commit a0e0eccbdfd1793727334b50cb25f6186072c268 Author: ModelHub XC Date: Sat Jun 6 18:31:16 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: mradermacher/L3.1-Pneuma-8B-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..eb8842e --- /dev/null +++ b/.gitattributes @@ -0,0 +1,61 @@ +*.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 +L3.1-Pneuma-8B.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Pneuma-8B.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Pneuma-8B.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Pneuma-8B.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Pneuma-8B.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Pneuma-8B.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Pneuma-8B.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Pneuma-8B.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Pneuma-8B.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Pneuma-8B.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Pneuma-8B.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Pneuma-8B.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Pneuma-8B.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Pneuma-8B.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Pneuma-8B.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Pneuma-8B.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Pneuma-8B.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Pneuma-8B.i1-Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Pneuma-8B.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Pneuma-8B.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Pneuma-8B.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Pneuma-8B.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Pneuma-8B.i1-Q4_0_4_8.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Pneuma-8B.i1-Q4_0_8_8.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Pneuma-8B.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/L3.1-Pneuma-8B.i1-IQ1_M.gguf b/L3.1-Pneuma-8B.i1-IQ1_M.gguf new file mode 100644 index 0000000..5d41ccc --- /dev/null +++ b/L3.1-Pneuma-8B.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d876375e8724e0e941560b769729b5502c44c809237d9118dbdf897cad08adf9 +size 2161977376 diff --git a/L3.1-Pneuma-8B.i1-IQ1_S.gguf b/L3.1-Pneuma-8B.i1-IQ1_S.gguf new file mode 100644 index 0000000..08335cf --- /dev/null +++ b/L3.1-Pneuma-8B.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09ad506307cdf73e4d4218cbc61790d1e8b3d91139a37cfa97ccc0d4c2d85c7c +size 2019633184 diff --git a/L3.1-Pneuma-8B.i1-IQ2_M.gguf b/L3.1-Pneuma-8B.i1-IQ2_M.gguf new file mode 100644 index 0000000..b016813 --- /dev/null +++ b/L3.1-Pneuma-8B.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:752eb5d0a6d1ceed5e04e9cb9ab384229c86c04902a0752bc7321e40fedbd553 +size 2948286496 diff --git a/L3.1-Pneuma-8B.i1-IQ2_S.gguf b/L3.1-Pneuma-8B.i1-IQ2_S.gguf new file mode 100644 index 0000000..32b11ba --- /dev/null +++ b/L3.1-Pneuma-8B.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5666610ba956300c0c6e5b02537d01fb69471b6cb8beece44ddd67922bb39cdd +size 2758494240 diff --git a/L3.1-Pneuma-8B.i1-IQ2_XS.gguf b/L3.1-Pneuma-8B.i1-IQ2_XS.gguf new file mode 100644 index 0000000..21d3d77 --- /dev/null +++ b/L3.1-Pneuma-8B.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a1f3609c58532bc4fe849120ddcba7e4c195a386f61bf54f97d432db12474fa +size 2605787168 diff --git a/L3.1-Pneuma-8B.i1-IQ2_XXS.gguf b/L3.1-Pneuma-8B.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..0456f96 --- /dev/null +++ b/L3.1-Pneuma-8B.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d9d4e49c182f88223206c97a0c950ebd3a13e02cbce5e5f597edb95234edf22 +size 2399217696 diff --git a/L3.1-Pneuma-8B.i1-IQ3_M.gguf b/L3.1-Pneuma-8B.i1-IQ3_M.gguf new file mode 100644 index 0000000..80227ed --- /dev/null +++ b/L3.1-Pneuma-8B.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0789b17ca3f744bca10922379f8dc561849441be5368a9a2158692ad96cedef +size 3784828960 diff --git a/L3.1-Pneuma-8B.i1-IQ3_S.gguf b/L3.1-Pneuma-8B.i1-IQ3_S.gguf new file mode 100644 index 0000000..364c31c --- /dev/null +++ b/L3.1-Pneuma-8B.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8cb2768fcb3a635e009a584a6fc794c006dc175311ae52673512a63e6d632c42 +size 3682330656 diff --git a/L3.1-Pneuma-8B.i1-IQ3_XS.gguf b/L3.1-Pneuma-8B.i1-IQ3_XS.gguf new file mode 100644 index 0000000..9fbf225 --- /dev/null +++ b/L3.1-Pneuma-8B.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e399244bb91074cde4f6ea4747c9ad9f52dc1b5d795cb7fda298a530903be51 +size 3518752800 diff --git a/L3.1-Pneuma-8B.i1-IQ3_XXS.gguf b/L3.1-Pneuma-8B.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..52bae83 --- /dev/null +++ b/L3.1-Pneuma-8B.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e592e6845cbb4506cd4437f7364ba335c63517a4e645035600af57911ce86bbd +size 3274917920 diff --git a/L3.1-Pneuma-8B.i1-IQ4_XS.gguf b/L3.1-Pneuma-8B.i1-IQ4_XS.gguf new file mode 100644 index 0000000..f443f8e --- /dev/null +++ b/L3.1-Pneuma-8B.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f85ff48fa179372295e8166f3854da59b144cb8250a27f886ecc18717440486 +size 4447668256 diff --git a/L3.1-Pneuma-8B.i1-Q2_K.gguf b/L3.1-Pneuma-8B.i1-Q2_K.gguf new file mode 100644 index 0000000..28c4592 --- /dev/null +++ b/L3.1-Pneuma-8B.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec1d413e0c9789b421fc8601fc5b84c5c48f3fd9ebacf5e881f10ef12459dfdf +size 3179137056 diff --git a/L3.1-Pneuma-8B.i1-Q2_K_S.gguf b/L3.1-Pneuma-8B.i1-Q2_K_S.gguf new file mode 100644 index 0000000..771c027 --- /dev/null +++ b/L3.1-Pneuma-8B.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6738371b5453d0c8a1c1b9297beabd666377f5f4683f3739978b53e56d4b153c +size 2988820512 diff --git a/L3.1-Pneuma-8B.i1-Q3_K_L.gguf b/L3.1-Pneuma-8B.i1-Q3_K_L.gguf new file mode 100644 index 0000000..290c781 --- /dev/null +++ b/L3.1-Pneuma-8B.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ba039e767f8f51cfec9f3036af28644cbcb01ebf36c1977b830a9344d7fec10 +size 4321962016 diff --git a/L3.1-Pneuma-8B.i1-Q3_K_M.gguf b/L3.1-Pneuma-8B.i1-Q3_K_M.gguf new file mode 100644 index 0000000..4101409 --- /dev/null +++ b/L3.1-Pneuma-8B.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa7206c642572f52a501d0dc7d935a2dc6728315df8b38b444aae85c4664f507 +size 4018923552 diff --git a/L3.1-Pneuma-8B.i1-Q3_K_S.gguf b/L3.1-Pneuma-8B.i1-Q3_K_S.gguf new file mode 100644 index 0000000..842289b --- /dev/null +++ b/L3.1-Pneuma-8B.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14b77c12d85924528b0edd254c0560b564da061a2b4e660f57f010478c063f23 +size 3664504864 diff --git a/L3.1-Pneuma-8B.i1-Q4_0.gguf b/L3.1-Pneuma-8B.i1-Q4_0.gguf new file mode 100644 index 0000000..1a3265a --- /dev/null +++ b/L3.1-Pneuma-8B.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1a948b65859565ef161fc09c9c20e5c27a43c971d27821af483da20f0dd2fef +size 4675897376 diff --git a/L3.1-Pneuma-8B.i1-Q4_0_4_4.gguf b/L3.1-Pneuma-8B.i1-Q4_0_4_4.gguf new file mode 100644 index 0000000..41325e4 --- /dev/null +++ b/L3.1-Pneuma-8B.i1-Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:38abef8552c9379c43466358b2711eee09ed2a0655b9820ddddb7b50ed1f2488 +size 4661217312 diff --git a/L3.1-Pneuma-8B.i1-Q4_0_4_8.gguf b/L3.1-Pneuma-8B.i1-Q4_0_4_8.gguf new file mode 100644 index 0000000..9b83155 --- /dev/null +++ b/L3.1-Pneuma-8B.i1-Q4_0_4_8.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b739acf5cc6647eb9bfc70c24051a36dd222c401ff8c436ef1db9a377612b33b +size 4661217312 diff --git a/L3.1-Pneuma-8B.i1-Q4_0_8_8.gguf b/L3.1-Pneuma-8B.i1-Q4_0_8_8.gguf new file mode 100644 index 0000000..c20810c --- /dev/null +++ b/L3.1-Pneuma-8B.i1-Q4_0_8_8.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53737a159daa227808a20514400cf0527d7fb8d46b016d55fc5d66bff9d4d1f4 +size 4661217312 diff --git a/L3.1-Pneuma-8B.i1-Q4_K_M.gguf b/L3.1-Pneuma-8B.i1-Q4_K_M.gguf new file mode 100644 index 0000000..1ce254f --- /dev/null +++ b/L3.1-Pneuma-8B.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f7b254239a55038ea1f2a959e0ea85f233f1a06f7d75dbc88350f1715bb04d3 +size 4920739872 diff --git a/L3.1-Pneuma-8B.i1-Q4_K_S.gguf b/L3.1-Pneuma-8B.i1-Q4_K_S.gguf new file mode 100644 index 0000000..81c103c --- /dev/null +++ b/L3.1-Pneuma-8B.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e5a112200b30759ae52b6c03eb2e34fee621a724970336bcbf3922ff8a9f37e +size 4692674592 diff --git a/L3.1-Pneuma-8B.i1-Q5_K_M.gguf b/L3.1-Pneuma-8B.i1-Q5_K_M.gguf new file mode 100644 index 0000000..6720ddf --- /dev/null +++ b/L3.1-Pneuma-8B.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68d516ea4cab04df061ca65c39f74e55db17840b9e34198ba054359da3c7ae10 +size 5732993056 diff --git a/L3.1-Pneuma-8B.i1-Q5_K_S.gguf b/L3.1-Pneuma-8B.i1-Q5_K_S.gguf new file mode 100644 index 0000000..ba6a0ac --- /dev/null +++ b/L3.1-Pneuma-8B.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df27ed2282e5f6e11c86baacb8708a2950e7d990defd1a7a764764137f7b8c67 +size 5599299616 diff --git a/L3.1-Pneuma-8B.i1-Q6_K.gguf b/L3.1-Pneuma-8B.i1-Q6_K.gguf new file mode 100644 index 0000000..1476175 --- /dev/null +++ b/L3.1-Pneuma-8B.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d9825e38b3ea2a25d10f089a77c00eb732ea61f9c5d7c2b0dc575190fae6341 +size 6596012064 diff --git a/README.md b/README.md new file mode 100644 index 0000000..8417343 --- /dev/null +++ b/README.md @@ -0,0 +1,85 @@ +--- +base_model: Third-Space/L3.1-Pneuma-8B +language: +- en +library_name: transformers +license: llama3.1 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- axolotl +- generated_from_trainer +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/Third-Space/L3.1-Pneuma-8B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#L3.1-Pneuma-8B-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/L3.1-Pneuma-8B-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/L3.1-Pneuma-8B-i1-GGUF/resolve/main/L3.1-Pneuma-8B.i1-IQ1_S.gguf) | i1-IQ1_S | 2.1 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Pneuma-8B-i1-GGUF/resolve/main/L3.1-Pneuma-8B.i1-IQ1_M.gguf) | i1-IQ1_M | 2.3 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Pneuma-8B-i1-GGUF/resolve/main/L3.1-Pneuma-8B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Pneuma-8B-i1-GGUF/resolve/main/L3.1-Pneuma-8B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Pneuma-8B-i1-GGUF/resolve/main/L3.1-Pneuma-8B.i1-IQ2_S.gguf) | i1-IQ2_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Pneuma-8B-i1-GGUF/resolve/main/L3.1-Pneuma-8B.i1-IQ2_M.gguf) | i1-IQ2_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Pneuma-8B-i1-GGUF/resolve/main/L3.1-Pneuma-8B.i1-Q2_K_S.gguf) | i1-Q2_K_S | 3.1 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Pneuma-8B-i1-GGUF/resolve/main/L3.1-Pneuma-8B.i1-Q2_K.gguf) | i1-Q2_K | 3.3 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Pneuma-8B-i1-GGUF/resolve/main/L3.1-Pneuma-8B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Pneuma-8B-i1-GGUF/resolve/main/L3.1-Pneuma-8B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Pneuma-8B-i1-GGUF/resolve/main/L3.1-Pneuma-8B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.8 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Pneuma-8B-i1-GGUF/resolve/main/L3.1-Pneuma-8B.i1-IQ3_S.gguf) | i1-IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Pneuma-8B-i1-GGUF/resolve/main/L3.1-Pneuma-8B.i1-IQ3_M.gguf) | i1-IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Pneuma-8B-i1-GGUF/resolve/main/L3.1-Pneuma-8B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.1 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Pneuma-8B-i1-GGUF/resolve/main/L3.1-Pneuma-8B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.4 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Pneuma-8B-i1-GGUF/resolve/main/L3.1-Pneuma-8B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Pneuma-8B-i1-GGUF/resolve/main/L3.1-Pneuma-8B.i1-Q4_0_4_4.gguf) | i1-Q4_0_4_4 | 4.8 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Pneuma-8B-i1-GGUF/resolve/main/L3.1-Pneuma-8B.i1-Q4_0_4_8.gguf) | i1-Q4_0_4_8 | 4.8 | fast on arm+i8mm, low quality | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Pneuma-8B-i1-GGUF/resolve/main/L3.1-Pneuma-8B.i1-Q4_0_8_8.gguf) | i1-Q4_0_8_8 | 4.8 | fast on arm+sve, low quality | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Pneuma-8B-i1-GGUF/resolve/main/L3.1-Pneuma-8B.i1-Q4_0.gguf) | i1-Q4_0 | 4.8 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Pneuma-8B-i1-GGUF/resolve/main/L3.1-Pneuma-8B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.8 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Pneuma-8B-i1-GGUF/resolve/main/L3.1-Pneuma-8B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Pneuma-8B-i1-GGUF/resolve/main/L3.1-Pneuma-8B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Pneuma-8B-i1-GGUF/resolve/main/L3.1-Pneuma-8B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Pneuma-8B-i1-GGUF/resolve/main/L3.1-Pneuma-8B.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..9b94f87 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2738aa1fb8c6790837fa4482ca1b6851a0c4a1bc115d08bf70bbfb361d4955d0 +size 4988157