commit e69db4703e4e748d631ac31833ec39e128174391 Author: ModelHub XC Date: Thu Jul 23 11:57:10 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen3-8B-MegaScience-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..af02a0f --- /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 +Qwen3-8B-MegaScience.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-8B-MegaScience.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-8B-MegaScience.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-8B-MegaScience.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-8B-MegaScience.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-8B-MegaScience.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-8B-MegaScience.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-8B-MegaScience.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-8B-MegaScience.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-8B-MegaScience.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-8B-MegaScience.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-8B-MegaScience.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-8B-MegaScience.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-8B-MegaScience.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-8B-MegaScience.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-8B-MegaScience.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-8B-MegaScience.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-8B-MegaScience.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-8B-MegaScience.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-8B-MegaScience.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-8B-MegaScience.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-8B-MegaScience.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-8B-MegaScience.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-8B-MegaScience.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-8B-MegaScience.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen3-8B-MegaScience.i1-IQ1_M.gguf b/Qwen3-8B-MegaScience.i1-IQ1_M.gguf new file mode 100644 index 0000000..53153ec --- /dev/null +++ b/Qwen3-8B-MegaScience.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c15c75fdd63f417976af57627db7efa186be5fbd18c2d2de01c13f7cc5b6ed23 +size 2256148736 diff --git a/Qwen3-8B-MegaScience.i1-IQ1_S.gguf b/Qwen3-8B-MegaScience.i1-IQ1_S.gguf new file mode 100644 index 0000000..cc82a58 --- /dev/null +++ b/Qwen3-8B-MegaScience.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca456699f74f70dcbcda92be131d82cd85fa990c7215905177e1b4697bae031e +size 2115770624 diff --git a/Qwen3-8B-MegaScience.i1-IQ2_M.gguf b/Qwen3-8B-MegaScience.i1-IQ2_M.gguf new file mode 100644 index 0000000..75361f0 --- /dev/null +++ b/Qwen3-8B-MegaScience.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec38b02ef6bd349ed7fe86f4c08a6056ee01f119d2da39ef1311b4b24b9ec846 +size 3051915520 diff --git a/Qwen3-8B-MegaScience.i1-IQ2_S.gguf b/Qwen3-8B-MegaScience.i1-IQ2_S.gguf new file mode 100644 index 0000000..0910582 --- /dev/null +++ b/Qwen3-8B-MegaScience.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8e6eb70b35031644fd9d64662b6bf44c0eec9e3d3856b28af5e4dbc2b3997ea +size 2864744704 diff --git a/Qwen3-8B-MegaScience.i1-IQ2_XS.gguf b/Qwen3-8B-MegaScience.i1-IQ2_XS.gguf new file mode 100644 index 0000000..b505c98 --- /dev/null +++ b/Qwen3-8B-MegaScience.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b805ca6024c0897c91f8e91267cddf2b1453fe2c25f9aa2c8b46e70cdb82a6dc +size 2696157440 diff --git a/Qwen3-8B-MegaScience.i1-IQ2_XXS.gguf b/Qwen3-8B-MegaScience.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..02b6af7 --- /dev/null +++ b/Qwen3-8B-MegaScience.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b13af15370c96092425b0f96125030e230589fcd3fb9a7bab035760f4101b4c +size 2490112256 diff --git a/Qwen3-8B-MegaScience.i1-IQ3_M.gguf b/Qwen3-8B-MegaScience.i1-IQ3_M.gguf new file mode 100644 index 0000000..33472ca --- /dev/null +++ b/Qwen3-8B-MegaScience.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc8bc2968d93a3e85a5edfa61245a5b7919f889f3545cfc063255340afd24449 +size 3896621312 diff --git a/Qwen3-8B-MegaScience.i1-IQ3_S.gguf b/Qwen3-8B-MegaScience.i1-IQ3_S.gguf new file mode 100644 index 0000000..e99b7a4 --- /dev/null +++ b/Qwen3-8B-MegaScience.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c42a54b87cec27b0639932415f7b75f3d41ce48cd8a455ac0bf9e9128a026996 +size 3789666560 diff --git a/Qwen3-8B-MegaScience.i1-IQ3_XS.gguf b/Qwen3-8B-MegaScience.i1-IQ3_XS.gguf new file mode 100644 index 0000000..5625fae --- /dev/null +++ b/Qwen3-8B-MegaScience.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:034e180eaccd20f925ef980122352bc288be0f5d3d936166ee7238895ee12fab +size 3626875136 diff --git a/Qwen3-8B-MegaScience.i1-IQ3_XXS.gguf b/Qwen3-8B-MegaScience.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..87201d3 --- /dev/null +++ b/Qwen3-8B-MegaScience.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee0c541e0f58307ec1448e32b74480f6599ce0ab6be3e70cd03361d10acdac1c +size 3369634048 diff --git a/Qwen3-8B-MegaScience.i1-IQ4_NL.gguf b/Qwen3-8B-MegaScience.i1-IQ4_NL.gguf new file mode 100644 index 0000000..0dbee88 --- /dev/null +++ b/Qwen3-8B-MegaScience.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe5d8db3c7b592c0ef3a56afb928af0181278771bfef51aee211159b43f47fbf +size 4793624832 diff --git a/Qwen3-8B-MegaScience.i1-IQ4_XS.gguf b/Qwen3-8B-MegaScience.i1-IQ4_XS.gguf new file mode 100644 index 0000000..e71376f --- /dev/null +++ b/Qwen3-8B-MegaScience.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:397021d3faa60ed812776b7c46a0614f62a5ce7aea951a0dbf5939157ede137b +size 4561840384 diff --git a/Qwen3-8B-MegaScience.i1-Q2_K.gguf b/Qwen3-8B-MegaScience.i1-Q2_K.gguf new file mode 100644 index 0000000..4242ef4 --- /dev/null +++ b/Qwen3-8B-MegaScience.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8fc4c7e8c25827115285ccf7a77c0321415f0d8f2dce20e35a5e90b0c6596851 +size 3281733888 diff --git a/Qwen3-8B-MegaScience.i1-Q2_K_S.gguf b/Qwen3-8B-MegaScience.i1-Q2_K_S.gguf new file mode 100644 index 0000000..52d5d37 --- /dev/null +++ b/Qwen3-8B-MegaScience.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6bcc63e62edfb69a8f849f9a7a480b89eae4b12dbf54a56ead57a9a3ed85a551 +size 3083553024 diff --git a/Qwen3-8B-MegaScience.i1-Q3_K_L.gguf b/Qwen3-8B-MegaScience.i1-Q3_K_L.gguf new file mode 100644 index 0000000..6cc0497 --- /dev/null +++ b/Qwen3-8B-MegaScience.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:42d3f06ee91e67182a85f313bfe787afdc7e76d451bbe7d8454305e11f718e44 +size 4431395072 diff --git a/Qwen3-8B-MegaScience.i1-Q3_K_M.gguf b/Qwen3-8B-MegaScience.i1-Q3_K_M.gguf new file mode 100644 index 0000000..26db036 --- /dev/null +++ b/Qwen3-8B-MegaScience.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:141cd9043b9999937076ae0cab8a61039cff098f9d49a77109bba41eb6920957 +size 4124162304 diff --git a/Qwen3-8B-MegaScience.i1-Q3_K_S.gguf b/Qwen3-8B-MegaScience.i1-Q3_K_S.gguf new file mode 100644 index 0000000..1d92383 --- /dev/null +++ b/Qwen3-8B-MegaScience.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d07246d11e5dd0770795f2517bca45ccc09214cfd1bf3e244fd15d792ef74156 +size 3769612544 diff --git a/Qwen3-8B-MegaScience.i1-Q4_0.gguf b/Qwen3-8B-MegaScience.i1-Q4_0.gguf new file mode 100644 index 0000000..df52754 --- /dev/null +++ b/Qwen3-8B-MegaScience.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e01d15dbc70597fa5b5cbd47b6eda78a4975e8c0ece3aaefcae92c4b25bf26f +size 4787333376 diff --git a/Qwen3-8B-MegaScience.i1-Q4_1.gguf b/Qwen3-8B-MegaScience.i1-Q4_1.gguf new file mode 100644 index 0000000..73b4bdb --- /dev/null +++ b/Qwen3-8B-MegaScience.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24d1f5fca531c283ff238ecab730f6246ffb60b14fd0a5a2d13b4d9237463c94 +size 5247756544 diff --git a/Qwen3-8B-MegaScience.i1-Q4_K_M.gguf b/Qwen3-8B-MegaScience.i1-Q4_K_M.gguf new file mode 100644 index 0000000..e0ffab2 --- /dev/null +++ b/Qwen3-8B-MegaScience.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a115cf9bcbd930cbc4137386aa3e143b1c2b9af0cf47c507e57b7de131d32c9 +size 5027784960 diff --git a/Qwen3-8B-MegaScience.i1-Q4_K_S.gguf b/Qwen3-8B-MegaScience.i1-Q4_K_S.gguf new file mode 100644 index 0000000..ca4ed8c --- /dev/null +++ b/Qwen3-8B-MegaScience.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:efd708893315740fc003ecfa41d132af9ac1ede930689e2b578c3ccfa43fac14 +size 4802013440 diff --git a/Qwen3-8B-MegaScience.i1-Q5_K_M.gguf b/Qwen3-8B-MegaScience.i1-Q5_K_M.gguf new file mode 100644 index 0000000..ff69a27 --- /dev/null +++ b/Qwen3-8B-MegaScience.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9164dbe871a9e1c87a1f853e9fe36d5f96d51b5ab5e160a70c8f5931bfa1968 +size 5851113728 diff --git a/Qwen3-8B-MegaScience.i1-Q5_K_S.gguf b/Qwen3-8B-MegaScience.i1-Q5_K_S.gguf new file mode 100644 index 0000000..25a77f8 --- /dev/null +++ b/Qwen3-8B-MegaScience.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b097a52c0349fe9771937a249ae933c88c2a5bf6fffd2b8a4681120b699341c +size 5720762624 diff --git a/Qwen3-8B-MegaScience.i1-Q6_K.gguf b/Qwen3-8B-MegaScience.i1-Q6_K.gguf new file mode 100644 index 0000000..1746535 --- /dev/null +++ b/Qwen3-8B-MegaScience.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3c44a0f8db316da423b0fe4edec2f5f63315f7218cc5ef2ca27bb97ba79d5a2 +size 6725900544 diff --git a/Qwen3-8B-MegaScience.imatrix.gguf b/Qwen3-8B-MegaScience.imatrix.gguf new file mode 100644 index 0000000..7fb1ec9 --- /dev/null +++ b/Qwen3-8B-MegaScience.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b2b8b6f9c68d2a17aebaf71718d0b071e6bf623cebd31accaa7819830423525 +size 5347200 diff --git a/README.md b/README.md new file mode 100644 index 0000000..0a4ec8e --- /dev/null +++ b/README.md @@ -0,0 +1,90 @@ +--- +base_model: MegaScience/Qwen3-8B-MegaScience +datasets: +- MegaScience/MegaScience +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- qwen +- science +- scientific-reasoning +- causal-lm +- instruction-tuning +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/MegaScience/Qwen3-8B-MegaScience + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3-8B-MegaScience-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/Qwen3-8B-MegaScience-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/Qwen3-8B-MegaScience-i1-GGUF/resolve/main/Qwen3-8B-MegaScience.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-MegaScience-i1-GGUF/resolve/main/Qwen3-8B-MegaScience.i1-IQ1_S.gguf) | i1-IQ1_S | 2.2 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-MegaScience-i1-GGUF/resolve/main/Qwen3-8B-MegaScience.i1-IQ1_M.gguf) | i1-IQ1_M | 2.4 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-MegaScience-i1-GGUF/resolve/main/Qwen3-8B-MegaScience.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-MegaScience-i1-GGUF/resolve/main/Qwen3-8B-MegaScience.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-MegaScience-i1-GGUF/resolve/main/Qwen3-8B-MegaScience.i1-IQ2_S.gguf) | i1-IQ2_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-MegaScience-i1-GGUF/resolve/main/Qwen3-8B-MegaScience.i1-IQ2_M.gguf) | i1-IQ2_M | 3.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-MegaScience-i1-GGUF/resolve/main/Qwen3-8B-MegaScience.i1-Q2_K_S.gguf) | i1-Q2_K_S | 3.2 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-MegaScience-i1-GGUF/resolve/main/Qwen3-8B-MegaScience.i1-Q2_K.gguf) | i1-Q2_K | 3.4 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-MegaScience-i1-GGUF/resolve/main/Qwen3-8B-MegaScience.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.5 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-MegaScience-i1-GGUF/resolve/main/Qwen3-8B-MegaScience.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-MegaScience-i1-GGUF/resolve/main/Qwen3-8B-MegaScience.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.9 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-MegaScience-i1-GGUF/resolve/main/Qwen3-8B-MegaScience.i1-IQ3_S.gguf) | i1-IQ3_S | 3.9 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-MegaScience-i1-GGUF/resolve/main/Qwen3-8B-MegaScience.i1-IQ3_M.gguf) | i1-IQ3_M | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-MegaScience-i1-GGUF/resolve/main/Qwen3-8B-MegaScience.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.2 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-MegaScience-i1-GGUF/resolve/main/Qwen3-8B-MegaScience.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.5 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-MegaScience-i1-GGUF/resolve/main/Qwen3-8B-MegaScience.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.7 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-MegaScience-i1-GGUF/resolve/main/Qwen3-8B-MegaScience.i1-Q4_0.gguf) | i1-Q4_0 | 4.9 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-MegaScience-i1-GGUF/resolve/main/Qwen3-8B-MegaScience.i1-IQ4_NL.gguf) | i1-IQ4_NL | 4.9 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-MegaScience-i1-GGUF/resolve/main/Qwen3-8B-MegaScience.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.9 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-MegaScience-i1-GGUF/resolve/main/Qwen3-8B-MegaScience.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-MegaScience-i1-GGUF/resolve/main/Qwen3-8B-MegaScience.i1-Q4_1.gguf) | i1-Q4_1 | 5.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-MegaScience-i1-GGUF/resolve/main/Qwen3-8B-MegaScience.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-MegaScience-i1-GGUF/resolve/main/Qwen3-8B-MegaScience.i1-Q5_K_M.gguf) | i1-Q5_K_M | 6.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-MegaScience-i1-GGUF/resolve/main/Qwen3-8B-MegaScience.i1-Q6_K.gguf) | i1-Q6_K | 6.8 | 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. + +