commit ec30b9ec88e656febc389e4491e611b6119d53c1 Author: ModelHub XC Date: Sat Oct 3 06:49:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama3.2-3B-ShiningValiant2-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..d993786 --- /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 +Llama3.2-3B-ShiningValiant2.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-3B-ShiningValiant2.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-3B-ShiningValiant2.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-3B-ShiningValiant2.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-3B-ShiningValiant2.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-3B-ShiningValiant2.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-3B-ShiningValiant2.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-3B-ShiningValiant2.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-3B-ShiningValiant2.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-3B-ShiningValiant2.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-3B-ShiningValiant2.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-3B-ShiningValiant2.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-3B-ShiningValiant2.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-3B-ShiningValiant2.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-3B-ShiningValiant2.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-3B-ShiningValiant2.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-3B-ShiningValiant2.i1-Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-3B-ShiningValiant2.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-3B-ShiningValiant2.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-3B-ShiningValiant2.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-3B-ShiningValiant2.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-3B-ShiningValiant2.i1-Q4_0_4_8.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-3B-ShiningValiant2.i1-Q4_0_8_8.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-3B-ShiningValiant2.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama3.2-3B-ShiningValiant2.i1-IQ1_M.gguf b/Llama3.2-3B-ShiningValiant2.i1-IQ1_M.gguf new file mode 100644 index 0000000..72ce331 --- /dev/null +++ b/Llama3.2-3B-ShiningValiant2.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74421adb6f667f62d7a732a1ea648c2f2be24c52ed16935612b65ed9c69d5e7a +size 924193024 diff --git a/Llama3.2-3B-ShiningValiant2.i1-IQ1_S.gguf b/Llama3.2-3B-ShiningValiant2.i1-IQ1_S.gguf new file mode 100644 index 0000000..6dca099 --- /dev/null +++ b/Llama3.2-3B-ShiningValiant2.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91037f15500ba0fd06640a13e97c7ed68d5ef5af73baceddfc0136decdfa5ea7 +size 868159744 diff --git a/Llama3.2-3B-ShiningValiant2.i1-IQ2_M.gguf b/Llama3.2-3B-ShiningValiant2.i1-IQ2_M.gguf new file mode 100644 index 0000000..a57b37d --- /dev/null +++ b/Llama3.2-3B-ShiningValiant2.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce8c6d752a99fd81cab99c10f2f7df5dccc2c23f7ac2028f179b2b80f8865aa4 +size 1229033728 diff --git a/Llama3.2-3B-ShiningValiant2.i1-IQ2_S.gguf b/Llama3.2-3B-ShiningValiant2.i1-IQ2_S.gguf new file mode 100644 index 0000000..7231fd9 --- /dev/null +++ b/Llama3.2-3B-ShiningValiant2.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dbb350b054a6e3007d4798977a9b0da31eadc241d8f7bbf455f4486fe67f7803 +size 1154322688 diff --git a/Llama3.2-3B-ShiningValiant2.i1-IQ2_XS.gguf b/Llama3.2-3B-ShiningValiant2.i1-IQ2_XS.gguf new file mode 100644 index 0000000..16faa1b --- /dev/null +++ b/Llama3.2-3B-ShiningValiant2.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff494d57ea4dde6100741c1b921a2be1a7fb36a77baf04e816f0317ee2eb8545 +size 1100550400 diff --git a/Llama3.2-3B-ShiningValiant2.i1-IQ2_XXS.gguf b/Llama3.2-3B-ShiningValiant2.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..0fe5cac --- /dev/null +++ b/Llama3.2-3B-ShiningValiant2.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ead118a0798c028244ca80dae4faf6a8202908bf5d4f6177d895dd8442ee7fe +size 1017581824 diff --git a/Llama3.2-3B-ShiningValiant2.i1-IQ3_M.gguf b/Llama3.2-3B-ShiningValiant2.i1-IQ3_M.gguf new file mode 100644 index 0000000..4109dd6 --- /dev/null +++ b/Llama3.2-3B-ShiningValiant2.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11771b863c791845322916749483b112f756a5a742b9c06f63d2b38db2be5383 +size 1599670528 diff --git a/Llama3.2-3B-ShiningValiant2.i1-IQ3_S.gguf b/Llama3.2-3B-ShiningValiant2.i1-IQ3_S.gguf new file mode 100644 index 0000000..c7d102f --- /dev/null +++ b/Llama3.2-3B-ShiningValiant2.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a619da9557f18c58166ac09b729605c5589f4f2d55211bdc67b8523e6c879c7 +size 1542850816 diff --git a/Llama3.2-3B-ShiningValiant2.i1-IQ3_XS.gguf b/Llama3.2-3B-ShiningValiant2.i1-IQ3_XS.gguf new file mode 100644 index 0000000..514bb0a --- /dev/null +++ b/Llama3.2-3B-ShiningValiant2.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:939426a312f9bcbfd78ed0214c42d567c0b4238105336854557afd4051042bd9 +size 1476790528 diff --git a/Llama3.2-3B-ShiningValiant2.i1-IQ3_XXS.gguf b/Llama3.2-3B-ShiningValiant2.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..4d99e4e --- /dev/null +++ b/Llama3.2-3B-ShiningValiant2.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6bfecac1a084317450a1e51bbb7a22e919d3a8e6a2ed2aa16ac29c3cf6392ede +size 1348768000 diff --git a/Llama3.2-3B-ShiningValiant2.i1-IQ4_XS.gguf b/Llama3.2-3B-ShiningValiant2.i1-IQ4_XS.gguf new file mode 100644 index 0000000..c63cd3f --- /dev/null +++ b/Llama3.2-3B-ShiningValiant2.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7f0ec6c9767167534fcef00d4232a22cc5591457214db9fd977192e842e79d1 +size 1829112064 diff --git a/Llama3.2-3B-ShiningValiant2.i1-Q2_K.gguf b/Llama3.2-3B-ShiningValiant2.i1-Q2_K.gguf new file mode 100644 index 0000000..6afb56b --- /dev/null +++ b/Llama3.2-3B-ShiningValiant2.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69388c58f6d0cedd9eaa914a8a9685d9d56bc28cfba5bc943a3c6835a43ae9ee +size 1363937536 diff --git a/Llama3.2-3B-ShiningValiant2.i1-Q3_K_L.gguf b/Llama3.2-3B-ShiningValiant2.i1-Q3_K_L.gguf new file mode 100644 index 0000000..228aa12 --- /dev/null +++ b/Llama3.2-3B-ShiningValiant2.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a25290a20daef4e5e96423d30da51ce366f50bf93757cc29957e01d25589400d +size 1815349504 diff --git a/Llama3.2-3B-ShiningValiant2.i1-Q3_K_M.gguf b/Llama3.2-3B-ShiningValiant2.i1-Q3_K_M.gguf new file mode 100644 index 0000000..3d36f2a --- /dev/null +++ b/Llama3.2-3B-ShiningValiant2.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8eaea1e7b8b94751f62406535b4fb49e5cdaed4df037b39200d11e8a07afe4d6 +size 1687161088 diff --git a/Llama3.2-3B-ShiningValiant2.i1-Q3_K_S.gguf b/Llama3.2-3B-ShiningValiant2.i1-Q3_K_S.gguf new file mode 100644 index 0000000..68f18e5 --- /dev/null +++ b/Llama3.2-3B-ShiningValiant2.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f70fa9fa5ff6f2c6a76db896a7d427dda9c947caac3732135388baa618aab00 +size 1542850816 diff --git a/Llama3.2-3B-ShiningValiant2.i1-Q4_0.gguf b/Llama3.2-3B-ShiningValiant2.i1-Q4_0.gguf new file mode 100644 index 0000000..8a6d344 --- /dev/null +++ b/Llama3.2-3B-ShiningValiant2.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff91b70bbfd81e9ca53f42f1543a8c1dfa0d839dc3f53ba896915fc93c581e97 +size 1921911040 diff --git a/Llama3.2-3B-ShiningValiant2.i1-Q4_0_4_4.gguf b/Llama3.2-3B-ShiningValiant2.i1-Q4_0_4_4.gguf new file mode 100644 index 0000000..5ffbad2 --- /dev/null +++ b/Llama3.2-3B-ShiningValiant2.i1-Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fcb5775229161906162349a25aa1af77a753add704b973e09e16dbf3ef19523c +size 1917192448 diff --git a/Llama3.2-3B-ShiningValiant2.i1-Q4_0_4_8.gguf b/Llama3.2-3B-ShiningValiant2.i1-Q4_0_4_8.gguf new file mode 100644 index 0000000..13da317 --- /dev/null +++ b/Llama3.2-3B-ShiningValiant2.i1-Q4_0_4_8.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5614f099bb3dcbb36b422841eb0985892c199fcbbd26a6858b261c0c0efa99e1 +size 1917192448 diff --git a/Llama3.2-3B-ShiningValiant2.i1-Q4_0_8_8.gguf b/Llama3.2-3B-ShiningValiant2.i1-Q4_0_8_8.gguf new file mode 100644 index 0000000..1e9b0ed --- /dev/null +++ b/Llama3.2-3B-ShiningValiant2.i1-Q4_0_8_8.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:63354e547156d9add161c1f78b3f1e01598c783f3c6e234ea95bbcd0ffa51c07 +size 1917192448 diff --git a/Llama3.2-3B-ShiningValiant2.i1-Q4_K_M.gguf b/Llama3.2-3B-ShiningValiant2.i1-Q4_K_M.gguf new file mode 100644 index 0000000..33e4fb3 --- /dev/null +++ b/Llama3.2-3B-ShiningValiant2.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:700521dc6a8a50e2d0bb5ccde12399209004155f9c68751aeac7feccf2cd4957 +size 2019379456 diff --git a/Llama3.2-3B-ShiningValiant2.i1-Q4_K_S.gguf b/Llama3.2-3B-ShiningValiant2.i1-Q4_K_S.gguf new file mode 100644 index 0000000..d673b1a --- /dev/null +++ b/Llama3.2-3B-ShiningValiant2.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb0c1ffa8c1528471807086b1f344145bd8c3776e09ac4abe8212662239112e0 +size 1928202496 diff --git a/Llama3.2-3B-ShiningValiant2.i1-Q5_K_M.gguf b/Llama3.2-3B-ShiningValiant2.i1-Q5_K_M.gguf new file mode 100644 index 0000000..d1874fb --- /dev/null +++ b/Llama3.2-3B-ShiningValiant2.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e052869e744fa11aa5a9b842844b36b4c135d2438617084da2e8feb6230d241f +size 2322155776 diff --git a/Llama3.2-3B-ShiningValiant2.i1-Q5_K_S.gguf b/Llama3.2-3B-ShiningValiant2.i1-Q5_K_S.gguf new file mode 100644 index 0000000..28a362d --- /dev/null +++ b/Llama3.2-3B-ShiningValiant2.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a304a7ba815af37b860777b263d815e5d0d58fee7879e92f9f6af2fa2c7d4b3 +size 2269513984 diff --git a/Llama3.2-3B-ShiningValiant2.i1-Q6_K.gguf b/Llama3.2-3B-ShiningValiant2.i1-Q6_K.gguf new file mode 100644 index 0000000..ac0ce7a --- /dev/null +++ b/Llama3.2-3B-ShiningValiant2.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb912cc420e260a3167ec3933d7550df430d12d985cbb56e3032b14a5fdb1159 +size 2643855616 diff --git a/README.md b/README.md new file mode 100644 index 0000000..5c76cfc --- /dev/null +++ b/README.md @@ -0,0 +1,105 @@ +--- +base_model: ValiantLabs/Llama3.2-3B-ShiningValiant2 +datasets: +- sequelbox/Celestia +- sequelbox/Spurline +- sequelbox/Supernova +language: +- en +library_name: transformers +license: llama3.2 +model_type: llama +quantized_by: mradermacher +tags: +- shining-valiant +- shining-valiant-2 +- valiant +- valiant-labs +- llama +- llama-3.2 +- llama-3.2-instruct +- llama-3.2-instruct-3b +- llama-3 +- llama-3-instruct +- llama-3-instruct-3b +- 3b +- science +- physics +- biology +- chemistry +- compsci +- computer-science +- engineering +- technical +- conversational +- chat +- instruct +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/ValiantLabs/Llama3.2-3B-ShiningValiant2 + + +static quants are available at https://huggingface.co/mradermacher/Llama3.2-3B-ShiningValiant2-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/Llama3.2-3B-ShiningValiant2-i1-GGUF/resolve/main/Llama3.2-3B-ShiningValiant2.i1-IQ1_S.gguf) | i1-IQ1_S | 1.0 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-3B-ShiningValiant2-i1-GGUF/resolve/main/Llama3.2-3B-ShiningValiant2.i1-IQ1_M.gguf) | i1-IQ1_M | 1.0 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-3B-ShiningValiant2-i1-GGUF/resolve/main/Llama3.2-3B-ShiningValiant2.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-3B-ShiningValiant2-i1-GGUF/resolve/main/Llama3.2-3B-ShiningValiant2.i1-IQ2_XS.gguf) | i1-IQ2_XS | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-3B-ShiningValiant2-i1-GGUF/resolve/main/Llama3.2-3B-ShiningValiant2.i1-IQ2_S.gguf) | i1-IQ2_S | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-3B-ShiningValiant2-i1-GGUF/resolve/main/Llama3.2-3B-ShiningValiant2.i1-IQ2_M.gguf) | i1-IQ2_M | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-3B-ShiningValiant2-i1-GGUF/resolve/main/Llama3.2-3B-ShiningValiant2.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 1.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-3B-ShiningValiant2-i1-GGUF/resolve/main/Llama3.2-3B-ShiningValiant2.i1-Q2_K.gguf) | i1-Q2_K | 1.5 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-3B-ShiningValiant2-i1-GGUF/resolve/main/Llama3.2-3B-ShiningValiant2.i1-IQ3_XS.gguf) | i1-IQ3_XS | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-3B-ShiningValiant2-i1-GGUF/resolve/main/Llama3.2-3B-ShiningValiant2.i1-IQ3_S.gguf) | i1-IQ3_S | 1.6 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-3B-ShiningValiant2-i1-GGUF/resolve/main/Llama3.2-3B-ShiningValiant2.i1-Q3_K_S.gguf) | i1-Q3_K_S | 1.6 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-3B-ShiningValiant2-i1-GGUF/resolve/main/Llama3.2-3B-ShiningValiant2.i1-IQ3_M.gguf) | i1-IQ3_M | 1.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-3B-ShiningValiant2-i1-GGUF/resolve/main/Llama3.2-3B-ShiningValiant2.i1-Q3_K_M.gguf) | i1-Q3_K_M | 1.8 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-3B-ShiningValiant2-i1-GGUF/resolve/main/Llama3.2-3B-ShiningValiant2.i1-Q3_K_L.gguf) | i1-Q3_K_L | 1.9 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-3B-ShiningValiant2-i1-GGUF/resolve/main/Llama3.2-3B-ShiningValiant2.i1-IQ4_XS.gguf) | i1-IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-3B-ShiningValiant2-i1-GGUF/resolve/main/Llama3.2-3B-ShiningValiant2.i1-Q4_0_4_4.gguf) | i1-Q4_0_4_4 | 2.0 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-3B-ShiningValiant2-i1-GGUF/resolve/main/Llama3.2-3B-ShiningValiant2.i1-Q4_0_4_8.gguf) | i1-Q4_0_4_8 | 2.0 | fast on arm+i8mm, low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-3B-ShiningValiant2-i1-GGUF/resolve/main/Llama3.2-3B-ShiningValiant2.i1-Q4_0_8_8.gguf) | i1-Q4_0_8_8 | 2.0 | fast on arm+sve, low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-3B-ShiningValiant2-i1-GGUF/resolve/main/Llama3.2-3B-ShiningValiant2.i1-Q4_0.gguf) | i1-Q4_0 | 2.0 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-3B-ShiningValiant2-i1-GGUF/resolve/main/Llama3.2-3B-ShiningValiant2.i1-Q4_K_S.gguf) | i1-Q4_K_S | 2.0 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-3B-ShiningValiant2-i1-GGUF/resolve/main/Llama3.2-3B-ShiningValiant2.i1-Q4_K_M.gguf) | i1-Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-3B-ShiningValiant2-i1-GGUF/resolve/main/Llama3.2-3B-ShiningValiant2.i1-Q5_K_S.gguf) | i1-Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-3B-ShiningValiant2-i1-GGUF/resolve/main/Llama3.2-3B-ShiningValiant2.i1-Q5_K_M.gguf) | i1-Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-3B-ShiningValiant2-i1-GGUF/resolve/main/Llama3.2-3B-ShiningValiant2.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..9d6c129 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef43b561283811cfd236954a89891e8bfb3c40f3156f54133d317c97f738a698 +size 2988377