bartowski/Mistral-Nemo-Prism-12B-GGUF
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: bartowski/Mistral-Nemo-Prism-12B-GGUF
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-08-05 05:23:12 +08:00
commit 13f67a6285
30 changed files with 274 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

62
.gitattributes vendored Normal file
View File

@@ -0,0 +1,62 @@
*.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
Mistral-Nemo-Prism-12B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
Mistral-Nemo-Prism-12B-Q6_K_L.gguf filter=lfs diff=lfs merge=lfs -text
Mistral-Nemo-Prism-12B-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
Mistral-Nemo-Prism-12B-Q5_K_L.gguf filter=lfs diff=lfs merge=lfs -text
Mistral-Nemo-Prism-12B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
Mistral-Nemo-Prism-12B-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
Mistral-Nemo-Prism-12B-Q4_K_L.gguf filter=lfs diff=lfs merge=lfs -text
Mistral-Nemo-Prism-12B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
Mistral-Nemo-Prism-12B-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
Mistral-Nemo-Prism-12B-Q4_0_8_8.gguf filter=lfs diff=lfs merge=lfs -text
Mistral-Nemo-Prism-12B-Q4_0_4_8.gguf filter=lfs diff=lfs merge=lfs -text
Mistral-Nemo-Prism-12B-Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text
Mistral-Nemo-Prism-12B-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
Mistral-Nemo-Prism-12B-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
Mistral-Nemo-Prism-12B-Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
Mistral-Nemo-Prism-12B-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
Mistral-Nemo-Prism-12B-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
Mistral-Nemo-Prism-12B-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
Mistral-Nemo-Prism-12B-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
Mistral-Nemo-Prism-12B-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
Mistral-Nemo-Prism-12B-Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text
Mistral-Nemo-Prism-12B-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
Mistral-Nemo-Prism-12B-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text
Mistral-Nemo-Prism-12B-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text
Mistral-Nemo-Prism-12B-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text
Mistral-Nemo-Prism-12B-f16.gguf filter=lfs diff=lfs merge=lfs -text
Mistral-Nemo-Prism-12B.imatrix filter=lfs diff=lfs merge=lfs -text

3
Mistral-Nemo-Prism-12B-IQ2_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:26714b566c8c9c48e19093c98672f51336374b83e664824e1c509a15fd812baa
size 4435023424

3
Mistral-Nemo-Prism-12B-IQ2_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5e28b66aea63c660d39c55547c7fd69af0b18a8937f0fb172208a9625de69df0
size 4138473024

3
Mistral-Nemo-Prism-12B-IQ2_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:6b947b9c51dcf880330ad7254df0e9e8b1f8f552624d485f38f2209a1a21484d
size 3915077184

3
Mistral-Nemo-Prism-12B-IQ3_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:63c06880cf3032b7affa408f98400f54f2f88eb76c27db609dbbdd3d9429631b
size 5722232384

3
Mistral-Nemo-Prism-12B-IQ3_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c88f010dfe604c8d299e54de6cc3fba5f2b8c1033b120a7604052f6b477674db
size 5306488384

3
Mistral-Nemo-Prism-12B-IQ4_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:aec84ff88c481e647a04683dbb9fa9a98aa61cb72d8a6903ca259ea8bebfef6a
size 6742709824

3
Mistral-Nemo-Prism-12B-Q2_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:48ffb57a9fa5cc5e43801c78b4c7b7dd0bb1056a3f22a1cd44dbdb37e7aa157a
size 4791047744

3
Mistral-Nemo-Prism-12B-Q2_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ea12a8992515373ee0f72d49444b81429eaa4d2f8a4141e94e12ad5c2e2ee346
size 5446407744

3
Mistral-Nemo-Prism-12B-Q3_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:56c4fc19f52e7112d2665ab978a44eb85f9709f497ae4c6ca76fc3471f2a1302
size 6561502784

3
Mistral-Nemo-Prism-12B-Q3_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d37fc8ffc884c7ebb817c21a314458cf21703d8a0e95c65ef12ce5bedb927a7c
size 6083089984

3
Mistral-Nemo-Prism-12B-Q3_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:6f77e25bb8742864fd5f20972ebace1952b6c530290827ccfa0e26eaf00daf78
size 5534225984

3
Mistral-Nemo-Prism-12B-Q3_K_XL.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:6023484e32b5e1894cc50da3043aea41e541dcbe87a433be30b01e022292bab6
size 7148705344

3
Mistral-Nemo-Prism-12B-Q4_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f65a64f9312015b1115348f6f1dd0ca51ef562e34e9eeca5e86612a3d9dac19a
size 7094638144

3
Mistral-Nemo-Prism-12B-Q4_0_4_4.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1eb28c63ff1aec67f66213ad85a6cbe01bfa37b16746c2b49dd8a1b7a0add677
size 7071700544

3
Mistral-Nemo-Prism-12B-Q4_0_4_8.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:628a780c9fb80f0dfc517bff26d0059035691be6f0c9830dd9e613b6f1e7462b
size 7071700544

3
Mistral-Nemo-Prism-12B-Q4_0_8_8.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:7281c98781b9e87a61dc4fb17c934086e5bfbce8cff46af86aa225b92fe5b093
size 7071700544

3
Mistral-Nemo-Prism-12B-Q4_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a0c03277d2b650e3d6aaa6b17da087f5ffd83b489b5bcf3c060162723a40173d
size 7975278144

3
Mistral-Nemo-Prism-12B-Q4_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:96b922c6d55d94ffb91e869b8cccaf2b6dc449d75b1456f4d4578c92c8184c25
size 7477204544

3
Mistral-Nemo-Prism-12B-Q4_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0f3c625c0dd5432b10dcc08f1d5a2e08693ad246ea5a6b7830c2284768290570
size 7120197184

3
Mistral-Nemo-Prism-12B-Q5_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a9c464f958428d522dfc90a06ad6aca79b8006cf9d15b384919c322d8d441b8c
size 9141818944

3
Mistral-Nemo-Prism-12B-Q5_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:accbe5f09bc21546eb4a0051ff9778eb5541889c6c3e5f3c4885f675635bce68
size 8727631424

3
Mistral-Nemo-Prism-12B-Q5_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2d600ed7ac544325e33a1d5dd53c30db7aaddd961324df0b6516a8dd7db4e2ca
size 8518735424

3
Mistral-Nemo-Prism-12B-Q6_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3dd76c37f330f76469c8326da798f6fcbf8dbca164be766cd151feda8b50a3a1
size 10056209984

3
Mistral-Nemo-Prism-12B-Q6_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c9c360f950999a1a881f1dc951ae8b7d502ff26c0a864fcfae9613f28ac09a27
size 10381268544

3
Mistral-Nemo-Prism-12B-Q8_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d987e92b09fccb86d893877bc6c62688e7b9d6b0ca97dae70a51ad5537bf1578
size 13022369344

3
Mistral-Nemo-Prism-12B-f16.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2fffaf8dc52d1e845e44fc709ecadd1e8a28ae8f3e331abd3b2656b4e3dbe506
size 24504276288

3
Mistral-Nemo-Prism-12B.imatrix Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:aabc677c35a263585266d040424d339133541f5239ca45b05608f0f0d5eb06c6
size 7054418

130
README.md Normal file
View File

@@ -0,0 +1,130 @@
---
quantized_by: bartowski
pipeline_tag: text-generation
datasets:
- nbeerbower/Arkhaios-DPO
- nbeerbower/Purpura-DPO
base_model: nbeerbower/Mistral-Nemo-Prism-12B
license: apache-2.0
---
## Llamacpp imatrix Quantizations of Mistral-Nemo-Prism-12B
Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b4058">b4058</a> for quantization.
Original model: https://huggingface.co/nbeerbower/Mistral-Nemo-Prism-12B
All quants made using imatrix option with dataset from [here](https://gist.github.com/bartowski1182/eb213dccb3571f863da82e99418f81e8)
Run them in [LM Studio](https://lmstudio.ai/)
## Prompt format
```
<|im_start|>system
{system_prompt}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
```
## Download a file (not the whole branch) from below:
| Filename | Quant type | File Size | Split | Description |
| -------- | ---------- | --------- | ----- | ----------- |
| [Mistral-Nemo-Prism-12B-f16.gguf](https://huggingface.co/bartowski/Mistral-Nemo-Prism-12B-GGUF/blob/main/Mistral-Nemo-Prism-12B-f16.gguf) | f16 | 24.50GB | false | Full F16 weights. |
| [Mistral-Nemo-Prism-12B-Q8_0.gguf](https://huggingface.co/bartowski/Mistral-Nemo-Prism-12B-GGUF/blob/main/Mistral-Nemo-Prism-12B-Q8_0.gguf) | Q8_0 | 13.02GB | false | Extremely high quality, generally unneeded but max available quant. |
| [Mistral-Nemo-Prism-12B-Q6_K_L.gguf](https://huggingface.co/bartowski/Mistral-Nemo-Prism-12B-GGUF/blob/main/Mistral-Nemo-Prism-12B-Q6_K_L.gguf) | Q6_K_L | 10.38GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. |
| [Mistral-Nemo-Prism-12B-Q6_K.gguf](https://huggingface.co/bartowski/Mistral-Nemo-Prism-12B-GGUF/blob/main/Mistral-Nemo-Prism-12B-Q6_K.gguf) | Q6_K | 10.06GB | false | Very high quality, near perfect, *recommended*. |
| [Mistral-Nemo-Prism-12B-Q5_K_L.gguf](https://huggingface.co/bartowski/Mistral-Nemo-Prism-12B-GGUF/blob/main/Mistral-Nemo-Prism-12B-Q5_K_L.gguf) | Q5_K_L | 9.14GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. |
| [Mistral-Nemo-Prism-12B-Q5_K_M.gguf](https://huggingface.co/bartowski/Mistral-Nemo-Prism-12B-GGUF/blob/main/Mistral-Nemo-Prism-12B-Q5_K_M.gguf) | Q5_K_M | 8.73GB | false | High quality, *recommended*. |
| [Mistral-Nemo-Prism-12B-Q5_K_S.gguf](https://huggingface.co/bartowski/Mistral-Nemo-Prism-12B-GGUF/blob/main/Mistral-Nemo-Prism-12B-Q5_K_S.gguf) | Q5_K_S | 8.52GB | false | High quality, *recommended*. |
| [Mistral-Nemo-Prism-12B-Q4_K_L.gguf](https://huggingface.co/bartowski/Mistral-Nemo-Prism-12B-GGUF/blob/main/Mistral-Nemo-Prism-12B-Q4_K_L.gguf) | Q4_K_L | 7.98GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. |
| [Mistral-Nemo-Prism-12B-Q4_K_M.gguf](https://huggingface.co/bartowski/Mistral-Nemo-Prism-12B-GGUF/blob/main/Mistral-Nemo-Prism-12B-Q4_K_M.gguf) | Q4_K_M | 7.48GB | false | Good quality, default size for most use cases, *recommended*. |
| [Mistral-Nemo-Prism-12B-Q3_K_XL.gguf](https://huggingface.co/bartowski/Mistral-Nemo-Prism-12B-GGUF/blob/main/Mistral-Nemo-Prism-12B-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. |
| [Mistral-Nemo-Prism-12B-Q4_K_S.gguf](https://huggingface.co/bartowski/Mistral-Nemo-Prism-12B-GGUF/blob/main/Mistral-Nemo-Prism-12B-Q4_K_S.gguf) | Q4_K_S | 7.12GB | false | Slightly lower quality with more space savings, *recommended*. |
| [Mistral-Nemo-Prism-12B-Q4_0.gguf](https://huggingface.co/bartowski/Mistral-Nemo-Prism-12B-GGUF/blob/main/Mistral-Nemo-Prism-12B-Q4_0.gguf) | Q4_0 | 7.09GB | false | Legacy format, generally not worth using over similarly sized formats |
| [Mistral-Nemo-Prism-12B-Q4_0_8_8.gguf](https://huggingface.co/bartowski/Mistral-Nemo-Prism-12B-GGUF/blob/main/Mistral-Nemo-Prism-12B-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*. |
| [Mistral-Nemo-Prism-12B-Q4_0_4_8.gguf](https://huggingface.co/bartowski/Mistral-Nemo-Prism-12B-GGUF/blob/main/Mistral-Nemo-Prism-12B-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*. |
| [Mistral-Nemo-Prism-12B-Q4_0_4_4.gguf](https://huggingface.co/bartowski/Mistral-Nemo-Prism-12B-GGUF/blob/main/Mistral-Nemo-Prism-12B-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*. |
| [Mistral-Nemo-Prism-12B-IQ4_XS.gguf](https://huggingface.co/bartowski/Mistral-Nemo-Prism-12B-GGUF/blob/main/Mistral-Nemo-Prism-12B-IQ4_XS.gguf) | IQ4_XS | 6.74GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
| [Mistral-Nemo-Prism-12B-Q3_K_L.gguf](https://huggingface.co/bartowski/Mistral-Nemo-Prism-12B-GGUF/blob/main/Mistral-Nemo-Prism-12B-Q3_K_L.gguf) | Q3_K_L | 6.56GB | false | Lower quality but usable, good for low RAM availability. |
| [Mistral-Nemo-Prism-12B-Q3_K_M.gguf](https://huggingface.co/bartowski/Mistral-Nemo-Prism-12B-GGUF/blob/main/Mistral-Nemo-Prism-12B-Q3_K_M.gguf) | Q3_K_M | 6.08GB | false | Low quality. |
| [Mistral-Nemo-Prism-12B-IQ3_M.gguf](https://huggingface.co/bartowski/Mistral-Nemo-Prism-12B-GGUF/blob/main/Mistral-Nemo-Prism-12B-IQ3_M.gguf) | IQ3_M | 5.72GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
| [Mistral-Nemo-Prism-12B-Q3_K_S.gguf](https://huggingface.co/bartowski/Mistral-Nemo-Prism-12B-GGUF/blob/main/Mistral-Nemo-Prism-12B-Q3_K_S.gguf) | Q3_K_S | 5.53GB | false | Low quality, not recommended. |
| [Mistral-Nemo-Prism-12B-Q2_K_L.gguf](https://huggingface.co/bartowski/Mistral-Nemo-Prism-12B-GGUF/blob/main/Mistral-Nemo-Prism-12B-Q2_K_L.gguf) | Q2_K_L | 5.45GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. |
| [Mistral-Nemo-Prism-12B-IQ3_XS.gguf](https://huggingface.co/bartowski/Mistral-Nemo-Prism-12B-GGUF/blob/main/Mistral-Nemo-Prism-12B-IQ3_XS.gguf) | IQ3_XS | 5.31GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
| [Mistral-Nemo-Prism-12B-Q2_K.gguf](https://huggingface.co/bartowski/Mistral-Nemo-Prism-12B-GGUF/blob/main/Mistral-Nemo-Prism-12B-Q2_K.gguf) | Q2_K | 4.79GB | false | Very low quality but surprisingly usable. |
| [Mistral-Nemo-Prism-12B-IQ2_M.gguf](https://huggingface.co/bartowski/Mistral-Nemo-Prism-12B-GGUF/blob/main/Mistral-Nemo-Prism-12B-IQ2_M.gguf) | IQ2_M | 4.44GB | false | Relatively low quality, uses SOTA techniques to be surprisingly usable. |
| [Mistral-Nemo-Prism-12B-IQ2_S.gguf](https://huggingface.co/bartowski/Mistral-Nemo-Prism-12B-GGUF/blob/main/Mistral-Nemo-Prism-12B-IQ2_S.gguf) | IQ2_S | 4.14GB | false | Low quality, uses SOTA techniques to be usable. |
| [Mistral-Nemo-Prism-12B-IQ2_XS.gguf](https://huggingface.co/bartowski/Mistral-Nemo-Prism-12B-GGUF/blob/main/Mistral-Nemo-Prism-12B-IQ2_XS.gguf) | IQ2_XS | 3.92GB | 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.
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.
Thanks!
## Downloading using huggingface-cli
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/Mistral-Nemo-Prism-12B-GGUF --include "Mistral-Nemo-Prism-12B-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/Mistral-Nemo-Prism-12B-GGUF --include "Mistral-Nemo-Prism-12B-Q8_0/*" --local-dir ./
```
You can either specify a new local-dir (Mistral-Nemo-Prism-12B-Q8_0) or download them all in place (./)
## Q4_0_X_X
These are *NOT* for Metal (Apple) offloading, only ARM chips.
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)
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!).
## Which file should I choose?
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/ggerganov/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 and Apple Metal, but will be slower than their K-quant equivalent, so speed vs performance is a tradeoff you'll have to decide.
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.
## 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.
Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski

1
configuration.json Normal file
View File

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