commit 28b0845432fcc7e58fec103ef2d0ddc590b73b9b Author: ModelHub XC Date: Fri Apr 17 01:57:53 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/DeepSeek-V3-DRAFT-0.6B-v3.0-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..6ee5f3a --- /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 +DeepSeek-V3-DRAFT-0.6B-v3.0.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-V3-DRAFT-0.6B-v3.0.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-V3-DRAFT-0.6B-v3.0.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-V3-DRAFT-0.6B-v3.0.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-V3-DRAFT-0.6B-v3.0.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-V3-DRAFT-0.6B-v3.0.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-V3-DRAFT-0.6B-v3.0.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-V3-DRAFT-0.6B-v3.0.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-V3-DRAFT-0.6B-v3.0.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-V3-DRAFT-0.6B-v3.0.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-V3-DRAFT-0.6B-v3.0.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-V3-DRAFT-0.6B-v3.0.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-V3-DRAFT-0.6B-v3.0.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-V3-DRAFT-0.6B-v3.0.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-V3-DRAFT-0.6B-v3.0.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-V3-DRAFT-0.6B-v3.0.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-V3-DRAFT-0.6B-v3.0.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-V3-DRAFT-0.6B-v3.0.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-V3-DRAFT-0.6B-v3.0.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-V3-DRAFT-0.6B-v3.0.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-V3-DRAFT-0.6B-v3.0.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-V3-DRAFT-0.6B-v3.0.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-V3-DRAFT-0.6B-v3.0.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-V3-DRAFT-0.6B-v3.0.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-V3-DRAFT-0.6B-v3.0.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/DeepSeek-V3-DRAFT-0.6B-v3.0.i1-IQ1_M.gguf b/DeepSeek-V3-DRAFT-0.6B-v3.0.i1-IQ1_M.gguf new file mode 100644 index 0000000..d085927 --- /dev/null +++ b/DeepSeek-V3-DRAFT-0.6B-v3.0.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01fe955bf036cda8c70082e0c9e6e4cc21e53f03ecc13d8d68a1c18049264ccc +size 360866240 diff --git a/DeepSeek-V3-DRAFT-0.6B-v3.0.i1-IQ1_S.gguf b/DeepSeek-V3-DRAFT-0.6B-v3.0.i1-IQ1_S.gguf new file mode 100644 index 0000000..80652f8 --- /dev/null +++ b/DeepSeek-V3-DRAFT-0.6B-v3.0.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a15cb05c60ec1fc78f2e88d7a0f7c2ac7578d73d1a695cb8147091a475d58d1 +size 358721216 diff --git a/DeepSeek-V3-DRAFT-0.6B-v3.0.i1-IQ2_M.gguf b/DeepSeek-V3-DRAFT-0.6B-v3.0.i1-IQ2_M.gguf new file mode 100644 index 0000000..5bc2b51 --- /dev/null +++ b/DeepSeek-V3-DRAFT-0.6B-v3.0.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3aebf56864b4885b173741801541f868e4a401312f57f9201b8b3c50af184f92 +size 371489216 diff --git a/DeepSeek-V3-DRAFT-0.6B-v3.0.i1-IQ2_S.gguf b/DeepSeek-V3-DRAFT-0.6B-v3.0.i1-IQ2_S.gguf new file mode 100644 index 0000000..4e757e7 --- /dev/null +++ b/DeepSeek-V3-DRAFT-0.6B-v3.0.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0903fd46322bef9a6d0126d9a5650dabc4028f3d43c5283e1c300542710ee07c +size 368629184 diff --git a/DeepSeek-V3-DRAFT-0.6B-v3.0.i1-IQ2_XS.gguf b/DeepSeek-V3-DRAFT-0.6B-v3.0.i1-IQ2_XS.gguf new file mode 100644 index 0000000..17e5489 --- /dev/null +++ b/DeepSeek-V3-DRAFT-0.6B-v3.0.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec76dff2d6b2d6049ceabed87feef1dfd45808bdfc9eed1ec747a6b07f9f76de +size 367301312 diff --git a/DeepSeek-V3-DRAFT-0.6B-v3.0.i1-IQ2_XXS.gguf b/DeepSeek-V3-DRAFT-0.6B-v3.0.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..2c25701 --- /dev/null +++ b/DeepSeek-V3-DRAFT-0.6B-v3.0.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8a3e5598e1da6ff0d453972e16530ab2556f602659f0bd4d999d7616676dbd2 +size 364441280 diff --git a/DeepSeek-V3-DRAFT-0.6B-v3.0.i1-IQ3_M.gguf b/DeepSeek-V3-DRAFT-0.6B-v3.0.i1-IQ3_M.gguf new file mode 100644 index 0000000..90f0a29 --- /dev/null +++ b/DeepSeek-V3-DRAFT-0.6B-v3.0.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7d3c3163a1c0fcba25cb9a96cd22c4f1ce197d8420d2cea8e8157ae9395bcf2 +size 385644224 diff --git a/DeepSeek-V3-DRAFT-0.6B-v3.0.i1-IQ3_S.gguf b/DeepSeek-V3-DRAFT-0.6B-v3.0.i1-IQ3_S.gguf new file mode 100644 index 0000000..10f2acf --- /dev/null +++ b/DeepSeek-V3-DRAFT-0.6B-v3.0.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac3586be5fcd3a892350369377924c99fa4269f6356505bcde2e8ee5f122e2e2 +size 381499328 diff --git a/DeepSeek-V3-DRAFT-0.6B-v3.0.i1-IQ3_XS.gguf b/DeepSeek-V3-DRAFT-0.6B-v3.0.i1-IQ3_XS.gguf new file mode 100644 index 0000000..8ce5ea7 --- /dev/null +++ b/DeepSeek-V3-DRAFT-0.6B-v3.0.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5f1781668dc28662a430420922abe91364f1c14ea89cf99ff91ba85e6e24c3c +size 381499328 diff --git a/DeepSeek-V3-DRAFT-0.6B-v3.0.i1-IQ3_XXS.gguf b/DeepSeek-V3-DRAFT-0.6B-v3.0.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..e779506 --- /dev/null +++ b/DeepSeek-V3-DRAFT-0.6B-v3.0.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5b5c487ed4dcb85f4eb4a0bb3682dae61ee08830ee2a2caa7111aa40e138bf8 +size 376596416 diff --git a/DeepSeek-V3-DRAFT-0.6B-v3.0.i1-IQ4_NL.gguf b/DeepSeek-V3-DRAFT-0.6B-v3.0.i1-IQ4_NL.gguf new file mode 100644 index 0000000..41eed03 --- /dev/null +++ b/DeepSeek-V3-DRAFT-0.6B-v3.0.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b498be79ac28e7d4b48d0c1eec74e4e713a474070693271fa770e0f2576b1114 +size 395562944 diff --git a/DeepSeek-V3-DRAFT-0.6B-v3.0.i1-IQ4_XS.gguf b/DeepSeek-V3-DRAFT-0.6B-v3.0.i1-IQ4_XS.gguf new file mode 100644 index 0000000..d8592ed --- /dev/null +++ b/DeepSeek-V3-DRAFT-0.6B-v3.0.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be6b018841c98f5ab927c397c7eabbb14eea41ee3ac1ddd75fe3da7bf5b3eec4 +size 392294336 diff --git a/DeepSeek-V3-DRAFT-0.6B-v3.0.i1-Q2_K.gguf b/DeepSeek-V3-DRAFT-0.6B-v3.0.i1-Q2_K.gguf new file mode 100644 index 0000000..438328e --- /dev/null +++ b/DeepSeek-V3-DRAFT-0.6B-v3.0.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:717b213d05e280ce5774f46a3d615a9f3807d27b32ee9ac251364336ffdf1118 +size 381499328 diff --git a/DeepSeek-V3-DRAFT-0.6B-v3.0.i1-Q2_K_S.gguf b/DeepSeek-V3-DRAFT-0.6B-v3.0.i1-Q2_K_S.gguf new file mode 100644 index 0000000..ce363fd --- /dev/null +++ b/DeepSeek-V3-DRAFT-0.6B-v3.0.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:29e97fec78c7aaa24db2e7fbb9a6fc1f8b2d9caa50e8940144bfabdea2349e37 +size 373940672 diff --git a/DeepSeek-V3-DRAFT-0.6B-v3.0.i1-Q3_K_L.gguf b/DeepSeek-V3-DRAFT-0.6B-v3.0.i1-Q3_K_L.gguf new file mode 100644 index 0000000..59cb211 --- /dev/null +++ b/DeepSeek-V3-DRAFT-0.6B-v3.0.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8bac97e0e1f8f6713217bbbbd92d7d6cfd36d4aa630b790dc9da7cd735f81935 +size 412250048 diff --git a/DeepSeek-V3-DRAFT-0.6B-v3.0.i1-Q3_K_M.gguf b/DeepSeek-V3-DRAFT-0.6B-v3.0.i1-Q3_K_M.gguf new file mode 100644 index 0000000..1eb9b0e --- /dev/null +++ b/DeepSeek-V3-DRAFT-0.6B-v3.0.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3df659708f27939e25486f07cc8e578949f9d239236aa37fde2bea4f472c3963 +size 398358464 diff --git a/DeepSeek-V3-DRAFT-0.6B-v3.0.i1-Q3_K_S.gguf b/DeepSeek-V3-DRAFT-0.6B-v3.0.i1-Q3_K_S.gguf new file mode 100644 index 0000000..4ce0e62 --- /dev/null +++ b/DeepSeek-V3-DRAFT-0.6B-v3.0.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d51fa2a036127acd81f38f5153df4dd7464c8d540fcc7a31fb08450d4fc1142 +size 381155264 diff --git a/DeepSeek-V3-DRAFT-0.6B-v3.0.i1-Q4_0.gguf b/DeepSeek-V3-DRAFT-0.6B-v3.0.i1-Q4_0.gguf new file mode 100644 index 0000000..fe597a9 --- /dev/null +++ b/DeepSeek-V3-DRAFT-0.6B-v3.0.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0dd6303a4eabca9562c22501c2aebafad81b6f11d4919cdf81abd4ca1f1c9352 +size 395864000 diff --git a/DeepSeek-V3-DRAFT-0.6B-v3.0.i1-Q4_1.gguf b/DeepSeek-V3-DRAFT-0.6B-v3.0.i1-Q4_1.gguf new file mode 100644 index 0000000..1c6788e --- /dev/null +++ b/DeepSeek-V3-DRAFT-0.6B-v3.0.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:81b2cc6756dfdffc10f8f5bc2c67d71328fad13c85ee0851739e4de92c999861 +size 424650688 diff --git a/DeepSeek-V3-DRAFT-0.6B-v3.0.i1-Q4_K_M.gguf b/DeepSeek-V3-DRAFT-0.6B-v3.0.i1-Q4_K_M.gguf new file mode 100644 index 0000000..8a0c8d5 --- /dev/null +++ b/DeepSeek-V3-DRAFT-0.6B-v3.0.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9328a160192c4d21e69f17436cc7289370a2dc7bbc42c9a8aa0cdad2bf7c3f03 +size 455179200 diff --git a/DeepSeek-V3-DRAFT-0.6B-v3.0.i1-Q4_K_S.gguf b/DeepSeek-V3-DRAFT-0.6B-v3.0.i1-Q4_K_S.gguf new file mode 100644 index 0000000..689ae65 --- /dev/null +++ b/DeepSeek-V3-DRAFT-0.6B-v3.0.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51711373bab7ca0a7653381ed5b5cb4c26ddb809755ae7b3af6a1e6ebf3bfec4 +size 442843072 diff --git a/DeepSeek-V3-DRAFT-0.6B-v3.0.i1-Q5_K_M.gguf b/DeepSeek-V3-DRAFT-0.6B-v3.0.i1-Q5_K_M.gguf new file mode 100644 index 0000000..3b9a705 --- /dev/null +++ b/DeepSeek-V3-DRAFT-0.6B-v3.0.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0bf7898bbe79be404d7c41fcba481dabdf42d32a1ded2fcafffd450131cc6278 +size 484697024 diff --git a/DeepSeek-V3-DRAFT-0.6B-v3.0.i1-Q5_K_S.gguf b/DeepSeek-V3-DRAFT-0.6B-v3.0.i1-Q5_K_S.gguf new file mode 100644 index 0000000..1fd44ec --- /dev/null +++ b/DeepSeek-V3-DRAFT-0.6B-v3.0.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f31e9360e1e2d7dc6b42276aa358aedab1e99686442189937d6a2705b1e622b2 +size 477321152 diff --git a/DeepSeek-V3-DRAFT-0.6B-v3.0.i1-Q6_K.gguf b/DeepSeek-V3-DRAFT-0.6B-v3.0.i1-Q6_K.gguf new file mode 100644 index 0000000..b3a98d3 --- /dev/null +++ b/DeepSeek-V3-DRAFT-0.6B-v3.0.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee0b51fad25afb8504c327b197a3c4062510a69bd3975a7bb8c4adc4d2d50500 +size 606545856 diff --git a/DeepSeek-V3-DRAFT-0.6B-v3.0.imatrix.gguf b/DeepSeek-V3-DRAFT-0.6B-v3.0.imatrix.gguf new file mode 100644 index 0000000..d456cf7 --- /dev/null +++ b/DeepSeek-V3-DRAFT-0.6B-v3.0.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:290a4a27d0c6672ff42a885d5b144db404c16cd5a574fabb270b1c973f27284d +size 1008928 diff --git a/README.md b/README.md new file mode 100644 index 0000000..5a07a86 --- /dev/null +++ b/README.md @@ -0,0 +1,92 @@ +--- +base_model: jukofyork/DeepSeek-V3-DRAFT-0.6B-v3.0 +datasets: +- agentlans/common-crawl-sample +- bigcode/the-stack-smol-xl +- rombodawg/Everything_Instruct +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- draft +- speculative-decoding +--- +## About + + + + + + + + + +weighted/imatrix quants of https://huggingface.co/jukofyork/DeepSeek-V3-DRAFT-0.6B-v3.0 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#DeepSeek-V3-DRAFT-0.6B-v3.0-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/DeepSeek-V3-DRAFT-0.6B-v3.0-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/DeepSeek-V3-DRAFT-0.6B-v3.0-i1-GGUF/resolve/main/DeepSeek-V3-DRAFT-0.6B-v3.0.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-V3-DRAFT-0.6B-v3.0-i1-GGUF/resolve/main/DeepSeek-V3-DRAFT-0.6B-v3.0.i1-IQ1_S.gguf) | i1-IQ1_S | 0.5 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-V3-DRAFT-0.6B-v3.0-i1-GGUF/resolve/main/DeepSeek-V3-DRAFT-0.6B-v3.0.i1-IQ1_M.gguf) | i1-IQ1_M | 0.5 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-V3-DRAFT-0.6B-v3.0-i1-GGUF/resolve/main/DeepSeek-V3-DRAFT-0.6B-v3.0.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-V3-DRAFT-0.6B-v3.0-i1-GGUF/resolve/main/DeepSeek-V3-DRAFT-0.6B-v3.0.i1-IQ2_XS.gguf) | i1-IQ2_XS | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-V3-DRAFT-0.6B-v3.0-i1-GGUF/resolve/main/DeepSeek-V3-DRAFT-0.6B-v3.0.i1-IQ2_S.gguf) | i1-IQ2_S | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-V3-DRAFT-0.6B-v3.0-i1-GGUF/resolve/main/DeepSeek-V3-DRAFT-0.6B-v3.0.i1-IQ2_M.gguf) | i1-IQ2_M | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-V3-DRAFT-0.6B-v3.0-i1-GGUF/resolve/main/DeepSeek-V3-DRAFT-0.6B-v3.0.i1-Q2_K_S.gguf) | i1-Q2_K_S | 0.5 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-V3-DRAFT-0.6B-v3.0-i1-GGUF/resolve/main/DeepSeek-V3-DRAFT-0.6B-v3.0.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 0.5 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-V3-DRAFT-0.6B-v3.0-i1-GGUF/resolve/main/DeepSeek-V3-DRAFT-0.6B-v3.0.i1-Q3_K_S.gguf) | i1-Q3_K_S | 0.5 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-V3-DRAFT-0.6B-v3.0-i1-GGUF/resolve/main/DeepSeek-V3-DRAFT-0.6B-v3.0.i1-IQ3_S.gguf) | i1-IQ3_S | 0.5 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-V3-DRAFT-0.6B-v3.0-i1-GGUF/resolve/main/DeepSeek-V3-DRAFT-0.6B-v3.0.i1-IQ3_XS.gguf) | i1-IQ3_XS | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-V3-DRAFT-0.6B-v3.0-i1-GGUF/resolve/main/DeepSeek-V3-DRAFT-0.6B-v3.0.i1-Q2_K.gguf) | i1-Q2_K | 0.5 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-V3-DRAFT-0.6B-v3.0-i1-GGUF/resolve/main/DeepSeek-V3-DRAFT-0.6B-v3.0.i1-IQ3_M.gguf) | i1-IQ3_M | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-V3-DRAFT-0.6B-v3.0-i1-GGUF/resolve/main/DeepSeek-V3-DRAFT-0.6B-v3.0.i1-IQ4_XS.gguf) | i1-IQ4_XS | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-V3-DRAFT-0.6B-v3.0-i1-GGUF/resolve/main/DeepSeek-V3-DRAFT-0.6B-v3.0.i1-IQ4_NL.gguf) | i1-IQ4_NL | 0.5 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-V3-DRAFT-0.6B-v3.0-i1-GGUF/resolve/main/DeepSeek-V3-DRAFT-0.6B-v3.0.i1-Q4_0.gguf) | i1-Q4_0 | 0.5 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-V3-DRAFT-0.6B-v3.0-i1-GGUF/resolve/main/DeepSeek-V3-DRAFT-0.6B-v3.0.i1-Q3_K_M.gguf) | i1-Q3_K_M | 0.5 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-V3-DRAFT-0.6B-v3.0-i1-GGUF/resolve/main/DeepSeek-V3-DRAFT-0.6B-v3.0.i1-Q3_K_L.gguf) | i1-Q3_K_L | 0.5 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-V3-DRAFT-0.6B-v3.0-i1-GGUF/resolve/main/DeepSeek-V3-DRAFT-0.6B-v3.0.i1-Q4_1.gguf) | i1-Q4_1 | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-V3-DRAFT-0.6B-v3.0-i1-GGUF/resolve/main/DeepSeek-V3-DRAFT-0.6B-v3.0.i1-Q4_K_S.gguf) | i1-Q4_K_S | 0.5 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-V3-DRAFT-0.6B-v3.0-i1-GGUF/resolve/main/DeepSeek-V3-DRAFT-0.6B-v3.0.i1-Q4_K_M.gguf) | i1-Q4_K_M | 0.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-V3-DRAFT-0.6B-v3.0-i1-GGUF/resolve/main/DeepSeek-V3-DRAFT-0.6B-v3.0.i1-Q5_K_S.gguf) | i1-Q5_K_S | 0.6 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-V3-DRAFT-0.6B-v3.0-i1-GGUF/resolve/main/DeepSeek-V3-DRAFT-0.6B-v3.0.i1-Q5_K_M.gguf) | i1-Q5_K_M | 0.6 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-V3-DRAFT-0.6B-v3.0-i1-GGUF/resolve/main/DeepSeek-V3-DRAFT-0.6B-v3.0.i1-Q6_K.gguf) | i1-Q6_K | 0.7 | 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. + +