bartowski/Menlo_Lucy-128k-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/Menlo_Lucy-128k-GGUF
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-08-30 15:18:13 +08:00
commit 7841ee8851
27 changed files with 293 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

49
.gitattributes vendored Normal file
View File

@@ -0,0 +1,49 @@
*.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
Menlo_Lucy-128k.imatrix filter=lfs diff=lfs merge=lfs -text

3
Menlo_Lucy-128k-IQ3_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:7417b2d2f8d4d0abb2bc1d5a4cab347ea5fe96c77d917484dcdfc20afb67405d
size 895662560

3
Menlo_Lucy-128k-IQ3_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:46bcec0eea14d2b899c0e2818540c31d7586b3334525789fe4dab77ba029fce6
size 834222560

3
Menlo_Lucy-128k-IQ3_XXS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ec1f9c36f055632239714fc4725a403664792275e63e10f8ed94bca80c631bf8
size 754360800

3
Menlo_Lucy-128k-IQ4_NL.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2971328df64399088f54c29b4c3646977bdac443f74964a65e76bd7a4d7d76fb
size 1054423520

3
Menlo_Lucy-128k-IQ4_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5bd7eb5134d4cf7aee2ed22d74db83af1fdc2a9ecaf1dc7a4dc9138481246a3e
size 1010383328

3
Menlo_Lucy-128k-Q2_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:210b20c8dd1db5a8e97d1e98167af81d28fde193d711d8274ac69c2be72495e0
size 777796064

3
Menlo_Lucy-128k-Q2_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:354c7024839b45c5045183fe3affde6d66125d6573cb47ae022b71a05a333ab2
size 853156320

3
Menlo_Lucy-128k-Q3_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e9944b5e3625e409aa662ce2e2f8586e90c485472fc9e994d581a3a3436f4155
size 1003502048

3
Menlo_Lucy-128k-Q3_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e1887cc0a26c74e94f6a5af24bbe6ea709f0e9edec1524702c322b724357486f
size 939538912

3
Menlo_Lucy-128k-Q3_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9e3a78ca578fafbe5507bb82939867c196454b6d495c117df13eb673bed44c8b
size 867252704

3
Menlo_Lucy-128k-Q3_K_XL.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:86d35abb7102b08b0eda22d88bb83acc12564fc8bb7a0ac33c114b9d1a9d535f
size 1078862304

3
Menlo_Lucy-128k-Q4_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b781fb5e8b8c9d68d33790802c7f30aeb1cf8c26c9ea8ef2d4eac26209d5f493
size 1056782816

3
Menlo_Lucy-128k-Q4_1.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b1b535762ae7190af6a2b7ed7a986c5007d92d92586886598e7002839f054b5f
size 1142503904

3
Menlo_Lucy-128k-Q4_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ef1211258677b14c4d7753015147e85aa5b682b9669ac52af064431d3633fcc7
size 1182769632

3
Menlo_Lucy-128k-Q4_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:fb3e591cccc5d2821f3c615fd6dc2ca86d409f56fbc124275510a9612a90e61f
size 1107409376

3
Menlo_Lucy-128k-Q4_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b5243c198c553c2d24a4228f1abc50e011eba83d03645d5a6b40717ea71cb1b6
size 1060190688

3
Menlo_Lucy-128k-Q5_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a58bccc97d7ef4c78689da374c63cdd202b44e7aa33f75d8865a8c96bb973071
size 1333240288

3
Menlo_Lucy-128k-Q5_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:73db0cfacc16408e3fb034de18c23421ce99ce334903d3186243a2cca70640e3
size 1257880032

3
Menlo_Lucy-128k-Q5_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:cc10dfb89ad3317cf4d520ce1d0b1d9a4b3f3a5a86a0df59ff5bb0245a9fa056
size 1230584288

3
Menlo_Lucy-128k-Q6_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:572d6e762d1b789358d4c8799377f8cd7823e2c8a22d4c228a5a50689f9dd653
size 1417755104

3
Menlo_Lucy-128k-Q6_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5b943017b0dde01b131d82ddee539b95b6ea420a6b5661a9adb7e97da611f279
size 1493115360

3
Menlo_Lucy-128k-Q8_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f7365edbd6ea438d1677189c724eda4426699124bfe7663c1b41b1fcf51f3dab
size 1834426848

3
Menlo_Lucy-128k-bf16.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2c77f8c9b540d25428cbe2500f59ba59073437951de43aef97415a74c13a3e9a
size 3447349472

3
Menlo_Lucy-128k.imatrix Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f5eded0cc7ff128157c2d70228413cdb7348bcee83d173a7fbab3cff3596299d
size 2070886

171
README.md Normal file
View File

@@ -0,0 +1,171 @@
---
quantized_by: bartowski
pipeline_tag: text-generation
base_model: Menlo/Lucy-128k
base_model_relation: quantized
---
## Llamacpp imatrix Quantizations of Lucy-128k by Menlo
Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b5924">b5924</a> for quantization.
Original model: https://huggingface.co/Menlo/Lucy-128k
All quants made using imatrix option with dataset from [here](https://gist.github.com/bartowski1182/eb213dccb3571f863da82e99418f81e8)
Run them in [LM Studio](https://lmstudio.ai/)
Run them directly with [llama.cpp](https://github.com/ggerganov/llama.cpp), or any other llama.cpp based project
## Prompt format
No chat template specified so default is used. This may be incorrect, check original model card for details.
```
<|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 |
| -------- | ---------- | --------- | ----- | ----------- |
| [Lucy-128k-bf16.gguf](https://huggingface.co/bartowski/Menlo_Lucy-128k-GGUF/blob/main/Menlo_Lucy-128k-bf16.gguf) | bf16 | 3.45GB | false | Full BF16 weights. |
| [Lucy-128k-Q8_0.gguf](https://huggingface.co/bartowski/Menlo_Lucy-128k-GGUF/blob/main/Menlo_Lucy-128k-Q8_0.gguf) | Q8_0 | 1.83GB | false | Extremely high quality, generally unneeded but max available quant. |
| [Lucy-128k-Q6_K_L.gguf](https://huggingface.co/bartowski/Menlo_Lucy-128k-GGUF/blob/main/Menlo_Lucy-128k-Q6_K_L.gguf) | Q6_K_L | 1.49GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. |
| [Lucy-128k-Q6_K.gguf](https://huggingface.co/bartowski/Menlo_Lucy-128k-GGUF/blob/main/Menlo_Lucy-128k-Q6_K.gguf) | Q6_K | 1.42GB | false | Very high quality, near perfect, *recommended*. |
| [Lucy-128k-Q5_K_L.gguf](https://huggingface.co/bartowski/Menlo_Lucy-128k-GGUF/blob/main/Menlo_Lucy-128k-Q5_K_L.gguf) | Q5_K_L | 1.33GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. |
| [Lucy-128k-Q5_K_M.gguf](https://huggingface.co/bartowski/Menlo_Lucy-128k-GGUF/blob/main/Menlo_Lucy-128k-Q5_K_M.gguf) | Q5_K_M | 1.26GB | false | High quality, *recommended*. |
| [Lucy-128k-Q5_K_S.gguf](https://huggingface.co/bartowski/Menlo_Lucy-128k-GGUF/blob/main/Menlo_Lucy-128k-Q5_K_S.gguf) | Q5_K_S | 1.23GB | false | High quality, *recommended*. |
| [Lucy-128k-Q4_K_L.gguf](https://huggingface.co/bartowski/Menlo_Lucy-128k-GGUF/blob/main/Menlo_Lucy-128k-Q4_K_L.gguf) | Q4_K_L | 1.18GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. |
| [Lucy-128k-Q4_1.gguf](https://huggingface.co/bartowski/Menlo_Lucy-128k-GGUF/blob/main/Menlo_Lucy-128k-Q4_1.gguf) | Q4_1 | 1.14GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. |
| [Lucy-128k-Q4_K_M.gguf](https://huggingface.co/bartowski/Menlo_Lucy-128k-GGUF/blob/main/Menlo_Lucy-128k-Q4_K_M.gguf) | Q4_K_M | 1.11GB | false | Good quality, default size for most use cases, *recommended*. |
| [Lucy-128k-Q3_K_XL.gguf](https://huggingface.co/bartowski/Menlo_Lucy-128k-GGUF/blob/main/Menlo_Lucy-128k-Q3_K_XL.gguf) | Q3_K_XL | 1.08GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. |
| [Lucy-128k-Q4_K_S.gguf](https://huggingface.co/bartowski/Menlo_Lucy-128k-GGUF/blob/main/Menlo_Lucy-128k-Q4_K_S.gguf) | Q4_K_S | 1.06GB | false | Slightly lower quality with more space savings, *recommended*. |
| [Lucy-128k-Q4_0.gguf](https://huggingface.co/bartowski/Menlo_Lucy-128k-GGUF/blob/main/Menlo_Lucy-128k-Q4_0.gguf) | Q4_0 | 1.06GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. |
| [Lucy-128k-IQ4_NL.gguf](https://huggingface.co/bartowski/Menlo_Lucy-128k-GGUF/blob/main/Menlo_Lucy-128k-IQ4_NL.gguf) | IQ4_NL | 1.05GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. |
| [Lucy-128k-IQ4_XS.gguf](https://huggingface.co/bartowski/Menlo_Lucy-128k-GGUF/blob/main/Menlo_Lucy-128k-IQ4_XS.gguf) | IQ4_XS | 1.01GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
| [Lucy-128k-Q3_K_L.gguf](https://huggingface.co/bartowski/Menlo_Lucy-128k-GGUF/blob/main/Menlo_Lucy-128k-Q3_K_L.gguf) | Q3_K_L | 1.00GB | false | Lower quality but usable, good for low RAM availability. |
| [Lucy-128k-Q3_K_M.gguf](https://huggingface.co/bartowski/Menlo_Lucy-128k-GGUF/blob/main/Menlo_Lucy-128k-Q3_K_M.gguf) | Q3_K_M | 0.94GB | false | Low quality. |
| [Lucy-128k-IQ3_M.gguf](https://huggingface.co/bartowski/Menlo_Lucy-128k-GGUF/blob/main/Menlo_Lucy-128k-IQ3_M.gguf) | IQ3_M | 0.90GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
| [Lucy-128k-Q3_K_S.gguf](https://huggingface.co/bartowski/Menlo_Lucy-128k-GGUF/blob/main/Menlo_Lucy-128k-Q3_K_S.gguf) | Q3_K_S | 0.87GB | false | Low quality, not recommended. |
| [Lucy-128k-Q2_K_L.gguf](https://huggingface.co/bartowski/Menlo_Lucy-128k-GGUF/blob/main/Menlo_Lucy-128k-Q2_K_L.gguf) | Q2_K_L | 0.85GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. |
| [Lucy-128k-IQ3_XS.gguf](https://huggingface.co/bartowski/Menlo_Lucy-128k-GGUF/blob/main/Menlo_Lucy-128k-IQ3_XS.gguf) | IQ3_XS | 0.83GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
| [Lucy-128k-Q2_K.gguf](https://huggingface.co/bartowski/Menlo_Lucy-128k-GGUF/blob/main/Menlo_Lucy-128k-Q2_K.gguf) | Q2_K | 0.78GB | false | Very low quality but surprisingly usable. |
| [Lucy-128k-IQ3_XXS.gguf](https://huggingface.co/bartowski/Menlo_Lucy-128k-GGUF/blob/main/Menlo_Lucy-128k-IQ3_XXS.gguf) | IQ3_XXS | 0.75GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. |
## 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/Menlo_Lucy-128k-GGUF --include "Menlo_Lucy-128k-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/Menlo_Lucy-128k-GGUF --include "Menlo_Lucy-128k-Q8_0/*" --local-dir ./
```
You can either specify a new local-dir (Menlo_Lucy-128k-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/ggerganov/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/ggerganov/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/ggerganov/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/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, 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

1
configuration.json Normal file
View File

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