bartowski/NuExtract-1.5-smol-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/NuExtract-1.5-smol-GGUF
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-08-05 11:45:12 +08:00
commit 43b2a2285a
25 changed files with 286 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

57
.gitattributes vendored Normal file
View File

@@ -0,0 +1,57 @@
*.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
NuExtract-1.5-smol-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
NuExtract-1.5-smol-Q6_K_L.gguf filter=lfs diff=lfs merge=lfs -text
NuExtract-1.5-smol-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
NuExtract-1.5-smol-Q5_K_L.gguf filter=lfs diff=lfs merge=lfs -text
NuExtract-1.5-smol-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
NuExtract-1.5-smol-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
NuExtract-1.5-smol-Q4_K_L.gguf filter=lfs diff=lfs merge=lfs -text
NuExtract-1.5-smol-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
NuExtract-1.5-smol-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
NuExtract-1.5-smol-Q4_0_8_8.gguf filter=lfs diff=lfs merge=lfs -text
NuExtract-1.5-smol-Q4_0_4_8.gguf filter=lfs diff=lfs merge=lfs -text
NuExtract-1.5-smol-Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text
NuExtract-1.5-smol-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
NuExtract-1.5-smol-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
NuExtract-1.5-smol-Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
NuExtract-1.5-smol-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
NuExtract-1.5-smol-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
NuExtract-1.5-smol-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
NuExtract-1.5-smol-Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text
NuExtract-1.5-smol-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
NuExtract-1.5-smol-f16.gguf filter=lfs diff=lfs merge=lfs -text
NuExtract-1.5-smol.imatrix filter=lfs diff=lfs merge=lfs -text

3
NuExtract-1.5-smol-IQ3_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3babc0f6970dd88cd833ea4646a31a05e6a910738080668bba5ff6870061c236
size 810242912

3
NuExtract-1.5-smol-IQ4_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b2bedaec5bb3af84a29df0542f985f6391262c70a478d6a3073721dfdadb4ff2
size 940397408

3
NuExtract-1.5-smol-Q2_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:6a2a74d3bdebeccb85c7ba50992a2a6bdb0fe0003ad51d97aa8488a170e5122b
size 674583392

3
NuExtract-1.5-smol-Q2_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:15c01edd5b7487731d5f685f7fea26d9b4dc79fde3c36fcc9f2b9a440467d9be
size 698962784

3
NuExtract-1.5-smol-Q3_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3d5924d6855dd46e3e23dea4b308748a77513591e3ba80169cdde3b24cec0097
size 932533088

3
NuExtract-1.5-smol-Q3_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:02da842d35d3f00ef71192b4d2c2093e686cc15c2a36de7cc2de804b8c66b1ab
size 776819552

3
NuExtract-1.5-smol-Q3_K_XL.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:78f49a9625ca606b99166245f75e03d862708eb6e4dd64a91c7e73a27799bf23
size 956912480

3
NuExtract-1.5-smol-Q4_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:dcd059bb58f5612fdd1758159bb671330837e11d8d24496ed3a5452bac2c9041
size 993874784

3
NuExtract-1.5-smol-Q4_0_4_4.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:69d1de27a3769ba131085b5e7433e5a30f6971a8b8e6702b16763d1960b61a25
size 990729056

3
NuExtract-1.5-smol-Q4_0_4_8.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:fa96dae618785ddd224f8066db9c03187529226f573b8c29d4a9bf6ea9eacb78
size 990729056

3
NuExtract-1.5-smol-Q4_0_8_8.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:da24dd2c00aca19bfd963e716826ac6c2f74c985e10161ddd33efc43f22ff94e
size 990729056

3
NuExtract-1.5-smol-Q4_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:48e16cf9ded2c8c900b75943513d3d329712869d99f4d6d3175d81498bdd9098
size 1079989088

3
NuExtract-1.5-smol-Q4_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c18efbe99655bc16736f26492e01cc4623dfa053c26b51142e0d7edf24d5baf3
size 1055609696

3
NuExtract-1.5-smol-Q4_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1ec673a6f6ca4feefb2895314b09b7cc2de4908d58e56d0ea65c4d7bbb31f79f
size 999117664

3
NuExtract-1.5-smol-Q5_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b1dca19776d6fe7e459c476d9467bbaf45acd2e58026b915c8f01e3970cc505a
size 1249858400

3
NuExtract-1.5-smol-Q5_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5d90cd6c4bcba4c09675ad587e6cc7bfbdec51a4b18959ca4921d287633b8d17
size 1225479008

3
NuExtract-1.5-smol-Q5_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f9844d1901a946de6de9fb0b4308e7f29a381035262c390527518149b4381a30
size 1192055648

3
NuExtract-1.5-smol-Q6_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c92653254d669a15ea68a5fd78f11c027084d6923eec58d8630767b945a593f6
size 1405965152

3
NuExtract-1.5-smol-Q6_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5bd1040c78593652326638a78cab2674d9d9172928521ea7a5b306454f70f51d
size 1430344544

3
NuExtract-1.5-smol-Q8_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:66f85f98d7939a24d73d869c5e2c3b60d6f5991442c9870d4985280ece8a3df2
size 1820414816

3
NuExtract-1.5-smol-f16.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:bca7fd7b5f683eca8f9429473a1d1570b3b00a089f957288ba3d09c3966113c7
size 3424735808

3
NuExtract-1.5-smol.imatrix Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:8ff1a088927012e6f440a73393ac1ad172b11a45056f83f8631be9dba049d6f4
size 1971650

162
README.md Normal file
View File

@@ -0,0 +1,162 @@
---
quantized_by: bartowski
pipeline_tag: text-generation
base_model: numind/NuExtract-1.5-smol
tags:
- nlp
license: mit
inference: true
language:
- multilingual
---
## Llamacpp imatrix Quantizations of NuExtract-1.5-smol
Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b4132">b4132</a> for quantization.
Original model: https://huggingface.co/numind/NuExtract-1.5-smol
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
No prompt format found, check original model page
## Download a file (not the whole branch) from below:
| Filename | Quant type | File Size | Split | Description |
| -------- | ---------- | --------- | ----- | ----------- |
| [NuExtract-1.5-smol-f16.gguf](https://huggingface.co/bartowski/NuExtract-1.5-smol-GGUF/blob/main/NuExtract-1.5-smol-f16.gguf) | f16 | 3.42GB | false | Full F16 weights. |
| [NuExtract-1.5-smol-Q8_0.gguf](https://huggingface.co/bartowski/NuExtract-1.5-smol-GGUF/blob/main/NuExtract-1.5-smol-Q8_0.gguf) | Q8_0 | 1.82GB | false | Extremely high quality, generally unneeded but max available quant. |
| [NuExtract-1.5-smol-Q6_K_L.gguf](https://huggingface.co/bartowski/NuExtract-1.5-smol-GGUF/blob/main/NuExtract-1.5-smol-Q6_K_L.gguf) | Q6_K_L | 1.43GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. |
| [NuExtract-1.5-smol-Q6_K.gguf](https://huggingface.co/bartowski/NuExtract-1.5-smol-GGUF/blob/main/NuExtract-1.5-smol-Q6_K.gguf) | Q6_K | 1.41GB | false | Very high quality, near perfect, *recommended*. |
| [NuExtract-1.5-smol-Q5_K_L.gguf](https://huggingface.co/bartowski/NuExtract-1.5-smol-GGUF/blob/main/NuExtract-1.5-smol-Q5_K_L.gguf) | Q5_K_L | 1.25GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. |
| [NuExtract-1.5-smol-Q5_K_M.gguf](https://huggingface.co/bartowski/NuExtract-1.5-smol-GGUF/blob/main/NuExtract-1.5-smol-Q5_K_M.gguf) | Q5_K_M | 1.23GB | false | High quality, *recommended*. |
| [NuExtract-1.5-smol-Q5_K_S.gguf](https://huggingface.co/bartowski/NuExtract-1.5-smol-GGUF/blob/main/NuExtract-1.5-smol-Q5_K_S.gguf) | Q5_K_S | 1.19GB | false | High quality, *recommended*. |
| [NuExtract-1.5-smol-Q4_K_L.gguf](https://huggingface.co/bartowski/NuExtract-1.5-smol-GGUF/blob/main/NuExtract-1.5-smol-Q4_K_L.gguf) | Q4_K_L | 1.08GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. |
| [NuExtract-1.5-smol-Q4_K_M.gguf](https://huggingface.co/bartowski/NuExtract-1.5-smol-GGUF/blob/main/NuExtract-1.5-smol-Q4_K_M.gguf) | Q4_K_M | 1.06GB | false | Good quality, default size for most use cases, *recommended*. |
| [NuExtract-1.5-smol-Q4_K_S.gguf](https://huggingface.co/bartowski/NuExtract-1.5-smol-GGUF/blob/main/NuExtract-1.5-smol-Q4_K_S.gguf) | Q4_K_S | 1.00GB | false | Slightly lower quality with more space savings, *recommended*. |
| [NuExtract-1.5-smol-Q4_0_8_8.gguf](https://huggingface.co/bartowski/NuExtract-1.5-smol-GGUF/blob/main/NuExtract-1.5-smol-Q4_0_8_8.gguf) | Q4_0_8_8 | 0.99GB | false | Optimized for ARM and AVX inference. Requires 'sve' support for ARM (see details below). *Don't use on Mac*. |
| [NuExtract-1.5-smol-Q4_0_4_8.gguf](https://huggingface.co/bartowski/NuExtract-1.5-smol-GGUF/blob/main/NuExtract-1.5-smol-Q4_0_4_8.gguf) | Q4_0_4_8 | 0.99GB | false | Optimized for ARM inference. Requires 'i8mm' support (see details below). *Don't use on Mac*. |
| [NuExtract-1.5-smol-Q4_0_4_4.gguf](https://huggingface.co/bartowski/NuExtract-1.5-smol-GGUF/blob/main/NuExtract-1.5-smol-Q4_0_4_4.gguf) | Q4_0_4_4 | 0.99GB | false | Optimized for ARM inference. Should work well on all ARM chips, not for use with GPUs. *Don't use on Mac*. |
| [NuExtract-1.5-smol-Q4_0.gguf](https://huggingface.co/bartowski/NuExtract-1.5-smol-GGUF/blob/main/NuExtract-1.5-smol-Q4_0.gguf) | Q4_0 | 0.99GB | false | Legacy format, generally not worth using over similarly sized formats |
| [NuExtract-1.5-smol-Q3_K_XL.gguf](https://huggingface.co/bartowski/NuExtract-1.5-smol-GGUF/blob/main/NuExtract-1.5-smol-Q3_K_XL.gguf) | Q3_K_XL | 0.96GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. |
| [NuExtract-1.5-smol-IQ4_XS.gguf](https://huggingface.co/bartowski/NuExtract-1.5-smol-GGUF/blob/main/NuExtract-1.5-smol-IQ4_XS.gguf) | IQ4_XS | 0.94GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
| [NuExtract-1.5-smol-Q3_K_L.gguf](https://huggingface.co/bartowski/NuExtract-1.5-smol-GGUF/blob/main/NuExtract-1.5-smol-Q3_K_L.gguf) | Q3_K_L | 0.93GB | false | Lower quality but usable, good for low RAM availability. |
| [NuExtract-1.5-smol-IQ3_M.gguf](https://huggingface.co/bartowski/NuExtract-1.5-smol-GGUF/blob/main/NuExtract-1.5-smol-IQ3_M.gguf) | IQ3_M | 0.81GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
| [NuExtract-1.5-smol-Q3_K_S.gguf](https://huggingface.co/bartowski/NuExtract-1.5-smol-GGUF/blob/main/NuExtract-1.5-smol-Q3_K_S.gguf) | Q3_K_S | 0.78GB | false | Low quality, not recommended. |
| [NuExtract-1.5-smol-Q2_K_L.gguf](https://huggingface.co/bartowski/NuExtract-1.5-smol-GGUF/blob/main/NuExtract-1.5-smol-Q2_K_L.gguf) | Q2_K_L | 0.70GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. |
| [NuExtract-1.5-smol-Q2_K.gguf](https://huggingface.co/bartowski/NuExtract-1.5-smol-GGUF/blob/main/NuExtract-1.5-smol-Q2_K.gguf) | Q2_K | 0.67GB | false | Very low quality but surprisingly 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.
## 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/NuExtract-1.5-smol-GGUF --include "NuExtract-1.5-smol-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/NuExtract-1.5-smol-GGUF --include "NuExtract-1.5-smol-Q8_0/*" --local-dir ./
```
You can either specify a new local-dir (NuExtract-1.5-smol-Q8_0) or download them all in place (./)
</details>
## Q4_0_X_X information
<details>
<summary>Click to view Q4_0_X_X information</summary>
These are *NOT* for Metal (Apple) or GPU (nvidia/AMD/intel) offloading, only ARM chips (and certain AVX2/AVX512 CPUs).
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!).
If you're using a CPU that supports AVX2 or AVX512 (typically server CPUs and AMD's latest Zen5 CPUs) and are not offloading to a GPU, the Q4_0_8_8 may offer a nice speed as well:
<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 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.
</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.
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}