Hugging Face's logo

EasierAI
/
Mistral-NeMo-12B

Text Generation
GGUF
imatrix
conversational
Model card Files
xet
 Community
drkameleon bartowski commited on
Commit
30e0260
·
verified ·
0 Parent(s):

Duplicate from bartowski/Mistral-Nemo-Instruct-2407-GGUF

Browse files

Co-authored-by: Bartowski <bartowski@users.noreply.huggingface.co>

Files changed (28) hide show
  1. .gitattributes +61 -0
  2. Mistral-Nemo-Instruct-2407-IQ2_M.gguf +3 -0
  3. Mistral-Nemo-Instruct-2407-IQ3_M.gguf +3 -0
  4. Mistral-Nemo-Instruct-2407-IQ3_XS.gguf +3 -0
  5. Mistral-Nemo-Instruct-2407-IQ4_XS.gguf +3 -0
  6. Mistral-Nemo-Instruct-2407-Q2_K.gguf +3 -0
  7. Mistral-Nemo-Instruct-2407-Q2_K_L.gguf +3 -0
  8. Mistral-Nemo-Instruct-2407-Q3_K_L.gguf +3 -0
  9. Mistral-Nemo-Instruct-2407-Q3_K_M.gguf +3 -0
  10. Mistral-Nemo-Instruct-2407-Q3_K_S.gguf +3 -0
  11. Mistral-Nemo-Instruct-2407-Q3_K_XL.gguf +3 -0
  12. Mistral-Nemo-Instruct-2407-Q4_0.gguf +3 -0
  13. Mistral-Nemo-Instruct-2407-Q4_0_4_4.gguf +3 -0
  14. Mistral-Nemo-Instruct-2407-Q4_0_4_8.gguf +3 -0
  15. Mistral-Nemo-Instruct-2407-Q4_0_8_8.gguf +3 -0
  16. Mistral-Nemo-Instruct-2407-Q4_K_L.gguf +3 -0
  17. Mistral-Nemo-Instruct-2407-Q4_K_M.gguf +3 -0
  18. Mistral-Nemo-Instruct-2407-Q4_K_S.gguf +3 -0
  19. Mistral-Nemo-Instruct-2407-Q5_K_L.gguf +3 -0
  20. Mistral-Nemo-Instruct-2407-Q5_K_M.gguf +3 -0
  21. Mistral-Nemo-Instruct-2407-Q5_K_S.gguf +3 -0
  22. Mistral-Nemo-Instruct-2407-Q6_K.gguf +3 -0
  23. Mistral-Nemo-Instruct-2407-Q6_K_L.gguf +3 -0
  24. Mistral-Nemo-Instruct-2407-Q8_0.gguf +3 -0
  25. Mistral-Nemo-Instruct-2407-f16.gguf +3 -0
  26. Mistral-Nemo-Instruct-2407-f32.gguf +3 -0
  27. Mistral-Nemo-Instruct-2407.imatrix +3 -0
  28. README.md +137 -0
.gitattributes ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
+ *.model filter=lfs diff=lfs merge=lfs -text
13
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tar filter=lfs diff=lfs merge=lfs -text
29
+ *.tflite filter=lfs diff=lfs merge=lfs -text
30
+ *.tgz filter=lfs diff=lfs merge=lfs -text
31
+ *.wasm filter=lfs diff=lfs merge=lfs -text
32
+ *.xz 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
+ Mistral-Nemo-Instruct-2407-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
37
+ Mistral-Nemo-Instruct-2407-Q6_K_L.gguf filter=lfs diff=lfs merge=lfs -text
38
+ Mistral-Nemo-Instruct-2407-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
39
+ Mistral-Nemo-Instruct-2407-Q5_K_L.gguf filter=lfs diff=lfs merge=lfs -text
40
+ Mistral-Nemo-Instruct-2407-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
41
+ Mistral-Nemo-Instruct-2407-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
42
+ Mistral-Nemo-Instruct-2407-Q4_K_L.gguf filter=lfs diff=lfs merge=lfs -text
43
+ Mistral-Nemo-Instruct-2407-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
44
+ Mistral-Nemo-Instruct-2407-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
45
+ Mistral-Nemo-Instruct-2407-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
46
+ Mistral-Nemo-Instruct-2407-Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
47
+ Mistral-Nemo-Instruct-2407-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
48
+ Mistral-Nemo-Instruct-2407-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
49
+ Mistral-Nemo-Instruct-2407-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
50
+ Mistral-Nemo-Instruct-2407-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
51
+ Mistral-Nemo-Instruct-2407-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
52
+ Mistral-Nemo-Instruct-2407-Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text
53
+ Mistral-Nemo-Instruct-2407-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
54
+ Mistral-Nemo-Instruct-2407-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text
55
+ Mistral-Nemo-Instruct-2407-f32.gguf filter=lfs diff=lfs merge=lfs -text
56
+ Mistral-Nemo-Instruct-2407.imatrix filter=lfs diff=lfs merge=lfs -text
57
+ Mistral-Nemo-Instruct-2407-Q4_0_8_8.gguf filter=lfs diff=lfs merge=lfs -text
58
+ Mistral-Nemo-Instruct-2407-Q4_0_4_8.gguf filter=lfs diff=lfs merge=lfs -text
59
+ Mistral-Nemo-Instruct-2407-Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text
60
+ Mistral-Nemo-Instruct-2407-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
61
+ Mistral-Nemo-Instruct-2407-f16.gguf filter=lfs diff=lfs merge=lfs -text
Mistral-Nemo-Instruct-2407-IQ2_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72194914c723b1126f104d62b73c6da6adb4e47686bf2dfafa5def42dcbb41e9
3
+ size 4435027072
Mistral-Nemo-Instruct-2407-IQ3_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b695c69b285c17a602bb614b30c22e96100a9046681f4a773e231228ebc67a96
3
+ size 5722236032
Mistral-Nemo-Instruct-2407-IQ3_XS.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d68db0c60a66623392422b134eade128b77458581d9dc845f06a5c7b7144193a
3
+ size 5306492032
Mistral-Nemo-Instruct-2407-IQ4_XS.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4635276546fba351d9567641e55dc35ab9bce7fdc04a6f513ebb522326d3f41d
3
+ size 6742713472
Mistral-Nemo-Instruct-2407-Q2_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a1a7b2df7e21d6a3e41a1d99f7c2e69892adf061d99e6b9353e920cf3f5acbb
3
+ size 4791051392
Mistral-Nemo-Instruct-2407-Q2_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fafcdd92d1e5854b4564ab30c348ac9b227e7fad5a9516338f7f971ea2b93de2
3
+ size 5446411392
Mistral-Nemo-Instruct-2407-Q3_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9844586fc2809a6018bf6086753f655ce3528b38354d4b019eef5121938fd7c
3
+ size 6561506432
Mistral-Nemo-Instruct-2407-Q3_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42a78c7db9dc76c049c985eca8b3a0a7c218607e226e132168728a53f5104cc9
3
+ size 6083093632
Mistral-Nemo-Instruct-2407-Q3_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:feb33ad62929e746dd1ac857a76cad9ae8093e1a675c5edd17d3e7533840bbd4
3
+ size 5534229632
Mistral-Nemo-Instruct-2407-Q3_K_XL.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:768a20da7b0f99af2d5e09e0e63f667616a817d905012b78282b299289cd47d6
3
+ size 7148708992
Mistral-Nemo-Instruct-2407-Q4_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc7a72b30db1d9eac3ed7cab1f69d408621a01e12b4dc29a1c54639a74311017
3
+ size 7094641792
Mistral-Nemo-Instruct-2407-Q4_0_4_4.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:594f996e64ca85803a391e506dde49d0f3cba16aea15880c2851052ebb090223
3
+ size 7071704192
Mistral-Nemo-Instruct-2407-Q4_0_4_8.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:035bda8d0fdd52cdf991ff8d34f3515f51849044f76fcfdb4da98f90bfb9092d
3
+ size 7071704192
Mistral-Nemo-Instruct-2407-Q4_0_8_8.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d4ca1fa31e8cdff20eb130565b897430427e8002631aaaeb2d420331ee0a5b2
3
+ size 7071704192
Mistral-Nemo-Instruct-2407-Q4_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43e1d001f51830b2191d39c401fd266e1f0b875176069f8fd0cd6be4792dda5f
3
+ size 7975281792
Mistral-Nemo-Instruct-2407-Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c1a10d202d8788dbe5628dc962254d10654c853cae6aaeca0618f05490d4a46
3
+ size 7477208192
Mistral-Nemo-Instruct-2407-Q4_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:458c1775659eeb08647014ae91446c3646db098654e3054790f4ef3f354385c8
3
+ size 7120200832
Mistral-Nemo-Instruct-2407-Q5_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e0ccbeabb69988d93abc2e421589f6f8b10f56449c5e4fadc348a10eb652bd9
3
+ size 9141822592
Mistral-Nemo-Instruct-2407-Q5_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2118506b57d31403cba021b476ceb95600cc278fbc2feeaaf884b6e64fa6ee5
3
+ size 8727635072
Mistral-Nemo-Instruct-2407-Q5_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4637aba0d49de640521d5072c639e18238856f2a51ecb0cb3cbba086ffcf1f91
3
+ size 8518739072
Mistral-Nemo-Instruct-2407-Q6_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da9ac0c204363b96dcfdfdf9fedea0d6dd0a923dee0e22bf589994e118482482
3
+ size 10056213632
Mistral-Nemo-Instruct-2407-Q6_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54dfc2a56db2cd63f1dca3645a7fe67743c1ccc80e0d21753d2d2854058dc4e6
3
+ size 10381272192
Mistral-Nemo-Instruct-2407-Q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7985eab9b84d7d514253a53f372095d51f941f84a62cadaa0ccf6e1b3fbef494
3
+ size 13022372992
Mistral-Nemo-Instruct-2407-f16.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:816cde814bb83890089d08fbcf8e7268a622cd859e530fcee12442565cc7a964
3
+ size 24504279872
Mistral-Nemo-Instruct-2407-f32.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95cd4c88a408cf0b4ce9c6132ee43324f4462056f38ada8da606e7bf824d1e06
3
+ size 48999012032
Mistral-Nemo-Instruct-2407.imatrix ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4a024a3550a134fa76de0b4f55296f79f35719b00c71fbe1416f8c2df7328ef
3
+ size 7054418
README.md ADDED
@@ -0,0 +1,137 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: mistralai/Mistral-Nemo-Instruct-2407
3
+ language:
4
+ - en
5
+ - fr
6
+ - de
7
+ - es
8
+ - it
9
+ - pt
10
+ - ru
11
+ - zh
12
+ - ja
13
+ license: apache-2.0
14
+ pipeline_tag: text-generation
15
+ quantized_by: bartowski
16
+ extra_gated_description: If you want to learn more about how we process your personal
17
+ data, please read our <a href="https://mistral.ai/terms/">Privacy Policy</a>.
18
+ ---
19
+
20
+ ## Llamacpp imatrix Quantizations of Mistral-Nemo-Instruct-2407
21
+
22
+ Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b4014">b4014</a> for quantization.
23
+
24
+ Original model: https://huggingface.co/mistralai/Mistral-Nemo-Instruct-2407
25
+
26
+ All quants made using imatrix option with dataset from [here](https://gist.github.com/bartowski1182/eb213dccb3571f863da82e99418f81e8)
27
+
28
+ Run them in [LM Studio](https://lmstudio.ai/)
29
+
30
+ ## Prompt format
31
+
32
+ ```
33
+ <s>[INST]{prompt}[/INST]
34
+ ```
35
+
36
+ ## What's new:
37
+
38
+ Update chat template
39
+
40
+ ## Download a file (not the whole branch) from below:
41
+
42
+ | Filename | Quant type | File Size | Split | Description |
43
+ | -------- | ---------- | --------- | ----- | ----------- |
44
+ | [Mistral-Nemo-Instruct-2407-f16.gguf](https://huggingface.co/bartowski/Mistral-Nemo-Instruct-2407-GGUF/blob/main/Mistral-Nemo-Instruct-2407-f16.gguf) | f16 | 24.50GB | false | Full F16 weights. |
45
+ | [Mistral-Nemo-Instruct-2407-Q8_0.gguf](https://huggingface.co/bartowski/Mistral-Nemo-Instruct-2407-GGUF/blob/main/Mistral-Nemo-Instruct-2407-Q8_0.gguf) | Q8_0 | 13.02GB | false | Extremely high quality, generally unneeded but max available quant. |
46
+ | [Mistral-Nemo-Instruct-2407-Q6_K_L.gguf](https://huggingface.co/bartowski/Mistral-Nemo-Instruct-2407-GGUF/blob/main/Mistral-Nemo-Instruct-2407-Q6_K_L.gguf) | Q6_K_L | 10.38GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. |
47
+ | [Mistral-Nemo-Instruct-2407-Q6_K.gguf](https://huggingface.co/bartowski/Mistral-Nemo-Instruct-2407-GGUF/blob/main/Mistral-Nemo-Instruct-2407-Q6_K.gguf) | Q6_K | 10.06GB | false | Very high quality, near perfect, *recommended*. |
48
+ | [Mistral-Nemo-Instruct-2407-Q5_K_L.gguf](https://huggingface.co/bartowski/Mistral-Nemo-Instruct-2407-GGUF/blob/main/Mistral-Nemo-Instruct-2407-Q5_K_L.gguf) | Q5_K_L | 9.14GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. |
49
+ | [Mistral-Nemo-Instruct-2407-Q5_K_M.gguf](https://huggingface.co/bartowski/Mistral-Nemo-Instruct-2407-GGUF/blob/main/Mistral-Nemo-Instruct-2407-Q5_K_M.gguf) | Q5_K_M | 8.73GB | false | High quality, *recommended*. |
50
+ | [Mistral-Nemo-Instruct-2407-Q5_K_S.gguf](https://huggingface.co/bartowski/Mistral-Nemo-Instruct-2407-GGUF/blob/main/Mistral-Nemo-Instruct-2407-Q5_K_S.gguf) | Q5_K_S | 8.52GB | false | High quality, *recommended*. |
51
+ | [Mistral-Nemo-Instruct-2407-Q4_K_L.gguf](https://huggingface.co/bartowski/Mistral-Nemo-Instruct-2407-GGUF/blob/main/Mistral-Nemo-Instruct-2407-Q4_K_L.gguf) | Q4_K_L | 7.98GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. |
52
+ | [Mistral-Nemo-Instruct-2407-Q4_K_M.gguf](https://huggingface.co/bartowski/Mistral-Nemo-Instruct-2407-GGUF/blob/main/Mistral-Nemo-Instruct-2407-Q4_K_M.gguf) | Q4_K_M | 7.48GB | false | Good quality, default size for must use cases, *recommended*. |
53
+ | [Mistral-Nemo-Instruct-2407-Q3_K_XL.gguf](https://huggingface.co/bartowski/Mistral-Nemo-Instruct-2407-GGUF/blob/main/Mistral-Nemo-Instruct-2407-Q3_K_XL.gguf) | Q3_K_XL | 7.15GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. |
54
+ | [Mistral-Nemo-Instruct-2407-Q4_K_S.gguf](https://huggingface.co/bartowski/Mistral-Nemo-Instruct-2407-GGUF/blob/main/Mistral-Nemo-Instruct-2407-Q4_K_S.gguf) | Q4_K_S | 7.12GB | false | Slightly lower quality with more space savings, *recommended*. |
55
+ | [Mistral-Nemo-Instruct-2407-Q4_0.gguf](https://huggingface.co/bartowski/Mistral-Nemo-Instruct-2407-GGUF/blob/main/Mistral-Nemo-Instruct-2407-Q4_0.gguf) | Q4_0 | 7.09GB | false | Legacy format, generally not worth using over similarly sized formats |
56
+ | [Mistral-Nemo-Instruct-2407-Q4_0_8_8.gguf](https://huggingface.co/bartowski/Mistral-Nemo-Instruct-2407-GGUF/blob/main/Mistral-Nemo-Instruct-2407-Q4_0_8_8.gguf) | Q4_0_8_8 | 7.07GB | false | Optimized for ARM inference. Requires 'sve' support (see link below). *Don't use on Mac or Windows*. |
57
+ | [Mistral-Nemo-Instruct-2407-Q4_0_4_8.gguf](https://huggingface.co/bartowski/Mistral-Nemo-Instruct-2407-GGUF/blob/main/Mistral-Nemo-Instruct-2407-Q4_0_4_8.gguf) | Q4_0_4_8 | 7.07GB | false | Optimized for ARM inference. Requires 'i8mm' support (see link below). *Don't use on Mac or Windows*. |
58
+ | [Mistral-Nemo-Instruct-2407-Q4_0_4_4.gguf](https://huggingface.co/bartowski/Mistral-Nemo-Instruct-2407-GGUF/blob/main/Mistral-Nemo-Instruct-2407-Q4_0_4_4.gguf) | Q4_0_4_4 | 7.07GB | false | Optimized for ARM inference. Should work well on all ARM chips, pick this if you're unsure. *Don't use on Mac or Windows*. |
59
+ | [Mistral-Nemo-Instruct-2407-IQ4_XS.gguf](https://huggingface.co/bartowski/Mistral-Nemo-Instruct-2407-GGUF/blob/main/Mistral-Nemo-Instruct-2407-IQ4_XS.gguf) | IQ4_XS | 6.74GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
60
+ | [Mistral-Nemo-Instruct-2407-Q3_K_L.gguf](https://huggingface.co/bartowski/Mistral-Nemo-Instruct-2407-GGUF/blob/main/Mistral-Nemo-Instruct-2407-Q3_K_L.gguf) | Q3_K_L | 6.56GB | false | Lower quality but usable, good for low RAM availability. |
61
+ | [Mistral-Nemo-Instruct-2407-Q3_K_M.gguf](https://huggingface.co/bartowski/Mistral-Nemo-Instruct-2407-GGUF/blob/main/Mistral-Nemo-Instruct-2407-Q3_K_M.gguf) | Q3_K_M | 6.08GB | false | Low quality. |
62
+ | [Mistral-Nemo-Instruct-2407-IQ3_M.gguf](https://huggingface.co/bartowski/Mistral-Nemo-Instruct-2407-GGUF/blob/main/Mistral-Nemo-Instruct-2407-IQ3_M.gguf) | IQ3_M | 5.72GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
63
+ | [Mistral-Nemo-Instruct-2407-Q3_K_S.gguf](https://huggingface.co/bartowski/Mistral-Nemo-Instruct-2407-GGUF/blob/main/Mistral-Nemo-Instruct-2407-Q3_K_S.gguf) | Q3_K_S | 5.53GB | false | Low quality, not recommended. |
64
+ | [Mistral-Nemo-Instruct-2407-Q2_K_L.gguf](https://huggingface.co/bartowski/Mistral-Nemo-Instruct-2407-GGUF/blob/main/Mistral-Nemo-Instruct-2407-Q2_K_L.gguf) | Q2_K_L | 5.45GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. |
65
+ | [Mistral-Nemo-Instruct-2407-IQ3_XS.gguf](https://huggingface.co/bartowski/Mistral-Nemo-Instruct-2407-GGUF/blob/main/Mistral-Nemo-Instruct-2407-IQ3_XS.gguf) | IQ3_XS | 5.31GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
66
+ | [Mistral-Nemo-Instruct-2407-Q2_K.gguf](https://huggingface.co/bartowski/Mistral-Nemo-Instruct-2407-GGUF/blob/main/Mistral-Nemo-Instruct-2407-Q2_K.gguf) | Q2_K | 4.79GB | false | Very low quality but surprisingly usable. |
67
+ | [Mistral-Nemo-Instruct-2407-IQ2_M.gguf](https://huggingface.co/bartowski/Mistral-Nemo-Instruct-2407-GGUF/blob/main/Mistral-Nemo-Instruct-2407-IQ2_M.gguf) | IQ2_M | 4.44GB | false | Relatively low quality, uses SOTA techniques to be surprisingly usable. |
68
+
69
+ ## Embed/output weights
70
+
71
+ 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.
72
+
73
+ Some say that this improves the quality, others don't notice any difference. If you use these models PLEASE COMMENT with your findings. I would like feedback that these are actually used and useful so I don't keep uploading quants no one is using.
74
+
75
+ Thanks!
76
+
77
+ ## Downloading using huggingface-cli
78
+
79
+ First, make sure you have hugginface-cli installed:
80
+
81
+ ```
82
+ pip install -U "huggingface_hub[cli]"
83
+ ```
84
+
85
+ Then, you can target the specific file you want:
86
+
87
+ ```
88
+ huggingface-cli download bartowski/Mistral-Nemo-Instruct-2407-GGUF --include "Mistral-Nemo-Instruct-2407-Q4_K_M.gguf" --local-dir ./
89
+ ```
90
+
91
+ 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:
92
+
93
+ ```
94
+ huggingface-cli download bartowski/Mistral-Nemo-Instruct-2407-GGUF --include "Mistral-Nemo-Instruct-2407-Q8_0/*" --local-dir ./
95
+ ```
96
+
97
+ You can either specify a new local-dir (Mistral-Nemo-Instruct-2407-Q8_0) or download them all in place (./)
98
+
99
+ ## Q4_0_X_X
100
+
101
+ These are *NOT* for Metal (Apple) offloading, only ARM chips.
102
+
103
+ If you're using an ARM chip, the Q4_0_X_X quants will have a substantial speedup. Check out Q4_0_4_4 speed comparisons [on the original pull request](https://github.com/ggerganov/llama.cpp/pull/5780#pullrequestreview-21657544660)
104
+
105
+ To check which one would work best for your ARM chip, you can check [AArch64 SoC features](https://gpages.juszkiewicz.com.pl/arm-socs-table/arm-socs.html) (thanks EloyOn!).
106
+
107
+ ## Which file should I choose?
108
+
109
+ A great write up with charts showing various performances is provided by Artefact2 [here](https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9)
110
+
111
+ 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.
112
+
113
+ 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.
114
+
115
+ 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.
116
+
117
+ Next, you'll need to decide if you want to use an 'I-quant' or a 'K-quant'.
118
+
119
+ 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.
120
+
121
+ If you want to get more into the weeds, you can check out this extremely useful feature chart:
122
+
123
+ [llama.cpp feature matrix](https://github.com/ggerganov/llama.cpp/wiki/Feature-matrix)
124
+
125
+ 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.
126
+
127
+ These I-quants can also be used on CPU and Apple Metal, but will be slower than their K-quant equivalent, so speed vs performance is a tradeoff you'll have to decide.
128
+
129
+ The I-quants are *not* compatible with Vulcan, which is also AMD, so if you have an AMD card double check if you're using the rocBLAS build or the Vulcan build. At the time of writing this, LM Studio has a preview with ROCm support, and other inference engines have specific builds for ROCm.
130
+
131
+ ## Credits
132
+
133
+ Thank you kalomaze and Dampf for assistance in creating the imatrix calibration dataset
134
+
135
+ Thank you ZeroWw for the inspiration to experiment with embed/output
136
+
137
+ Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski