commit a97b505b715f1dd18ea863d7d3e30082ac591657 Author: ModelHub XC Date: Sat Sep 26 00:25:22 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: mradermacher/Firebal-Llama-3.1-8B-R1-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..bedb7a0 --- /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 +Firebal-Llama-3.1-8B-R1.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Firebal-Llama-3.1-8B-R1.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Firebal-Llama-3.1-8B-R1.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Firebal-Llama-3.1-8B-R1.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Firebal-Llama-3.1-8B-R1.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Firebal-Llama-3.1-8B-R1.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Firebal-Llama-3.1-8B-R1.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Firebal-Llama-3.1-8B-R1.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Firebal-Llama-3.1-8B-R1.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Firebal-Llama-3.1-8B-R1.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Firebal-Llama-3.1-8B-R1.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Firebal-Llama-3.1-8B-R1.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Firebal-Llama-3.1-8B-R1.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Firebal-Llama-3.1-8B-R1.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Firebal-Llama-3.1-8B-R1.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Firebal-Llama-3.1-8B-R1.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Firebal-Llama-3.1-8B-R1.i1-Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text +Firebal-Llama-3.1-8B-R1.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Firebal-Llama-3.1-8B-R1.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Firebal-Llama-3.1-8B-R1.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Firebal-Llama-3.1-8B-R1.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Firebal-Llama-3.1-8B-R1.i1-Q4_0_4_8.gguf filter=lfs diff=lfs merge=lfs -text +Firebal-Llama-3.1-8B-R1.i1-Q4_0_8_8.gguf filter=lfs diff=lfs merge=lfs -text +Firebal-Llama-3.1-8B-R1.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Firebal-Llama-3.1-8B-R1.i1-IQ1_M.gguf b/Firebal-Llama-3.1-8B-R1.i1-IQ1_M.gguf new file mode 100644 index 0000000..98fc3c2 --- /dev/null +++ b/Firebal-Llama-3.1-8B-R1.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f02131a567cb638ba7611b7c3d0b44fa0dfb2b815dcc539ced681ef057d3afa +size 2161977472 diff --git a/Firebal-Llama-3.1-8B-R1.i1-IQ1_S.gguf b/Firebal-Llama-3.1-8B-R1.i1-IQ1_S.gguf new file mode 100644 index 0000000..ed7fa0d --- /dev/null +++ b/Firebal-Llama-3.1-8B-R1.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4950844850b2fdd885d40f691b9859f0753f208d64e952c0f7887d62272f25c2 +size 2019633280 diff --git a/Firebal-Llama-3.1-8B-R1.i1-IQ2_M.gguf b/Firebal-Llama-3.1-8B-R1.i1-IQ2_M.gguf new file mode 100644 index 0000000..f8007a5 --- /dev/null +++ b/Firebal-Llama-3.1-8B-R1.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb4468fc7dae84ad174831905422e34155c684099a2e6ffc29b395cc04ef76c9 +size 2948286592 diff --git a/Firebal-Llama-3.1-8B-R1.i1-IQ2_S.gguf b/Firebal-Llama-3.1-8B-R1.i1-IQ2_S.gguf new file mode 100644 index 0000000..b383631 --- /dev/null +++ b/Firebal-Llama-3.1-8B-R1.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c630c2b2f9c47c877bcbf39b431ead94f5275a5984fbb870d1352cf61bf64fb +size 2758494336 diff --git a/Firebal-Llama-3.1-8B-R1.i1-IQ2_XS.gguf b/Firebal-Llama-3.1-8B-R1.i1-IQ2_XS.gguf new file mode 100644 index 0000000..bcc4f5d --- /dev/null +++ b/Firebal-Llama-3.1-8B-R1.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cddc237b4c1cb9febaf308b2788bd50bd15e31219dffcad57f64095dc1e835cd +size 2605787264 diff --git a/Firebal-Llama-3.1-8B-R1.i1-IQ2_XXS.gguf b/Firebal-Llama-3.1-8B-R1.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..18fedaf --- /dev/null +++ b/Firebal-Llama-3.1-8B-R1.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dbe5486322dddf5fa81e8d66f1b6dad3f25105c0e8b5df948c6dbdceb1535d90 +size 2399217792 diff --git a/Firebal-Llama-3.1-8B-R1.i1-IQ3_M.gguf b/Firebal-Llama-3.1-8B-R1.i1-IQ3_M.gguf new file mode 100644 index 0000000..76bfc11 --- /dev/null +++ b/Firebal-Llama-3.1-8B-R1.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7bfe39ad8794ee0f30ae356e1e055fb057fccee7e923ff7962f10c8e1b001366 +size 3784829056 diff --git a/Firebal-Llama-3.1-8B-R1.i1-IQ3_S.gguf b/Firebal-Llama-3.1-8B-R1.i1-IQ3_S.gguf new file mode 100644 index 0000000..6a7aeaf --- /dev/null +++ b/Firebal-Llama-3.1-8B-R1.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c06b6785cf9c10d64364384a6cfd974113d5520a79e909648ad2a47ec951604 +size 3682330752 diff --git a/Firebal-Llama-3.1-8B-R1.i1-IQ3_XS.gguf b/Firebal-Llama-3.1-8B-R1.i1-IQ3_XS.gguf new file mode 100644 index 0000000..18b9c90 --- /dev/null +++ b/Firebal-Llama-3.1-8B-R1.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7941306bb8780667fde7515bc1bf0bdb1192a583f0ecc5dc6754662cecb0d8ec +size 3518752896 diff --git a/Firebal-Llama-3.1-8B-R1.i1-IQ3_XXS.gguf b/Firebal-Llama-3.1-8B-R1.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..0f650e7 --- /dev/null +++ b/Firebal-Llama-3.1-8B-R1.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88d21d835ba6e5d5082c3dc1470f53623148606cfb1beda0c93af51fbac26521 +size 3274918016 diff --git a/Firebal-Llama-3.1-8B-R1.i1-IQ4_XS.gguf b/Firebal-Llama-3.1-8B-R1.i1-IQ4_XS.gguf new file mode 100644 index 0000000..78cd9a6 --- /dev/null +++ b/Firebal-Llama-3.1-8B-R1.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59b20eafaf9d48072976e00888caf4e98f38405acc9e77be1fe5594ee4dce8b6 +size 4447668352 diff --git a/Firebal-Llama-3.1-8B-R1.i1-Q2_K.gguf b/Firebal-Llama-3.1-8B-R1.i1-Q2_K.gguf new file mode 100644 index 0000000..6752df1 --- /dev/null +++ b/Firebal-Llama-3.1-8B-R1.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c2f488c6714d0d8e04133db81ef7cfe3ed7e5dff77f8033e0a5c89a9df9ac30 +size 3179137152 diff --git a/Firebal-Llama-3.1-8B-R1.i1-Q3_K_L.gguf b/Firebal-Llama-3.1-8B-R1.i1-Q3_K_L.gguf new file mode 100644 index 0000000..858100d --- /dev/null +++ b/Firebal-Llama-3.1-8B-R1.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd6516823bda3df72cd7ab382f83661e9ca57f68407e71804782361aaee8ea9a +size 4321962112 diff --git a/Firebal-Llama-3.1-8B-R1.i1-Q3_K_M.gguf b/Firebal-Llama-3.1-8B-R1.i1-Q3_K_M.gguf new file mode 100644 index 0000000..36d0bdc --- /dev/null +++ b/Firebal-Llama-3.1-8B-R1.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a6906f70a2b85525cff395d2dfa2c700ae26697083cb80ddc9b5155c8351a49b +size 4018923648 diff --git a/Firebal-Llama-3.1-8B-R1.i1-Q3_K_S.gguf b/Firebal-Llama-3.1-8B-R1.i1-Q3_K_S.gguf new file mode 100644 index 0000000..b693307 --- /dev/null +++ b/Firebal-Llama-3.1-8B-R1.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b5859595389cde33730f783ab3f7019dbf824344e4affa232b64bae1c6747e3 +size 3664504960 diff --git a/Firebal-Llama-3.1-8B-R1.i1-Q4_0.gguf b/Firebal-Llama-3.1-8B-R1.i1-Q4_0.gguf new file mode 100644 index 0000000..f0f5c27 --- /dev/null +++ b/Firebal-Llama-3.1-8B-R1.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e785851487092c27e34db5a112e9808e4fc18ba1f7926ecbc1861fac80c2f6c +size 4675897472 diff --git a/Firebal-Llama-3.1-8B-R1.i1-Q4_0_4_4.gguf b/Firebal-Llama-3.1-8B-R1.i1-Q4_0_4_4.gguf new file mode 100644 index 0000000..d5a09aa --- /dev/null +++ b/Firebal-Llama-3.1-8B-R1.i1-Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3464cfc448c4e5e9fd178ac63e78c8868c90a8595c3975de3207d6e82498ecea +size 4661217408 diff --git a/Firebal-Llama-3.1-8B-R1.i1-Q4_0_4_8.gguf b/Firebal-Llama-3.1-8B-R1.i1-Q4_0_4_8.gguf new file mode 100644 index 0000000..a9c4189 --- /dev/null +++ b/Firebal-Llama-3.1-8B-R1.i1-Q4_0_4_8.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26c5f83e4aa0f00227798916f17fe343c780cf45dcfa4bcf0f6963b74c6badbf +size 4661217408 diff --git a/Firebal-Llama-3.1-8B-R1.i1-Q4_0_8_8.gguf b/Firebal-Llama-3.1-8B-R1.i1-Q4_0_8_8.gguf new file mode 100644 index 0000000..d6d9215 --- /dev/null +++ b/Firebal-Llama-3.1-8B-R1.i1-Q4_0_8_8.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c72983c1c3798f8a4db01cc69a471bc803e8c050dbea41df849b1d0bef569018 +size 4661217408 diff --git a/Firebal-Llama-3.1-8B-R1.i1-Q4_K_M.gguf b/Firebal-Llama-3.1-8B-R1.i1-Q4_K_M.gguf new file mode 100644 index 0000000..87e61fb --- /dev/null +++ b/Firebal-Llama-3.1-8B-R1.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf945dd17162f9c1c3fe5a870891e3cbb5df69bce2b7c999049b57894ed2f540 +size 4920739968 diff --git a/Firebal-Llama-3.1-8B-R1.i1-Q4_K_S.gguf b/Firebal-Llama-3.1-8B-R1.i1-Q4_K_S.gguf new file mode 100644 index 0000000..b2db813 --- /dev/null +++ b/Firebal-Llama-3.1-8B-R1.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d99879727f2db63c1086593d154db05fe297166e92d1c267f5624abc1884ac99 +size 4692674688 diff --git a/Firebal-Llama-3.1-8B-R1.i1-Q5_K_M.gguf b/Firebal-Llama-3.1-8B-R1.i1-Q5_K_M.gguf new file mode 100644 index 0000000..c1596cf --- /dev/null +++ b/Firebal-Llama-3.1-8B-R1.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:abc9862d56a1bb1a2c877d54a1528319a1de02147bd856c211e08ed3b880747d +size 5732993152 diff --git a/Firebal-Llama-3.1-8B-R1.i1-Q5_K_S.gguf b/Firebal-Llama-3.1-8B-R1.i1-Q5_K_S.gguf new file mode 100644 index 0000000..b5d2d83 --- /dev/null +++ b/Firebal-Llama-3.1-8B-R1.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad11137bf12783921892790246e315848e0d72a96ebbe6edebc45a531ec558ad +size 5599299712 diff --git a/Firebal-Llama-3.1-8B-R1.i1-Q6_K.gguf b/Firebal-Llama-3.1-8B-R1.i1-Q6_K.gguf new file mode 100644 index 0000000..b9f7f57 --- /dev/null +++ b/Firebal-Llama-3.1-8B-R1.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:87065295f2de26c3229cca2bcd025875caa963cd03cf624f98d46d1b51e2f492 +size 6596012160 diff --git a/README.md b/README.md new file mode 100644 index 0000000..cd8e221 --- /dev/null +++ b/README.md @@ -0,0 +1,82 @@ +--- +base_model: EpistemeAI2/Firebal-Llama-3.1-8B-R1 +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +- trl +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/EpistemeAI2/Firebal-Llama-3.1-8B-R1 + + +static quants are available at https://huggingface.co/mradermacher/Firebal-Llama-3.1-8B-R1-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/Firebal-Llama-3.1-8B-R1-i1-GGUF/resolve/main/Firebal-Llama-3.1-8B-R1.i1-IQ1_S.gguf) | i1-IQ1_S | 2.1 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Firebal-Llama-3.1-8B-R1-i1-GGUF/resolve/main/Firebal-Llama-3.1-8B-R1.i1-IQ1_M.gguf) | i1-IQ1_M | 2.3 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Firebal-Llama-3.1-8B-R1-i1-GGUF/resolve/main/Firebal-Llama-3.1-8B-R1.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/Firebal-Llama-3.1-8B-R1-i1-GGUF/resolve/main/Firebal-Llama-3.1-8B-R1.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/Firebal-Llama-3.1-8B-R1-i1-GGUF/resolve/main/Firebal-Llama-3.1-8B-R1.i1-IQ2_S.gguf) | i1-IQ2_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Firebal-Llama-3.1-8B-R1-i1-GGUF/resolve/main/Firebal-Llama-3.1-8B-R1.i1-IQ2_M.gguf) | i1-IQ2_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Firebal-Llama-3.1-8B-R1-i1-GGUF/resolve/main/Firebal-Llama-3.1-8B-R1.i1-Q2_K.gguf) | i1-Q2_K | 3.3 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Firebal-Llama-3.1-8B-R1-i1-GGUF/resolve/main/Firebal-Llama-3.1-8B-R1.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Firebal-Llama-3.1-8B-R1-i1-GGUF/resolve/main/Firebal-Llama-3.1-8B-R1.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Firebal-Llama-3.1-8B-R1-i1-GGUF/resolve/main/Firebal-Llama-3.1-8B-R1.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.8 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Firebal-Llama-3.1-8B-R1-i1-GGUF/resolve/main/Firebal-Llama-3.1-8B-R1.i1-IQ3_S.gguf) | i1-IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Firebal-Llama-3.1-8B-R1-i1-GGUF/resolve/main/Firebal-Llama-3.1-8B-R1.i1-IQ3_M.gguf) | i1-IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Firebal-Llama-3.1-8B-R1-i1-GGUF/resolve/main/Firebal-Llama-3.1-8B-R1.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.1 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Firebal-Llama-3.1-8B-R1-i1-GGUF/resolve/main/Firebal-Llama-3.1-8B-R1.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.4 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Firebal-Llama-3.1-8B-R1-i1-GGUF/resolve/main/Firebal-Llama-3.1-8B-R1.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/Firebal-Llama-3.1-8B-R1-i1-GGUF/resolve/main/Firebal-Llama-3.1-8B-R1.i1-Q4_0_4_4.gguf) | i1-Q4_0_4_4 | 4.8 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/Firebal-Llama-3.1-8B-R1-i1-GGUF/resolve/main/Firebal-Llama-3.1-8B-R1.i1-Q4_0_4_8.gguf) | i1-Q4_0_4_8 | 4.8 | fast on arm+i8mm, low quality | +| [GGUF](https://huggingface.co/mradermacher/Firebal-Llama-3.1-8B-R1-i1-GGUF/resolve/main/Firebal-Llama-3.1-8B-R1.i1-Q4_0_8_8.gguf) | i1-Q4_0_8_8 | 4.8 | fast on arm+sve, low quality | +| [GGUF](https://huggingface.co/mradermacher/Firebal-Llama-3.1-8B-R1-i1-GGUF/resolve/main/Firebal-Llama-3.1-8B-R1.i1-Q4_0.gguf) | i1-Q4_0 | 4.8 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Firebal-Llama-3.1-8B-R1-i1-GGUF/resolve/main/Firebal-Llama-3.1-8B-R1.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.8 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Firebal-Llama-3.1-8B-R1-i1-GGUF/resolve/main/Firebal-Llama-3.1-8B-R1.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Firebal-Llama-3.1-8B-R1-i1-GGUF/resolve/main/Firebal-Llama-3.1-8B-R1.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Firebal-Llama-3.1-8B-R1-i1-GGUF/resolve/main/Firebal-Llama-3.1-8B-R1.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Firebal-Llama-3.1-8B-R1-i1-GGUF/resolve/main/Firebal-Llama-3.1-8B-R1.i1-Q6_K.gguf) | i1-Q6_K | 6.7 | 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..ad9cd02 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:754a8f650dcbee708a8ac4d400627acf71e3c41c5deabf0a3b8d2df2f9e6bf3e +size 4988157