Hugging Face's logo

bartowski
/
Meta-Llama-3-120B-Instruct-GGUF

Text Generation
GGUF
Merge
mergekit
lazymergekit
imatrix
conversational
Model card Files
xet
 Community
bartowski commited on
Commit
78d2668
·
verified ·
1 Parent(s): 3a198f8

Llamacpp quants

Browse files
Files changed (25) hide show
  1. .gitattributes +23 -0
  2. Meta-Llama-3-120B-Instruct-Q5_K_M.gguf/Meta-Llama-3-120B-Instruct-Q5_K_M-00001-of-00003.gguf +3 -0
  3. Meta-Llama-3-120B-Instruct-Q5_K_M.gguf/Meta-Llama-3-120B-Instruct-Q5_K_M-00002-of-00003.gguf +3 -0
  4. Meta-Llama-3-120B-Instruct-Q5_K_M.gguf/Meta-Llama-3-120B-Instruct-Q5_K_M-00003-of-00003.gguf +3 -0
  5. Meta-Llama-3-120B-Instruct-Q5_K_S.gguf/Meta-Llama-3-120B-Instruct-Q5_K_S-00001-of-00003.gguf +3 -0
  6. Meta-Llama-3-120B-Instruct-Q5_K_S.gguf/Meta-Llama-3-120B-Instruct-Q5_K_S-00002-of-00003.gguf +3 -0
  7. Meta-Llama-3-120B-Instruct-Q5_K_S.gguf/Meta-Llama-3-120B-Instruct-Q5_K_S-00003-of-00003.gguf +3 -0
  8. Meta-Llama-3-120B-Instruct-Q6_K.gguf/Meta-Llama-3-120B-Instruct-Q6_K-00001-of-00004.gguf +3 -0
  9. Meta-Llama-3-120B-Instruct-Q6_K.gguf/Meta-Llama-3-120B-Instruct-Q6_K-00002-of-00004.gguf +3 -0
  10. Meta-Llama-3-120B-Instruct-Q6_K.gguf/Meta-Llama-3-120B-Instruct-Q6_K-00003-of-00004.gguf +3 -0
  11. Meta-Llama-3-120B-Instruct-Q6_K.gguf/Meta-Llama-3-120B-Instruct-Q6_K-00004-of-00004.gguf +3 -0
  12. Meta-Llama-3-120B-Instruct-Q8_0.gguf/Meta-Llama-3-120B-Instruct-Q8_0-00001-of-00005.gguf +3 -0
  13. Meta-Llama-3-120B-Instruct-Q8_0.gguf/Meta-Llama-3-120B-Instruct-Q8_0-00002-of-00005.gguf +3 -0
  14. Meta-Llama-3-120B-Instruct-Q8_0.gguf/Meta-Llama-3-120B-Instruct-Q8_0-00003-of-00005.gguf +3 -0
  15. Meta-Llama-3-120B-Instruct-Q8_0.gguf/Meta-Llama-3-120B-Instruct-Q8_0-00004-of-00005.gguf +3 -0
  16. Meta-Llama-3-120B-Instruct-Q8_0.gguf/Meta-Llama-3-120B-Instruct-Q8_0-00005-of-00005.gguf +3 -0
  17. Meta-Llama-3-120B-Instruct-fp16.gguf/Meta-Llama-3-120B-Instruct-fp16-00001-of-00008.gguf +3 -0
  18. Meta-Llama-3-120B-Instruct-fp16.gguf/Meta-Llama-3-120B-Instruct-fp16-00002-of-00008.gguf +3 -0
  19. Meta-Llama-3-120B-Instruct-fp16.gguf/Meta-Llama-3-120B-Instruct-fp16-00003-of-00008.gguf +3 -0
  20. Meta-Llama-3-120B-Instruct-fp16.gguf/Meta-Llama-3-120B-Instruct-fp16-00004-of-00008.gguf +3 -0
  21. Meta-Llama-3-120B-Instruct-fp16.gguf/Meta-Llama-3-120B-Instruct-fp16-00005-of-00008.gguf +3 -0
  22. Meta-Llama-3-120B-Instruct-fp16.gguf/Meta-Llama-3-120B-Instruct-fp16-00006-of-00008.gguf +3 -0
  23. Meta-Llama-3-120B-Instruct-fp16.gguf/Meta-Llama-3-120B-Instruct-fp16-00007-of-00008.gguf +3 -0
  24. Meta-Llama-3-120B-Instruct-fp16.gguf/Meta-Llama-3-120B-Instruct-fp16-00008-of-00008.gguf +3 -0
  25. README.md +22 -18
.gitattributes CHANGED
@@ -66,3 +66,26 @@ Meta-Llama-3-120B-Instruct-Q4_K_S.gguf/Meta-Llama-3-120B-Instruct-Q4_K_S-00001-o
66
  Meta-Llama-3-120B-Instruct-Q4_K_S.gguf/Meta-Llama-3-120B-Instruct-Q4_K_S-00002-of-00003.gguf filter=lfs diff=lfs merge=lfs -text
67
  Meta-Llama-3-120B-Instruct-Q4_K_S.gguf/Meta-Llama-3-120B-Instruct-Q4_K_S-00003-of-00003.gguf filter=lfs diff=lfs merge=lfs -text
68
  Meta-Llama-3-120B-Instruct.imatrix filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
66
  Meta-Llama-3-120B-Instruct-Q4_K_S.gguf/Meta-Llama-3-120B-Instruct-Q4_K_S-00002-of-00003.gguf filter=lfs diff=lfs merge=lfs -text
67
  Meta-Llama-3-120B-Instruct-Q4_K_S.gguf/Meta-Llama-3-120B-Instruct-Q4_K_S-00003-of-00003.gguf filter=lfs diff=lfs merge=lfs -text
68
  Meta-Llama-3-120B-Instruct.imatrix filter=lfs diff=lfs merge=lfs -text
69
+ Meta-Llama-3-120B-Instruct-Q5_K_M.gguf/Meta-Llama-3-120B-Instruct-Q5_K_M-00001-of-00003.gguf filter=lfs diff=lfs merge=lfs -text
70
+ Meta-Llama-3-120B-Instruct-Q5_K_M.gguf/Meta-Llama-3-120B-Instruct-Q5_K_M-00002-of-00003.gguf filter=lfs diff=lfs merge=lfs -text
71
+ Meta-Llama-3-120B-Instruct-Q5_K_M.gguf/Meta-Llama-3-120B-Instruct-Q5_K_M-00003-of-00003.gguf filter=lfs diff=lfs merge=lfs -text
72
+ Meta-Llama-3-120B-Instruct-Q5_K_S.gguf/Meta-Llama-3-120B-Instruct-Q5_K_S-00001-of-00003.gguf filter=lfs diff=lfs merge=lfs -text
73
+ Meta-Llama-3-120B-Instruct-Q5_K_S.gguf/Meta-Llama-3-120B-Instruct-Q5_K_S-00002-of-00003.gguf filter=lfs diff=lfs merge=lfs -text
74
+ Meta-Llama-3-120B-Instruct-Q5_K_S.gguf/Meta-Llama-3-120B-Instruct-Q5_K_S-00003-of-00003.gguf filter=lfs diff=lfs merge=lfs -text
75
+ Meta-Llama-3-120B-Instruct-Q6_K.gguf/Meta-Llama-3-120B-Instruct-Q6_K-00001-of-00004.gguf filter=lfs diff=lfs merge=lfs -text
76
+ Meta-Llama-3-120B-Instruct-Q6_K.gguf/Meta-Llama-3-120B-Instruct-Q6_K-00002-of-00004.gguf filter=lfs diff=lfs merge=lfs -text
77
+ Meta-Llama-3-120B-Instruct-Q6_K.gguf/Meta-Llama-3-120B-Instruct-Q6_K-00003-of-00004.gguf filter=lfs diff=lfs merge=lfs -text
78
+ Meta-Llama-3-120B-Instruct-Q6_K.gguf/Meta-Llama-3-120B-Instruct-Q6_K-00004-of-00004.gguf filter=lfs diff=lfs merge=lfs -text
79
+ Meta-Llama-3-120B-Instruct-Q8_0.gguf/Meta-Llama-3-120B-Instruct-Q8_0-00001-of-00005.gguf filter=lfs diff=lfs merge=lfs -text
80
+ Meta-Llama-3-120B-Instruct-Q8_0.gguf/Meta-Llama-3-120B-Instruct-Q8_0-00002-of-00005.gguf filter=lfs diff=lfs merge=lfs -text
81
+ Meta-Llama-3-120B-Instruct-Q8_0.gguf/Meta-Llama-3-120B-Instruct-Q8_0-00003-of-00005.gguf filter=lfs diff=lfs merge=lfs -text
82
+ Meta-Llama-3-120B-Instruct-Q8_0.gguf/Meta-Llama-3-120B-Instruct-Q8_0-00004-of-00005.gguf filter=lfs diff=lfs merge=lfs -text
83
+ Meta-Llama-3-120B-Instruct-Q8_0.gguf/Meta-Llama-3-120B-Instruct-Q8_0-00005-of-00005.gguf filter=lfs diff=lfs merge=lfs -text
84
+ Meta-Llama-3-120B-Instruct-fp16.gguf/Meta-Llama-3-120B-Instruct-fp16-00001-of-00008.gguf filter=lfs diff=lfs merge=lfs -text
85
+ Meta-Llama-3-120B-Instruct-fp16.gguf/Meta-Llama-3-120B-Instruct-fp16-00002-of-00008.gguf filter=lfs diff=lfs merge=lfs -text
86
+ Meta-Llama-3-120B-Instruct-fp16.gguf/Meta-Llama-3-120B-Instruct-fp16-00003-of-00008.gguf filter=lfs diff=lfs merge=lfs -text
87
+ Meta-Llama-3-120B-Instruct-fp16.gguf/Meta-Llama-3-120B-Instruct-fp16-00004-of-00008.gguf filter=lfs diff=lfs merge=lfs -text
88
+ Meta-Llama-3-120B-Instruct-fp16.gguf/Meta-Llama-3-120B-Instruct-fp16-00005-of-00008.gguf filter=lfs diff=lfs merge=lfs -text
89
+ Meta-Llama-3-120B-Instruct-fp16.gguf/Meta-Llama-3-120B-Instruct-fp16-00006-of-00008.gguf filter=lfs diff=lfs merge=lfs -text
90
+ Meta-Llama-3-120B-Instruct-fp16.gguf/Meta-Llama-3-120B-Instruct-fp16-00007-of-00008.gguf filter=lfs diff=lfs merge=lfs -text
91
+ Meta-Llama-3-120B-Instruct-fp16.gguf/Meta-Llama-3-120B-Instruct-fp16-00008-of-00008.gguf filter=lfs diff=lfs merge=lfs -text
Meta-Llama-3-120B-Instruct-Q5_K_M.gguf/Meta-Llama-3-120B-Instruct-Q5_K_M-00001-of-00003.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ed026d4a19c525202783d85677433727019c22c5e63a515762a6e9d138e4476
3
+ size 32130594784
Meta-Llama-3-120B-Instruct-Q5_K_M.gguf/Meta-Llama-3-120B-Instruct-Q5_K_M-00002-of-00003.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6618c93cd6aba0e6cd91bc6875343445ca07b4a69541503dd46510310809a1ad
3
+ size 32189215232
Meta-Llama-3-120B-Instruct-Q5_K_M.gguf/Meta-Llama-3-120B-Instruct-Q5_K_M-00003-of-00003.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc3d6ec8e43ddf9d2bec1040c60e44f30fec7f3f7fae47fd1b6e00c7f28ad04a
3
+ size 21898317312
Meta-Llama-3-120B-Instruct-Q5_K_S.gguf/Meta-Llama-3-120B-Instruct-Q5_K_S-00001-of-00003.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:744eff7cd0455f4c95bd8a76e242d64c192e19f60463e36b911ca559ab49b7d2
3
+ size 32080722848
Meta-Llama-3-120B-Instruct-Q5_K_S.gguf/Meta-Llama-3-120B-Instruct-Q5_K_S-00002-of-00003.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0ee788521fbd93b9547d8631403c01bd54957f710831303a1da16ee6510d44f
3
+ size 32144028512
Meta-Llama-3-120B-Instruct-Q5_K_S.gguf/Meta-Llama-3-120B-Instruct-Q5_K_S-00003-of-00003.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0fca3cf2a28b28929a252632f557db6cb4b3b75a0250b2910f437a13d4cffe4d
3
+ size 19731728608
Meta-Llama-3-120B-Instruct-Q6_K.gguf/Meta-Llama-3-120B-Instruct-Q6_K-00001-of-00004.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7581d6eb0ac1a87cf4f61ee5b17e4960c04883319fdba32d8e24fd87104f459
3
+ size 32184117664
Meta-Llama-3-120B-Instruct-Q6_K.gguf/Meta-Llama-3-120B-Instruct-Q6_K-00002-of-00004.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2787d0289b912bc6449e984da6823187191985392451584a33ae11261242bef1
3
+ size 32097329376
Meta-Llama-3-120B-Instruct-Q6_K.gguf/Meta-Llama-3-120B-Instruct-Q6_K-00003-of-00004.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81353035ecd5dde9a67f6ef4fe6d6dedc429fce81832b8f16245a1609c52eb43
3
+ size 32207397472
Meta-Llama-3-120B-Instruct-Q6_K.gguf/Meta-Llama-3-120B-Instruct-Q6_K-00004-of-00004.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e0a58c04a46bb3efb386864db8e7c692c11ca05b7c66f011f3ef60cc7edbed1
3
+ size 3516697472
Meta-Llama-3-120B-Instruct-Q8_0.gguf/Meta-Llama-3-120B-Instruct-Q8_0-00001-of-00005.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50337b149ed36d3fe720ad6bb9e7850686f1e63f036426d67caa67b9d30b5ea5
3
+ size 32083055552
Meta-Llama-3-120B-Instruct-Q8_0.gguf/Meta-Llama-3-120B-Instruct-Q8_0-00002-of-00005.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e2fbfc06e4e09881fdb8acb0858d459e5c0c951f98742a958014b0dda418f49
3
+ size 32079858336
Meta-Llama-3-120B-Instruct-Q8_0.gguf/Meta-Llama-3-120B-Instruct-Q8_0-00003-of-00005.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0f96b851f48b7a0a166251c5467beb1b724018a8ec62429d9fe880351cc2431
3
+ size 32142215904
Meta-Llama-3-120B-Instruct-Q8_0.gguf/Meta-Llama-3-120B-Instruct-Q8_0-00004-of-00005.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef379c3567406f9aad9e7cd682af217189da571ffb8ed8e77e55beff4a68558e
3
+ size 32160074784
Meta-Llama-3-120B-Instruct-Q8_0.gguf/Meta-Llama-3-120B-Instruct-Q8_0-00005-of-00005.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:295224fd04b40698ff1b9d67462ac2f745fbeab21e680d58d5be381c0815b4a7
3
+ size 1060733824
Meta-Llama-3-120B-Instruct-fp16.gguf/Meta-Llama-3-120B-Instruct-fp16-00001-of-00008.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb123c047ffa144bd6da6a2b043309114b1eeef57410466d2949756c387103bb
3
+ size 31759757056
Meta-Llama-3-120B-Instruct-fp16.gguf/Meta-Llama-3-120B-Instruct-fp16-00002-of-00008.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:085cf4d4c4952666b76327863745a03691a4d266a9785ad66c7482245da261f5
3
+ size 32045738016
Meta-Llama-3-120B-Instruct-fp16.gguf/Meta-Llama-3-120B-Instruct-fp16-00003-of-00008.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e90680970e50d982af3bd4dc8ad25eeb23bb08bb76ef8a35df0355b0038e6fdf
3
+ size 32045738016
Meta-Llama-3-120B-Instruct-fp16.gguf/Meta-Llama-3-120B-Instruct-fp16-00004-of-00008.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08af60e214f90eeb94ea0d5addfcf98693c4773e6a3ca0b4dfae6145af33804a
3
+ size 31743682240
Meta-Llama-3-120B-Instruct-fp16.gguf/Meta-Llama-3-120B-Instruct-fp16-00005-of-00008.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b861bd89f9271b3c8b556ed70c946f2c2413dfb852e23e5f83fba2fc52957515
3
+ size 32062548128
Meta-Llama-3-120B-Instruct-fp16.gguf/Meta-Llama-3-120B-Instruct-fp16-00006-of-00008.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47aa397a827c8b68ac502fa62968e4f6a8d6cb6f971e7ec2d8319c1b615ad2e8
3
+ size 31877900128
Meta-Llama-3-120B-Instruct-fp16.gguf/Meta-Llama-3-120B-Instruct-fp16-00007-of-00008.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:afbbacd7be0fb72cb531d283cc5f2cfc3b5ad099499cda4ae25f301dc2a9dd65
3
+ size 32196733248
Meta-Llama-3-120B-Instruct-fp16.gguf/Meta-Llama-3-120B-Instruct-fp16-00008-of-00008.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8dda673375963000684d1527b33e1ffe1e858fc3c676de39b43e8203ba740fdf
3
+ size 20066343328
README.md CHANGED
@@ -40,24 +40,28 @@ All quants made using imatrix option with dataset provided by Kalomaze [here](ht
40
 
41
  | Filename | Quant type | File Size | Description |
42
  | -------- | ---------- | --------- | ----------- |
43
- | [Meta-Llama-3-120B-Instruct-Q4_K_M.gguf](https://huggingface.co/bartowski/Meta-Llama-3-120B-Instruct-GGUF/tree/main/Meta-Llama-3-120B-Instruct-Q4_K_M.gguf) | Q4_K_M | 73.24GB | Good quality, uses about 4.83 bits per weight, *recommended*. |
44
- | [Meta-Llama-3-120B-Instruct-Q4_K_S.gguf](https://huggingface.co/bartowski/Meta-Llama-3-120B-Instruct-GGUF/tree/main/Meta-Llama-3-120B-Instruct-Q4_K_S.gguf) | Q4_K_S | 69.35GB | Slightly lower quality with more space savings, *recommended*. |
45
- | [Meta-Llama-3-120B-Instruct-IQ4_NL.gguf](https://huggingface.co/bartowski/Meta-Llama-3-120B-Instruct-GGUF/tree/main/Meta-Llama-3-120B-Instruct-IQ4_NL.gguf) | IQ4_NL | 68.99GB | Decent quality, slightly smaller than Q4_K_S with similar performance *recommended*. |
46
- | [Meta-Llama-3-120B-Instruct-IQ4_XS.gguf](https://huggingface.co/bartowski/Meta-Llama-3-120B-Instruct-GGUF/tree/main/Meta-Llama-3-120B-Instruct-IQ4_XS.gguf) | IQ4_XS | 65.25GB | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
47
- | [Meta-Llama-3-120B-Instruct-Q3_K_L.gguf](https://huggingface.co/bartowski/Meta-Llama-3-120B-Instruct-GGUF/tree/main/Meta-Llama-3-120B-Instruct-Q3_K_L.gguf) | Q3_K_L | 64.00GB | Lower quality but usable, good for low RAM availability. |
48
- | [Meta-Llama-3-120B-Instruct-Q3_K_M.gguf](https://huggingface.co/bartowski/Meta-Llama-3-120B-Instruct-GGUF/tree/main/Meta-Llama-3-120B-Instruct-Q3_K_M.gguf) | Q3_K_M | 58.81GB | Even lower quality. |
49
- | [Meta-Llama-3-120B-Instruct-IQ3_M.gguf](https://huggingface.co/bartowski/Meta-Llama-3-120B-Instruct-GGUF/tree/main/Meta-Llama-3-120B-Instruct-IQ3_M.gguf) | IQ3_M | 54.73GB | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
50
- | [Meta-Llama-3-120B-Instruct-IQ3_S.gguf](https://huggingface.co/bartowski/Meta-Llama-3-120B-Instruct-GGUF/tree/main/Meta-Llama-3-120B-Instruct-IQ3_S.gguf) | IQ3_S | 52.95GB | Lower quality, new method with decent performance, recommended over Q3_K_S quant, same size with better performance. |
51
- | [Meta-Llama-3-120B-Instruct-Q3_K_S.gguf](https://huggingface.co/bartowski/Meta-Llama-3-120B-Instruct-GGUF/tree/main/Meta-Llama-3-120B-Instruct-Q3_K_S.gguf) | Q3_K_S | 52.80GB | Low quality, not recommended. |
52
- | [Meta-Llama-3-120B-Instruct-IQ3_XS.gguf](https://huggingface.co/bartowski/Meta-Llama-3-120B-Instruct-GGUF/tree/main/Meta-Llama-3-120B-Instruct-IQ3_XS.gguf) | IQ3_XS | 50.15GB | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
53
- | [Meta-Llama-3-120B-Instruct-IQ3_XXS.gguf](https://huggingface.co/bartowski/Meta-Llama-3-120B-Instruct-GGUF/blob/main/Meta-Llama-3-120B-Instruct-IQ3_XXS.gguf) | IQ3_XXS | 47.03GB | Lower quality, new method with decent performance, comparable to Q3 quants. |
54
- | [Meta-Llama-3-120B-Instruct-Q2_K.gguf](https://huggingface.co/bartowski/Meta-Llama-3-120B-Instruct-GGUF/blob/main/Meta-Llama-3-120B-Instruct-Q2_K.gguf) | Q2_K | 45.09GB | Very low quality but surprisingly usable. |
55
- | [Meta-Llama-3-120B-Instruct-IQ2_M.gguf](https://huggingface.co/bartowski/Meta-Llama-3-120B-Instruct-GGUF/blob/main/Meta-Llama-3-120B-Instruct-IQ2_M.gguf) | IQ2_M | 41.30GB | Very low quality, uses SOTA techniques to also be surprisingly usable. |
56
- | [Meta-Llama-3-120B-Instruct-IQ2_S.gguf](https://huggingface.co/bartowski/Meta-Llama-3-120B-Instruct-GGUF/blob/main/Meta-Llama-3-120B-Instruct-IQ2_S.gguf) | IQ2_S | 38.02GB | Very low quality, uses SOTA techniques to be usable. |
57
- | [Meta-Llama-3-120B-Instruct-IQ2_XS.gguf](https://huggingface.co/bartowski/Meta-Llama-3-120B-Instruct-GGUF/blob/main/Meta-Llama-3-120B-Instruct-IQ2_XS.gguf) | IQ2_XS | 36.18GB | Very low quality, uses SOTA techniques to be usable. |
58
- | [Meta-Llama-3-120B-Instruct-IQ2_XXS.gguf](https://huggingface.co/bartowski/Meta-Llama-3-120B-Instruct-GGUF/blob/main/Meta-Llama-3-120B-Instruct-IQ2_XXS.gguf) | IQ2_XXS | 32.60GB | Lower quality, uses SOTA techniques to be usable. |
59
- | [Meta-Llama-3-120B-Instruct-IQ1_M.gguf](https://huggingface.co/bartowski/Meta-Llama-3-120B-Instruct-GGUF/blob/main/Meta-Llama-3-120B-Instruct-IQ1_M.gguf) | IQ1_M | 28.49GB | Extremely low quality, *not* recommended. |
60
- | [Meta-Llama-3-120B-Instruct-IQ1_S.gguf](https://huggingface.co/bartowski/Meta-Llama-3-120B-Instruct-GGUF/blob/main/Meta-Llama-3-120B-Instruct-IQ1_S.gguf) | IQ1_S | 26.02GB | Extremely low quality, *not* recommended. |
 
 
 
 
61
 
62
  ## Downloading using huggingface-cli
63
 
 
40
 
41
  | Filename | Quant type | File Size | Description |
42
  | -------- | ---------- | --------- | ----------- |
43
+ | [Meta-Llama-3-120B-Instruct-Q8_0.gguf](https://huggingface.co/bartowski/Meta-Llama-3-120B-Instruct-GGUF/tree/main/Meta-Llama-3-120B-Instruct-Q8_0.gguf) | Q8_0 | 129.52GB | Extremely high quality, generally unneeded but max available quant. |
44
+ | [Meta-Llama-3-120B-Instruct-Q6_K.gguf](https://huggingface.co/bartowski/Meta-Llama-3-120B-Instruct-GGUF/tree/main/Meta-Llama-3-120B-Instruct-Q6_K.gguf) | Q6_K | 100.00GB | Very high quality, near perfect, *recommended*. |
45
+ | [Meta-Llama-3-120B-Instruct-Q5_K_M.gguf](https://huggingface.co/bartowski/Meta-Llama-3-120B-Instruct-GGUF/tree/main/Meta-Llama-3-120B-Instruct-Q5_K_M.gguf) | Q5_K_M | 86.21GB | High quality, *recommended*. |
46
+ | [Meta-Llama-3-120B-Instruct-Q5_K_S.gguf](https://huggingface.co/bartowski/Meta-Llama-3-120B-Instruct-GGUF/tree/main/Meta-Llama-3-120B-Instruct-Q5_K_S.gguf) | Q5_K_S | 83.95GB | High quality, *recommended*. |
47
+ | [Meta-Llama-3-120B-Instruct-Q4_K_M.gguf](https://huggingface.co/bartowski/Meta-Llama-3-120B-Instruct-GGUF//main/Meta-Llama-3-120B-Instruct-Q4_K_M.gguf) | Q4_K_M | | Good quality, uses about 4.83 bits per weight, *recommended*. |
48
+ | [Meta-Llama-3-120B-Instruct-Q4_K_S.gguf](https://huggingface.co/bartowski/Meta-Llama-3-120B-Instruct-GGUF//main/Meta-Llama-3-120B-Instruct-Q4_K_S.gguf) | Q4_K_S | | Slightly lower quality with more space savings, *recommended*. |
49
+ | [Meta-Llama-3-120B-Instruct-IQ4_NL.gguf](https://huggingface.co/bartowski/Meta-Llama-3-120B-Instruct-GGUF//main/Meta-Llama-3-120B-Instruct-IQ4_NL.gguf) | IQ4_NL | | Decent quality, slightly smaller than Q4_K_S with similar performance *recommended*. |
50
+ | [Meta-Llama-3-120B-Instruct-IQ4_XS.gguf](https://huggingface.co/bartowski/Meta-Llama-3-120B-Instruct-GGUF//main/Meta-Llama-3-120B-Instruct-IQ4_XS.gguf) | IQ4_XS | | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
51
+ | [Meta-Llama-3-120B-Instruct-Q3_K_L.gguf](https://huggingface.co/bartowski/Meta-Llama-3-120B-Instruct-GGUF//main/Meta-Llama-3-120B-Instruct-Q3_K_L.gguf) | Q3_K_L | | Lower quality but usable, good for low RAM availability. |
52
+ | [Meta-Llama-3-120B-Instruct-Q3_K_M.gguf](https://huggingface.co/bartowski/Meta-Llama-3-120B-Instruct-GGUF//main/Meta-Llama-3-120B-Instruct-Q3_K_M.gguf) | Q3_K_M | | Even lower quality. |
53
+ | [Meta-Llama-3-120B-Instruct-IQ3_M.gguf](https://huggingface.co/bartowski/Meta-Llama-3-120B-Instruct-GGUF//main/Meta-Llama-3-120B-Instruct-IQ3_M.gguf) | IQ3_M | | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
54
+ | [Meta-Llama-3-120B-Instruct-IQ3_S.gguf](https://huggingface.co/bartowski/Meta-Llama-3-120B-Instruct-GGUF//main/Meta-Llama-3-120B-Instruct-IQ3_S.gguf) | IQ3_S | | Lower quality, new method with decent performance, recommended over Q3_K_S quant, same size with better performance. |
55
+ | [Meta-Llama-3-120B-Instruct-Q3_K_S.gguf](https://huggingface.co/bartowski/Meta-Llama-3-120B-Instruct-GGUF//main/Meta-Llama-3-120B-Instruct-Q3_K_S.gguf) | Q3_K_S | | Low quality, not recommended. |
56
+ | [Meta-Llama-3-120B-Instruct-IQ3_XS.gguf](https://huggingface.co/bartowski/Meta-Llama-3-120B-Instruct-GGUF//main/Meta-Llama-3-120B-Instruct-IQ3_XS.gguf) | IQ3_XS | | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
57
+ | [Meta-Llama-3-120B-Instruct-IQ3_XXS.gguf](https://huggingface.co/bartowski/Meta-Llama-3-120B-Instruct-GGUF//main/Meta-Llama-3-120B-Instruct-IQ3_XXS.gguf) | IQ3_XXS | | Lower quality, new method with decent performance, comparable to Q3 quants. |
58
+ | [Meta-Llama-3-120B-Instruct-Q2_K.gguf](https://huggingface.co/bartowski/Meta-Llama-3-120B-Instruct-GGUF//main/Meta-Llama-3-120B-Instruct-Q2_K.gguf) | Q2_K | | Very low quality but surprisingly usable. |
59
+ | [Meta-Llama-3-120B-Instruct-IQ2_M.gguf](https://huggingface.co/bartowski/Meta-Llama-3-120B-Instruct-GGUF//main/Meta-Llama-3-120B-Instruct-IQ2_M.gguf) | IQ2_M | | Very low quality, uses SOTA techniques to also be surprisingly usable. |
60
+ | [Meta-Llama-3-120B-Instruct-IQ2_S.gguf](https://huggingface.co/bartowski/Meta-Llama-3-120B-Instruct-GGUF//main/Meta-Llama-3-120B-Instruct-IQ2_S.gguf) | IQ2_S | | Very low quality, uses SOTA techniques to be usable. |
61
+ | [Meta-Llama-3-120B-Instruct-IQ2_XS.gguf](https://huggingface.co/bartowski/Meta-Llama-3-120B-Instruct-GGUF//main/Meta-Llama-3-120B-Instruct-IQ2_XS.gguf) | IQ2_XS | | Very low quality, uses SOTA techniques to be usable. |
62
+ | [Meta-Llama-3-120B-Instruct-IQ2_XXS.gguf](https://huggingface.co/bartowski/Meta-Llama-3-120B-Instruct-GGUF//main/Meta-Llama-3-120B-Instruct-IQ2_XXS.gguf) | IQ2_XXS | | Lower quality, uses SOTA techniques to be usable. |
63
+ | [Meta-Llama-3-120B-Instruct-IQ1_M.gguf](https://huggingface.co/bartowski/Meta-Llama-3-120B-Instruct-GGUF//main/Meta-Llama-3-120B-Instruct-IQ1_M.gguf) | IQ1_M | | Extremely low quality, *not* recommended. |
64
+ | [Meta-Llama-3-120B-Instruct-IQ1_S.gguf](https://huggingface.co/bartowski/Meta-Llama-3-120B-Instruct-GGUF//main/Meta-Llama-3-120B-Instruct-IQ1_S.gguf) | IQ1_S | | Extremely low quality, *not* recommended. |
65
 
66
  ## Downloading using huggingface-cli
67