llama-3B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/LogicFlow-Llama-3B-i1-GGUF/resolve/main/LogicFlow-Llama-3B.i1-IQ4_NL.gguf) | i1-IQ4_NL | 2.0 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/LogicFlow-Llama-3B-i1-GGUF/resolve/main/LogicFlow-Llama-3B.i1-Q4_0.gguf) | i1-Q4_0 | 2.0 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/LogicFlow-Llama-3B-i1-GGUF/resolve/main/LogicFlow-Llama-3B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 2.0 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/LogicFlow-Llama-3B-i1-GGUF/resolve/main/LogicFlow-Llama-3B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LogicFlow-Llama-3B-i1-GGUF/resolve/main/LogicFlow-Llama-3B.i1-Q4_1.gguf) | i1-Q4_1 | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/LogicFlow-Llama-3B-i1-GGUF/resolve/main/LogicFlow-Llama-3B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/LogicFlow-Llama-3B-i1-GGUF/resolve/main/LogicFlow-Llama-3B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/LogicFlow-Llama-3B-i1-GGUF/resolve/main/LogicFlow-Llama-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. + +