Hugging Face's logo

Alcoft
/
HuggingFaceTB_SmolLM3-3B-GGUF

Text Generation
GGUF
conversational
Model card Files
xet
 Community
Alcoft commited on
Commit
068209d
·
verified ·
1 Parent(s): 9677bff

Upload folder using huggingface_hub

Browse files
Files changed (24) hide show
  1. .gitattributes +22 -0
  2. HuggingFaceTB_SmolLM3-3B.gguf +3 -0
  3. HuggingFaceTB_SmolLM3-3B_F16.gguf +3 -0
  4. HuggingFaceTB_SmolLM3-3B_Q2_K.gguf +3 -0
  5. HuggingFaceTB_SmolLM3-3B_Q2_K_L.gguf +3 -0
  6. HuggingFaceTB_SmolLM3-3B_Q2_K_XL.gguf +3 -0
  7. HuggingFaceTB_SmolLM3-3B_Q3_K_L.gguf +3 -0
  8. HuggingFaceTB_SmolLM3-3B_Q3_K_M.gguf +3 -0
  9. HuggingFaceTB_SmolLM3-3B_Q3_K_S.gguf +3 -0
  10. HuggingFaceTB_SmolLM3-3B_Q3_K_XL.gguf +3 -0
  11. HuggingFaceTB_SmolLM3-3B_Q3_K_XXL.gguf +3 -0
  12. HuggingFaceTB_SmolLM3-3B_Q4_K_L.gguf +3 -0
  13. HuggingFaceTB_SmolLM3-3B_Q4_K_M.gguf +3 -0
  14. HuggingFaceTB_SmolLM3-3B_Q4_K_S.gguf +3 -0
  15. HuggingFaceTB_SmolLM3-3B_Q4_K_XL.gguf +3 -0
  16. HuggingFaceTB_SmolLM3-3B_Q5_K_L.gguf +3 -0
  17. HuggingFaceTB_SmolLM3-3B_Q5_K_M.gguf +3 -0
  18. HuggingFaceTB_SmolLM3-3B_Q5_K_S.gguf +3 -0
  19. HuggingFaceTB_SmolLM3-3B_Q5_K_XL.gguf +3 -0
  20. HuggingFaceTB_SmolLM3-3B_Q6_K.gguf +3 -0
  21. HuggingFaceTB_SmolLM3-3B_Q6_K_L.gguf +3 -0
  22. HuggingFaceTB_SmolLM3-3B_Q6_K_XL.gguf +3 -0
  23. HuggingFaceTB_SmolLM3-3B_Q8_0.gguf +3 -0
  24. README.md +35 -0
.gitattributes CHANGED
@@ -33,3 +33,25 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ HuggingFaceTB_SmolLM3-3B.gguf filter=lfs diff=lfs merge=lfs -text
37
+ HuggingFaceTB_SmolLM3-3B_F16.gguf filter=lfs diff=lfs merge=lfs -text
38
+ HuggingFaceTB_SmolLM3-3B_Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
39
+ HuggingFaceTB_SmolLM3-3B_Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text
40
+ HuggingFaceTB_SmolLM3-3B_Q2_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
41
+ HuggingFaceTB_SmolLM3-3B_Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
42
+ HuggingFaceTB_SmolLM3-3B_Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
43
+ HuggingFaceTB_SmolLM3-3B_Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
44
+ HuggingFaceTB_SmolLM3-3B_Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
45
+ HuggingFaceTB_SmolLM3-3B_Q3_K_XXL.gguf filter=lfs diff=lfs merge=lfs -text
46
+ HuggingFaceTB_SmolLM3-3B_Q4_K_L.gguf filter=lfs diff=lfs merge=lfs -text
47
+ HuggingFaceTB_SmolLM3-3B_Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
48
+ HuggingFaceTB_SmolLM3-3B_Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
49
+ HuggingFaceTB_SmolLM3-3B_Q4_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
50
+ HuggingFaceTB_SmolLM3-3B_Q5_K_L.gguf filter=lfs diff=lfs merge=lfs -text
51
+ HuggingFaceTB_SmolLM3-3B_Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
52
+ HuggingFaceTB_SmolLM3-3B_Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
53
+ HuggingFaceTB_SmolLM3-3B_Q5_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
54
+ HuggingFaceTB_SmolLM3-3B_Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
55
+ HuggingFaceTB_SmolLM3-3B_Q6_K_L.gguf filter=lfs diff=lfs merge=lfs -text
56
+ HuggingFaceTB_SmolLM3-3B_Q6_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
57
+ HuggingFaceTB_SmolLM3-3B_Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
HuggingFaceTB_SmolLM3-3B.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f985540178662bcc7641c66c15caec4be5b27a5055fa8305aee5037b51826a4a
3
+ size 6158339904
HuggingFaceTB_SmolLM3-3B_F16.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c4122ee94376ba2152d0b5f8d54ef03c4e494bd18000fabb4c7b549c678f790
3
+ size 6158339904
HuggingFaceTB_SmolLM3-3B_Q2_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35359d6823d3d43ace2bc9af0260cb99414129e74032f0877646377c57a97066
3
+ size 1253302080
HuggingFaceTB_SmolLM3-3B_Q2_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05cee3808f46132d3daef25a9098eb5bd2b2abd351485c58502f98c3cde449f2
3
+ size 1316917056
HuggingFaceTB_SmolLM3-3B_Q2_K_XL.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b66e1dac41c7d8a42035285341a29509e0a5d99f7dc3ff9e19501beb1303b1f1
3
+ size 1563168576
HuggingFaceTB_SmolLM3-3B_Q3_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf65f227d1dff5476091b72814d0ce8a2a5919ca0e020be6631d8150a80c9867
3
+ size 1690214208
HuggingFaceTB_SmolLM3-3B_Q3_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1538818235ffaea9e6590276f191edaed630fe6382eaf30b366916b787a68916
3
+ size 1571069760
HuggingFaceTB_SmolLM3-3B_Q3_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa5a850bc24d304ce7c6caa5bbabee649e9c6de841b00140d34a649c5e609e87
3
+ size 1432313664
HuggingFaceTB_SmolLM3-3B_Q3_K_XL.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ec51a2095fbd255526d245c408cd49025395f130b2c42a5cdf8d73f3f21da77
3
+ size 1753829184
HuggingFaceTB_SmolLM3-3B_Q3_K_XXL.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f730bf479cf37259dae7abedcfbf0f8baf75b54e45c418c2f4fb269afbf11f9
3
+ size 2000080704
HuggingFaceTB_SmolLM3-3B_Q4_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de03fa239f43bb3221a1317a3a74e550b52f805c929d3ac154d7594e2ca898e7
3
+ size 1978920768
HuggingFaceTB_SmolLM3-3B_Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:327ec19dbef79f297963e37358c73191fbdda4c5473a2a1c5a9187db25d0047c
3
+ size 1915305792
HuggingFaceTB_SmolLM3-3B_Q4_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5624ab2225482553eacc00d830babaad5b2a46ca83fe860f05a60c30d32a259c
3
+ size 1817616192
HuggingFaceTB_SmolLM3-3B_Q4_K_XL.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63c87ac8bdbc201c971bc22ceff5074b418253a94658bae7609ca750b3bb18fa
3
+ size 2225172288
HuggingFaceTB_SmolLM3-3B_Q5_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3defddaafb701d80dcbc83769a00ecac8e80f7976abc5ad89ed20a37fb1247db
3
+ size 2277371712
HuggingFaceTB_SmolLM3-3B_Q5_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48ef556a88826cca7f057cf6b871fec59525ed9fc3338054ca11012f90ba51ab
3
+ size 2213756736
HuggingFaceTB_SmolLM3-3B_Q5_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b4580fa34b64ecd68ad0bafb2f9ec35d6039f02df3d807ba21ade09c8127eec
3
+ size 2157354816
HuggingFaceTB_SmolLM3-3B_Q5_K_XL.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dadf6b19d5e3b7c5116fd62fd976e02958635e028abe1f4a1c5c5d0a50fadcda
3
+ size 2523623232
HuggingFaceTB_SmolLM3-3B_Q6_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:278c9c15e3568a45d740d3e026f8048d1a1396e6292ea03e645138ed9e361b44
3
+ size 2530860864
HuggingFaceTB_SmolLM3-3B_Q6_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c20a97c6b622b3a8cec6d883f18a93b479b5ed3f9778111d6102961e0cda36f6
3
+ size 2594475840
HuggingFaceTB_SmolLM3-3B_Q6_K_XL.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f0b493b16158ef2427e092c72abd861ed3324e834d6021b686f70950592689f
3
+ size 2840727360
HuggingFaceTB_SmolLM3-3B_Q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f435a154a5100c049ef3c727fb09d30edb28c0b958232177710cc0d02845d310
3
+ size 3275575104
README.md ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model:
3
+ - HuggingFaceTB/SmolLM3-3B
4
+ pipeline_tag: text-generation
5
+ ---
6
+
7
+ |Quant|Size|Description|
8
+ |---|---|---|
9
+ |[Q2_K](https://huggingface.co/Alcoft/HuggingFaceTB_SmolLM3-3B-GGUF/resolve/main/output/HuggingFaceTB_SmolLM3-3B-GGUF/HuggingFaceTB_SmolLM3-3B_Q2_K.gguf)|1.17 GB|Not recommended for most people. Very low quality.|
10
+ |[Q2_K_L](https://huggingface.co/Alcoft/HuggingFaceTB_SmolLM3-3B-GGUF/resolve/main/output/HuggingFaceTB_SmolLM3-3B-GGUF/HuggingFaceTB_SmolLM3-3B_Q2_K_L.gguf)|1.23 GB|Not recommended for most people. Uses Q8_0 for output and embedding, and Q2_K for everything else. Very low quality.|
11
+ |[Q2_K_XL](https://huggingface.co/Alcoft/HuggingFaceTB_SmolLM3-3B-GGUF/resolve/main/output/HuggingFaceTB_SmolLM3-3B-GGUF/HuggingFaceTB_SmolLM3-3B_Q2_K_XL.gguf)|1.46 GB|Not recommended for most people. Uses F16 for output and embedding, and Q2_K for everything else. Very low quality.|
12
+ |[Q3_K_S](https://huggingface.co/Alcoft/HuggingFaceTB_SmolLM3-3B-GGUF/resolve/main/output/HuggingFaceTB_SmolLM3-3B-GGUF/HuggingFaceTB_SmolLM3-3B_Q3_K_S.gguf)|1.33 GB|Not recommended for most people. Prefer any bigger Q3_K quantization. Low quality.|
13
+ |[Q3_K_M](https://huggingface.co/Alcoft/HuggingFaceTB_SmolLM3-3B-GGUF/resolve/main/output/HuggingFaceTB_SmolLM3-3B-GGUF/HuggingFaceTB_SmolLM3-3B_Q3_K_M.gguf)|1.46 GB|Not recommended for most people. Low quality.|
14
+ |[Q3_K_L](https://huggingface.co/Alcoft/HuggingFaceTB_SmolLM3-3B-GGUF/resolve/main/output/HuggingFaceTB_SmolLM3-3B-GGUF/HuggingFaceTB_SmolLM3-3B_Q3_K_L.gguf)|1.57 GB|Not recommended for most people. Low quality.|
15
+ |[Q3_K_XL](https://huggingface.co/Alcoft/HuggingFaceTB_SmolLM3-3B-GGUF/resolve/main/output/HuggingFaceTB_SmolLM3-3B-GGUF/HuggingFaceTB_SmolLM3-3B_Q3_K_XL.gguf)|1.63 GB|Not recommended for most people. Uses Q8_0 for output and embedding, and Q3_K_L for everything else. Low quality.|
16
+ |[Q3_K_XXL](https://huggingface.co/Alcoft/HuggingFaceTB_SmolLM3-3B-GGUF/resolve/main/output/HuggingFaceTB_SmolLM3-3B-GGUF/HuggingFaceTB_SmolLM3-3B_Q3_K_XXL.gguf)|1.86 GB|Not recommended for most people. Uses F16 for output and embedding, and Q3_K_L for everything else. Low quality.|
17
+ |[Q4_K_S](https://huggingface.co/Alcoft/HuggingFaceTB_SmolLM3-3B-GGUF/resolve/main/output/HuggingFaceTB_SmolLM3-3B-GGUF/HuggingFaceTB_SmolLM3-3B_Q4_K_S.gguf)|1.69 GB|Recommended. Slightly low quality.|
18
+ |[Q4_K_M](https://huggingface.co/Alcoft/HuggingFaceTB_SmolLM3-3B-GGUF/resolve/main/output/HuggingFaceTB_SmolLM3-3B-GGUF/HuggingFaceTB_SmolLM3-3B_Q4_K_M.gguf)|1.78 GB|Recommended. Decent quality for most use cases.|
19
+ |[Q4_K_L](https://huggingface.co/Alcoft/HuggingFaceTB_SmolLM3-3B-GGUF/resolve/main/output/HuggingFaceTB_SmolLM3-3B-GGUF/HuggingFaceTB_SmolLM3-3B_Q4_K_L.gguf)|1.84 GB|Recommended. Uses Q8_0 for output and embedding, and Q4_K_M for everything else. Decent quality.|
20
+ |[Q4_K_XL](https://huggingface.co/Alcoft/HuggingFaceTB_SmolLM3-3B-GGUF/resolve/main/output/HuggingFaceTB_SmolLM3-3B-GGUF/HuggingFaceTB_SmolLM3-3B_Q4_K_XL.gguf)|2.07 GB|Recommended. Uses F16 for output and embedding, and Q4_K_M for everything else. Decent quality.|
21
+ |[Q5_K_S](https://huggingface.co/Alcoft/HuggingFaceTB_SmolLM3-3B-GGUF/resolve/main/output/HuggingFaceTB_SmolLM3-3B-GGUF/HuggingFaceTB_SmolLM3-3B_Q5_K_S.gguf)|2.01 GB|Recommended. High quality.|
22
+ |[Q5_K_M](https://huggingface.co/Alcoft/HuggingFaceTB_SmolLM3-3B-GGUF/resolve/main/output/HuggingFaceTB_SmolLM3-3B-GGUF/HuggingFaceTB_SmolLM3-3B_Q5_K_M.gguf)|2.06 GB|Recommended. High quality.|
23
+ |[Q5_K_L](https://huggingface.co/Alcoft/HuggingFaceTB_SmolLM3-3B-GGUF/resolve/main/output/HuggingFaceTB_SmolLM3-3B-GGUF/HuggingFaceTB_SmolLM3-3B_Q5_K_L.gguf)|2.12 GB|Recommended. Uses Q8_0 for output and embedding, and Q5_K_M for everything else. High quality.|
24
+ |[Q5_K_XL](https://huggingface.co/Alcoft/HuggingFaceTB_SmolLM3-3B-GGUF/resolve/main/output/HuggingFaceTB_SmolLM3-3B-GGUF/HuggingFaceTB_SmolLM3-3B_Q5_K_XL.gguf)|2.35 GB|Recommended. Uses F16 for output and embedding, and Q5_K_M for everything else. High quality.|
25
+ |[Q6_K](https://huggingface.co/Alcoft/HuggingFaceTB_SmolLM3-3B-GGUF/resolve/main/output/HuggingFaceTB_SmolLM3-3B-GGUF/HuggingFaceTB_SmolLM3-3B_Q6_K.gguf)|2.36 GB|Recommended. Very high quality.|
26
+ |[Q6_K_L](https://huggingface.co/Alcoft/HuggingFaceTB_SmolLM3-3B-GGUF/resolve/main/output/HuggingFaceTB_SmolLM3-3B-GGUF/HuggingFaceTB_SmolLM3-3B_Q6_K_L.gguf)|2.42 GB|Recommended. Uses Q8_0 for output and embedding, and Q6_K for everything else. Very high quality.|
27
+ |[Q6_K_XL](https://huggingface.co/Alcoft/HuggingFaceTB_SmolLM3-3B-GGUF/resolve/main/output/HuggingFaceTB_SmolLM3-3B-GGUF/HuggingFaceTB_SmolLM3-3B_Q6_K_XL.gguf)|2.65 GB|Recommended. Uses F16 for output and embedding, and Q6_K for everything else. Very high quality.|
28
+ |[Q8_0](https://huggingface.co/Alcoft/HuggingFaceTB_SmolLM3-3B-GGUF/resolve/main/output/HuggingFaceTB_SmolLM3-3B-GGUF/HuggingFaceTB_SmolLM3-3B_Q8_0.gguf)|3.05 GB|Recommended. Quality almost like F16.|
29
+ |[F16](https://huggingface.co/Alcoft/HuggingFaceTB_SmolLM3-3B-GGUF/resolve/main/output/HuggingFaceTB_SmolLM3-3B-GGUF/HuggingFaceTB_SmolLM3-3B_F16.gguf)|5.74 GB|Not recommended. Overkill. Prefer Q8_0.|
30
+ |[ORIGINAL (BF16)](https://huggingface.co/Alcoft/HuggingFaceTB_SmolLM3-3B-GGUF/resolve/main/HuggingFaceTB_SmolLM3-3B.gguf)|5.74 GB|Not recommended. Overkill. Prefer Q8_0.|
31
+
32
+ ---
33
+
34
+ Quantized using [TAO71-AI AutoQuantizer](https://github.com/TAO71-AI/AutoQuantizer).
35
+ You can check out the original model template [here](https://huggingface.co/HuggingFaceTB/SmolLM3-3B).