初始化项目，由ModelHub XC社区提供模型

Model: bartowski/CrucibleLab_M3.2-24B-Loki-V1.3-GGUF
Source: Original Platform

.gitattributes

@@ -0,0 +1,47 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bin.* filter=lfs diff=lfs merge=lfs -text
+*.bz2 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
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack 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
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* 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
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*.tfevents* filter=lfs diff=lfs merge=lfs -text
+*.db* filter=lfs diff=lfs merge=lfs -text
+*.ark* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.gguf* filter=lfs diff=lfs merge=lfs -text
+*.ggml filter=lfs diff=lfs merge=lfs -text
+*.llamafile* filter=lfs diff=lfs merge=lfs -text
+*.pt2 filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

CrucibleLab_M3.2-24B-Loki-V1.3-IQ2_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d50ba81e69e0e410a475dcbdcc2f6f7f540993cc06361a8917379d38227afdd9
+size 8114052416

CrucibleLab_M3.2-24B-Loki-V1.3-IQ2_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1242772e6d840522b4af9b843bf0b0ef41192ff9b08e5cb7a6cbcda539fb5e85
+size 7478353216

CrucibleLab_M3.2-24B-Loki-V1.3-IQ2_XS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e249e91997f89bfb39dedb9f308338d06bf37db2b5f5d3d5892c9a14930d0a1a
+size 7207034176

CrucibleLab_M3.2-24B-Loki-V1.3-IQ3_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14f54c835a7fcd46c20846d25916d98c2d1a5f8d78c8674eafa43e26625461c7
+size 10650950976

CrucibleLab_M3.2-24B-Loki-V1.3-IQ3_XS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1ebb095ddcbc2b2189185030fae531c77cfc7c54d68ec6907f1ec5e35caf878
+size 9907117376

CrucibleLab_M3.2-24B-Loki-V1.3-IQ3_XXS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4cdbf73cf7e3e0200a07c3b31dbb08cc917f0773d90f56158a8c9671a52a26e
+size 9280593216

CrucibleLab_M3.2-24B-Loki-V1.3-IQ4_NL.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07594ea548a89f5a2ac0013aeb2bbc6b70277a7b83484a242bbd339f01a1e6e9
+size 13468015936

CrucibleLab_M3.2-24B-Loki-V1.3-IQ4_XS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff6fed6619af1ef59a8efe1f4659820906d53ce0080cb246a05808575eb37c07
+size 12758916416

CrucibleLab_M3.2-24B-Loki-V1.3-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e564c61483ec03e7349fc68562009be0944a987b35b0ef3af860a8b20325ecb
+size 8890326336

CrucibleLab_M3.2-24B-Loki-V1.3-Q2_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6413fe973061aa3f915e0987a10e28bf6ff86efbdcfd8e90d1239db2cfc10999
+size 9545686336

CrucibleLab_M3.2-24B-Loki-V1.3-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97fe411e24ac072f6e9b5da2d707f495fd2d5e010dc2d5e4d21c95d6aa09e1ad
+size 12400762176

CrucibleLab_M3.2-24B-Loki-V1.3-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2cbde20d08168f2d22626caf4ccbcfb66684ea736e6401613ca840670ea4a93
+size 11474083136

CrucibleLab_M3.2-24B-Loki-V1.3-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:171a398531e5235b57a5191d3fc4c5f6081a38df067ec836bf19e2984cb134b1
+size 10400275776

CrucibleLab_M3.2-24B-Loki-V1.3-Q3_K_XL.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39e98e7209b61689011b90a96a4182117dca24b2ab64c8aa97b891307825c23a
+size 12987964736

CrucibleLab_M3.2-24B-Loki-V1.3-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e950d58fa3aed37ca5f584ab80bdc7303e1b7567defa007de6b6b4a94769518a
+size 13494230336

CrucibleLab_M3.2-24B-Loki-V1.3-Q4_1.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3c4591ec3262848ae5de8bdfe44da930aa145a50c5ac553cbfaea7f015897e4
+size 14873107776

CrucibleLab_M3.2-24B-Loki-V1.3-Q4_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:278f3e898011099338c3db30b9f26bfb65ed83d460ca4bd6174155a9699595ff
+size 14831983936

CrucibleLab_M3.2-24B-Loki-V1.3-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2006141edc4e917de6c1f81677fe4ef1a71374059f553f1b5bbfac3a9132cf70
+size 14333910336

CrucibleLab_M3.2-24B-Loki-V1.3-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:364b66613a19f4bae972d45741009ea142111e1434a3d9e38cbde2ea2ddfc8ad
+size 13549280576

CrucibleLab_M3.2-24B-Loki-V1.3-Q5_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e1f708c1f4a3973d24e76979e20b28d882c5085dcfd556d6ac14c9adbf98cad
+size 17178172736

CrucibleLab_M3.2-24B-Loki-V1.3-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31711bf660e3fd2960f2c185af7aa8ed7ebc0160490dfeec3a6d519529eb4cef
+size 16763985216

CrucibleLab_M3.2-24B-Loki-V1.3-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0fac9719c10a4d9b13203a637eabe2c5a3fd0def32329c42f5541d54dee9d8e
+size 16304414016

CrucibleLab_M3.2-24B-Loki-V1.3-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2dea23e50dc3f41639d9492a545341991a034cce9a5c9eb5e1158b2b87e1b0e8
+size 19345939776

CrucibleLab_M3.2-24B-Loki-V1.3-Q6_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:147e897a4c0e9debef06033e73204587cc57be0a6a4cb0ea637e779bdc8e1c8a
+size 19670998336

CrucibleLab_M3.2-24B-Loki-V1.3-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3922553b4b99555119949d23fb613661b1967cb728958ea0849a49e4128d5e7a
+size 25054780736

CrucibleLab_M3.2-24B-Loki-V1.3-bf16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17089dc7f563e29a229ac853d73a5a803055c8b4efe16baceaf059a0565fdb66
+size 47153519648

CrucibleLab_M3.2-24B-Loki-V1.3-imatrix.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25956c8d40c082d84353174f086f37d62a90cdef799af00c7cf455bf5855cb75
+size 10037344

README.md

@@ -0,0 +1,166 @@
+---
+quantized_by: bartowski
+pipeline_tag: text-generation
+base_model: CrucibleLab/M3.2-24B-Loki-V1.3
+base_model_relation: quantized
+---
+
+## Llamacpp imatrix Quantizations of M3.2-24B-Loki-V1.3 by CrucibleLab
+
+Using <a href="https://github.com/ggml-org/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggml-org/llama.cpp/releases/tag/b6258">b6258</a> for quantization.
+
+Original model: https://huggingface.co/CrucibleLab/M3.2-24B-Loki-V1.3
+
+All quants made using imatrix option with dataset from [here](https://gist.github.com/bartowski1182/eb213dccb3571f863da82e99418f81e8) combined with a subset of combined_all_small.parquet from Ed Addario [here](https://huggingface.co/datasets/eaddario/imatrix-calibration/blob/main/combined_all_small.parquet)
+
+Run them in [LM Studio](https://lmstudio.ai/)
+
+Run them directly with [llama.cpp](https://github.com/ggml-org/llama.cpp), or any other llama.cpp based project
+
+## Prompt format
+
+No prompt format found, check original model page
+
+## Download a file (not the whole branch) from below:
+
+| Filename | Quant type | File Size | Split | Description |
+| -------- | ---------- | --------- | ----- | ----------- |
+| [M3.2-24B-Loki-V1.3-bf16.gguf](https://huggingface.co/bartowski/CrucibleLab_M3.2-24B-Loki-V1.3-GGUF/blob/main/CrucibleLab_M3.2-24B-Loki-V1.3-bf16.gguf) | bf16 | 47.15GB | false | Full BF16 weights. |
+| [M3.2-24B-Loki-V1.3-Q8_0.gguf](https://huggingface.co/bartowski/CrucibleLab_M3.2-24B-Loki-V1.3-GGUF/blob/main/CrucibleLab_M3.2-24B-Loki-V1.3-Q8_0.gguf) | Q8_0 | 25.05GB | false | Extremely high quality, generally unneeded but max available quant. |
+| [M3.2-24B-Loki-V1.3-Q6_K_L.gguf](https://huggingface.co/bartowski/CrucibleLab_M3.2-24B-Loki-V1.3-GGUF/blob/main/CrucibleLab_M3.2-24B-Loki-V1.3-Q6_K_L.gguf) | Q6_K_L | 19.67GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. |
+| [M3.2-24B-Loki-V1.3-Q6_K.gguf](https://huggingface.co/bartowski/CrucibleLab_M3.2-24B-Loki-V1.3-GGUF/blob/main/CrucibleLab_M3.2-24B-Loki-V1.3-Q6_K.gguf) | Q6_K | 19.35GB | false | Very high quality, near perfect, *recommended*. |
+| [M3.2-24B-Loki-V1.3-Q5_K_L.gguf](https://huggingface.co/bartowski/CrucibleLab_M3.2-24B-Loki-V1.3-GGUF/blob/main/CrucibleLab_M3.2-24B-Loki-V1.3-Q5_K_L.gguf) | Q5_K_L | 17.18GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. |
+| [M3.2-24B-Loki-V1.3-Q5_K_M.gguf](https://huggingface.co/bartowski/CrucibleLab_M3.2-24B-Loki-V1.3-GGUF/blob/main/CrucibleLab_M3.2-24B-Loki-V1.3-Q5_K_M.gguf) | Q5_K_M | 16.76GB | false | High quality, *recommended*. |
+| [M3.2-24B-Loki-V1.3-Q5_K_S.gguf](https://huggingface.co/bartowski/CrucibleLab_M3.2-24B-Loki-V1.3-GGUF/blob/main/CrucibleLab_M3.2-24B-Loki-V1.3-Q5_K_S.gguf) | Q5_K_S | 16.30GB | false | High quality, *recommended*. |
+| [M3.2-24B-Loki-V1.3-Q4_1.gguf](https://huggingface.co/bartowski/CrucibleLab_M3.2-24B-Loki-V1.3-GGUF/blob/main/CrucibleLab_M3.2-24B-Loki-V1.3-Q4_1.gguf) | Q4_1 | 14.87GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. |
+| [M3.2-24B-Loki-V1.3-Q4_K_L.gguf](https://huggingface.co/bartowski/CrucibleLab_M3.2-24B-Loki-V1.3-GGUF/blob/main/CrucibleLab_M3.2-24B-Loki-V1.3-Q4_K_L.gguf) | Q4_K_L | 14.83GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. |
+| [M3.2-24B-Loki-V1.3-Q4_K_M.gguf](https://huggingface.co/bartowski/CrucibleLab_M3.2-24B-Loki-V1.3-GGUF/blob/main/CrucibleLab_M3.2-24B-Loki-V1.3-Q4_K_M.gguf) | Q4_K_M | 14.33GB | false | Good quality, default size for most use cases, *recommended*. |
+| [M3.2-24B-Loki-V1.3-Q4_K_S.gguf](https://huggingface.co/bartowski/CrucibleLab_M3.2-24B-Loki-V1.3-GGUF/blob/main/CrucibleLab_M3.2-24B-Loki-V1.3-Q4_K_S.gguf) | Q4_K_S | 13.55GB | false | Slightly lower quality with more space savings, *recommended*. |
+| [M3.2-24B-Loki-V1.3-Q4_0.gguf](https://huggingface.co/bartowski/CrucibleLab_M3.2-24B-Loki-V1.3-GGUF/blob/main/CrucibleLab_M3.2-24B-Loki-V1.3-Q4_0.gguf) | Q4_0 | 13.49GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. |
+| [M3.2-24B-Loki-V1.3-IQ4_NL.gguf](https://huggingface.co/bartowski/CrucibleLab_M3.2-24B-Loki-V1.3-GGUF/blob/main/CrucibleLab_M3.2-24B-Loki-V1.3-IQ4_NL.gguf) | IQ4_NL | 13.47GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. |
+| [M3.2-24B-Loki-V1.3-Q3_K_XL.gguf](https://huggingface.co/bartowski/CrucibleLab_M3.2-24B-Loki-V1.3-GGUF/blob/main/CrucibleLab_M3.2-24B-Loki-V1.3-Q3_K_XL.gguf) | Q3_K_XL | 12.99GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. |
+| [M3.2-24B-Loki-V1.3-IQ4_XS.gguf](https://huggingface.co/bartowski/CrucibleLab_M3.2-24B-Loki-V1.3-GGUF/blob/main/CrucibleLab_M3.2-24B-Loki-V1.3-IQ4_XS.gguf) | IQ4_XS | 12.76GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
+| [M3.2-24B-Loki-V1.3-Q3_K_L.gguf](https://huggingface.co/bartowski/CrucibleLab_M3.2-24B-Loki-V1.3-GGUF/blob/main/CrucibleLab_M3.2-24B-Loki-V1.3-Q3_K_L.gguf) | Q3_K_L | 12.40GB | false | Lower quality but usable, good for low RAM availability. |
+| [M3.2-24B-Loki-V1.3-Q3_K_M.gguf](https://huggingface.co/bartowski/CrucibleLab_M3.2-24B-Loki-V1.3-GGUF/blob/main/CrucibleLab_M3.2-24B-Loki-V1.3-Q3_K_M.gguf) | Q3_K_M | 11.47GB | false | Low quality. |
+| [M3.2-24B-Loki-V1.3-IQ3_M.gguf](https://huggingface.co/bartowski/CrucibleLab_M3.2-24B-Loki-V1.3-GGUF/blob/main/CrucibleLab_M3.2-24B-Loki-V1.3-IQ3_M.gguf) | IQ3_M | 10.65GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
+| [M3.2-24B-Loki-V1.3-Q3_K_S.gguf](https://huggingface.co/bartowski/CrucibleLab_M3.2-24B-Loki-V1.3-GGUF/blob/main/CrucibleLab_M3.2-24B-Loki-V1.3-Q3_K_S.gguf) | Q3_K_S | 10.40GB | false | Low quality, not recommended. |
+| [M3.2-24B-Loki-V1.3-IQ3_XS.gguf](https://huggingface.co/bartowski/CrucibleLab_M3.2-24B-Loki-V1.3-GGUF/blob/main/CrucibleLab_M3.2-24B-Loki-V1.3-IQ3_XS.gguf) | IQ3_XS | 9.91GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
+| [M3.2-24B-Loki-V1.3-Q2_K_L.gguf](https://huggingface.co/bartowski/CrucibleLab_M3.2-24B-Loki-V1.3-GGUF/blob/main/CrucibleLab_M3.2-24B-Loki-V1.3-Q2_K_L.gguf) | Q2_K_L | 9.55GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. |
+| [M3.2-24B-Loki-V1.3-IQ3_XXS.gguf](https://huggingface.co/bartowski/CrucibleLab_M3.2-24B-Loki-V1.3-GGUF/blob/main/CrucibleLab_M3.2-24B-Loki-V1.3-IQ3_XXS.gguf) | IQ3_XXS | 9.28GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. |
+| [M3.2-24B-Loki-V1.3-Q2_K.gguf](https://huggingface.co/bartowski/CrucibleLab_M3.2-24B-Loki-V1.3-GGUF/blob/main/CrucibleLab_M3.2-24B-Loki-V1.3-Q2_K.gguf) | Q2_K | 8.89GB | false | Very low quality but surprisingly usable. |
+| [M3.2-24B-Loki-V1.3-IQ2_M.gguf](https://huggingface.co/bartowski/CrucibleLab_M3.2-24B-Loki-V1.3-GGUF/blob/main/CrucibleLab_M3.2-24B-Loki-V1.3-IQ2_M.gguf) | IQ2_M | 8.11GB | false | Relatively low quality, uses SOTA techniques to be surprisingly usable. |
+| [M3.2-24B-Loki-V1.3-IQ2_S.gguf](https://huggingface.co/bartowski/CrucibleLab_M3.2-24B-Loki-V1.3-GGUF/blob/main/CrucibleLab_M3.2-24B-Loki-V1.3-IQ2_S.gguf) | IQ2_S | 7.48GB | false | Low quality, uses SOTA techniques to be usable. |
+| [M3.2-24B-Loki-V1.3-IQ2_XS.gguf](https://huggingface.co/bartowski/CrucibleLab_M3.2-24B-Loki-V1.3-GGUF/blob/main/CrucibleLab_M3.2-24B-Loki-V1.3-IQ2_XS.gguf) | IQ2_XS | 7.21GB | false | Low quality, uses SOTA techniques to be usable. |
+
+## Embed/output weights
+
+Some of these quants (Q3_K_XL, Q4_K_L etc) are the standard quantization method with the embeddings and output weights quantized to Q8_0 instead of what they would normally default to.
+
+## Downloading using huggingface-cli
+
+<details>
+  <summary>Click to view download instructions</summary>
+
+First, make sure you have hugginface-cli installed:
+
+```
+pip install -U "huggingface_hub[cli]"
+```
+
+Then, you can target the specific file you want:
+
+```
+huggingface-cli download bartowski/CrucibleLab_M3.2-24B-Loki-V1.3-GGUF --include "CrucibleLab_M3.2-24B-Loki-V1.3-Q4_K_M.gguf" --local-dir ./
+```
+
+If the model is bigger than 50GB, it will have been split into multiple files. In order to download them all to a local folder, run:
+
+```
+huggingface-cli download bartowski/CrucibleLab_M3.2-24B-Loki-V1.3-GGUF --include "CrucibleLab_M3.2-24B-Loki-V1.3-Q8_0/*" --local-dir ./
+```
+
+You can either specify a new local-dir (CrucibleLab_M3.2-24B-Loki-V1.3-Q8_0) or download them all in place (./)
+
+</details>
+
+## ARM/AVX information
+
+Previously, you would download Q4_0_4_4/4_8/8_8, and these would have their weights interleaved in memory in order to improve performance on ARM and AVX machines by loading up more data in one pass.
+
+Now, however, there is something called "online repacking" for weights. details in [this PR](https://github.com/ggml-org/llama.cpp/pull/9921). If you use Q4_0 and your hardware would benefit from repacking weights, it will do it automatically on the fly.
+
+As of llama.cpp build [b4282](https://github.com/ggml-org/llama.cpp/releases/tag/b4282) you will not be able to run the Q4_0_X_X files and will instead need to use Q4_0.
+
+Additionally, if you want to get slightly better quality for , you can use IQ4_NL thanks to [this PR](https://github.com/ggml-org/llama.cpp/pull/10541) which will also repack the weights for ARM, though only the 4_4 for now. The loading time may be slower but it will result in an overall speed incrase.
+
+<details>
+  <summary>Click to view Q4_0_X_X information (deprecated</summary>
+
+I'm keeping this section to show the potential theoretical uplift in performance from using the Q4_0 with online repacking.
+
+<details>
+  <summary>Click to view benchmarks on an AVX2 system (EPYC7702)</summary>
+
+| model                          |       size |     params | backend    | threads |          test |                  t/s |  % (vs Q4_0)  |
+| ------------------------------ | ---------: | ---------: | ---------- | ------: | ------------: | -------------------: |-------------: |
+| qwen2 3B Q4_0                  |   1.70 GiB |     3.09 B | CPU        |      64 |         pp512 |        204.03 ± 1.03 |          100% |
+| qwen2 3B Q4_0                  |   1.70 GiB |     3.09 B | CPU        |      64 |        pp1024 |        282.92 ± 0.19 |          100% |
+| qwen2 3B Q4_0                  |   1.70 GiB |     3.09 B | CPU        |      64 |        pp2048 |        259.49 ± 0.44 |          100% |
+| qwen2 3B Q4_0                  |   1.70 GiB |     3.09 B | CPU        |      64 |         tg128 |         39.12 ± 0.27 |          100% |
+| qwen2 3B Q4_0                  |   1.70 GiB |     3.09 B | CPU        |      64 |         tg256 |         39.31 ± 0.69 |          100% |
+| qwen2 3B Q4_0                  |   1.70 GiB |     3.09 B | CPU        |      64 |         tg512 |         40.52 ± 0.03 |          100% |
+| qwen2 3B Q4_K_M                |   1.79 GiB |     3.09 B | CPU        |      64 |         pp512 |        301.02 ± 1.74 |          147% |
+| qwen2 3B Q4_K_M                |   1.79 GiB |     3.09 B | CPU        |      64 |        pp1024 |        287.23 ± 0.20 |          101% |
+| qwen2 3B Q4_K_M                |   1.79 GiB |     3.09 B | CPU        |      64 |        pp2048 |        262.77 ± 1.81 |          101% |
+| qwen2 3B Q4_K_M                |   1.79 GiB |     3.09 B | CPU        |      64 |         tg128 |         18.80 ± 0.99 |           48% |
+| qwen2 3B Q4_K_M                |   1.79 GiB |     3.09 B | CPU        |      64 |         tg256 |         24.46 ± 3.04 |           83% |
+| qwen2 3B Q4_K_M                |   1.79 GiB |     3.09 B | CPU        |      64 |         tg512 |         36.32 ± 3.59 |           90% |
+| qwen2 3B Q4_0_8_8              |   1.69 GiB |     3.09 B | CPU        |      64 |         pp512 |        271.71 ± 3.53 |          133% |
+| qwen2 3B Q4_0_8_8              |   1.69 GiB |     3.09 B | CPU        |      64 |        pp1024 |       279.86 ± 45.63 |          100% |
+| qwen2 3B Q4_0_8_8              |   1.69 GiB |     3.09 B | CPU        |      64 |        pp2048 |        320.77 ± 5.00 |          124% |
+| qwen2 3B Q4_0_8_8              |   1.69 GiB |     3.09 B | CPU        |      64 |         tg128 |         43.51 ± 0.05 |          111% |
+| qwen2 3B Q4_0_8_8              |   1.69 GiB |     3.09 B | CPU        |      64 |         tg256 |         43.35 ± 0.09 |          110% |
+| qwen2 3B Q4_0_8_8              |   1.69 GiB |     3.09 B | CPU        |      64 |         tg512 |         42.60 ± 0.31 |          105% |
+
+Q4_0_8_8 offers a nice bump to prompt processing and a small bump to text generation
+
+</details>
+
+</details>
+
+## Which file should I choose?
+
+<details>
+  <summary>Click here for details</summary>
+
+A great write up with charts showing various performances is provided by Artefact2 [here](https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9)
+
+The first thing to figure out is how big a model you can run. To do this, you'll need to figure out how much RAM and/or VRAM you have.
+
+If you want your model running as FAST as possible, you'll want to fit the whole thing on your GPU's VRAM. Aim for a quant with a file size 1-2GB smaller than your GPU's total VRAM.
+
+If you want the absolute maximum quality, add both your system RAM and your GPU's VRAM together, then similarly grab a quant with a file size 1-2GB Smaller than that total.
+
+Next, you'll need to decide if you want to use an 'I-quant' or a 'K-quant'.
+
+If you don't want to think too much, grab one of the K-quants. These are in format 'QX_K_X', like Q5_K_M.
+
+If you want to get more into the weeds, you can check out this extremely useful feature chart:
+
+[llama.cpp feature matrix](https://github.com/ggml-org/llama.cpp/wiki/Feature-matrix)
+
+But basically, if you're aiming for below Q4, and you're running cuBLAS (Nvidia) or rocBLAS (AMD), you should look towards the I-quants. These are in format IQX_X, like IQ3_M. These are newer and offer better performance for their size.
+
+These I-quants can also be used on CPU, but will be slower than their K-quant equivalent, so speed vs performance is a tradeoff you'll have to decide.
+
+</details>
+
+## Credits
+
+Thank you kalomaze and Dampf for assistance in creating the imatrix calibration dataset.
+
+Thank you ZeroWw for the inspiration to experiment with embed/output.
+
+Thank you to LM Studio for sponsoring my work.
+
+Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski

configuration.json

@@ -0,0 +1 @@
+{"framework": "pytorch", "task": "text-generation", "allow_remote": true}