bartowski/Llama-3.1-Hawkish-8B-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/Llama-3.1-Hawkish-8B-GGUF
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-07-08 08:20:05 +08:00
commit 8c1183ac94
28 changed files with 273 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

60
.gitattributes vendored Normal file
View File

@@ -0,0 +1,60 @@
*.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
Llama-3.1-Hawkish-8B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
Llama-3.1-Hawkish-8B-Q6_K_L.gguf filter=lfs diff=lfs merge=lfs -text
Llama-3.1-Hawkish-8B-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
Llama-3.1-Hawkish-8B-Q5_K_L.gguf filter=lfs diff=lfs merge=lfs -text
Llama-3.1-Hawkish-8B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
Llama-3.1-Hawkish-8B-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
Llama-3.1-Hawkish-8B-Q4_K_L.gguf filter=lfs diff=lfs merge=lfs -text
Llama-3.1-Hawkish-8B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
Llama-3.1-Hawkish-8B-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
Llama-3.1-Hawkish-8B-Q4_0_8_8.gguf filter=lfs diff=lfs merge=lfs -text
Llama-3.1-Hawkish-8B-Q4_0_4_8.gguf filter=lfs diff=lfs merge=lfs -text
Llama-3.1-Hawkish-8B-Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text
Llama-3.1-Hawkish-8B-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
Llama-3.1-Hawkish-8B-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
Llama-3.1-Hawkish-8B-Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
Llama-3.1-Hawkish-8B-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
Llama-3.1-Hawkish-8B-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
Llama-3.1-Hawkish-8B-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
Llama-3.1-Hawkish-8B-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
Llama-3.1-Hawkish-8B-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
Llama-3.1-Hawkish-8B-Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text
Llama-3.1-Hawkish-8B-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
Llama-3.1-Hawkish-8B-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text
Llama-3.1-Hawkish-8B-f16.gguf filter=lfs diff=lfs merge=lfs -text
Llama-3.1-Hawkish-8B.imatrix filter=lfs diff=lfs merge=lfs -text

3
Llama-3.1-Hawkish-8B-IQ2_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0289df53895edfb4ba32a982e82613b27975200f3819e28c46428b03602ef09e
size 2948285728

3
Llama-3.1-Hawkish-8B-IQ3_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:900df8a16cbfa415ed30e440c63e1e9466da2f4fac5c39cf018d0640cceac236
size 3784828192

3
Llama-3.1-Hawkish-8B-IQ3_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:4363dde80b9900d1f4c75890818c3b79f409b5f3731a932f6b6f096f2e87bb8a
size 3518752032

3
Llama-3.1-Hawkish-8B-IQ4_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c36dc49172b7e70348e0e5d6f659807d2129ff49d183f83a65ed9d6af2cde383
size 4447667488

3
Llama-3.1-Hawkish-8B-Q2_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d05e4f6904f913ad82ee944025f0baca5ad30a68301d9ffc7499ec96bc408491
size 3179136288

3
Llama-3.1-Hawkish-8B-Q2_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:18287f3bddbce776f3a6328c012366d1fc21d756137186f64c3d421ea70581fd
size 3692160288

3
Llama-3.1-Hawkish-8B-Q3_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:deea81ade19972a75e59bcdcad67a35f00636b4e65381e57107b9c4c7f915d94
size 4321961248

3
Llama-3.1-Hawkish-8B-Q3_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:4f413da89b9a41d5ffed636b84f2ad6e57e45ce8ab8cb70c8a7b0f676ce028ae
size 4018922784

3
Llama-3.1-Hawkish-8B-Q3_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5e26cd6968f5f559fa52df7228114f6d0d8d500e43a0b880523105bc099565e3
size 3664504096

3
Llama-3.1-Hawkish-8B-Q3_K_XL.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1ea35a1d63bbe92739e2c0cbd0f9ffccbe9fdafffd0bccb14c221b3071e7cdb2
size 4781630752

3
Llama-3.1-Hawkish-8B-Q4_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:661a55e93c21c27c89950bf8a2fe2b1d6c79de1d7060ffa72e65a9af84592827
size 4675896608

3
Llama-3.1-Hawkish-8B-Q4_0_4_4.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:6b8099c2d25c99d0cf7aa75a34f097df62e19d9a821af43187c07f0afde915f5
size 4661216544

3
Llama-3.1-Hawkish-8B-Q4_0_4_8.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:bc07a9797c09df9c548463448f7bbc235aefab0d4fd5cc935ac0f761d372e1ad
size 4661216544

3
Llama-3.1-Hawkish-8B-Q4_0_8_8.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:074a09e0b1a6a1ffdd5963db5446a38e070b2e9f96d7201f6ad29197468006cf
size 4661216544

3
Llama-3.1-Hawkish-8B-Q4_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:8e7b55500983aa333b31f973bce257e8999c157e9647e595f2bd52647ceba398
size 5310637344

3
Llama-3.1-Hawkish-8B-Q4_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:613693936bbe641f41560151753716ba549ca052260fc5c0569e943e0bb834c3
size 4920739104

3
Llama-3.1-Hawkish-8B-Q4_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:6582552065e4373386483022ab7f30d5307285e9859ab2aed36c043f8e3b1eaa
size 4692673824

3
Llama-3.1-Hawkish-8B-Q5_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d6242f65d4ca4356e1ba4a2e93f5534586b48a9d422ce7b1680f2b249f2ced57
size 6057223456

3
Llama-3.1-Hawkish-8B-Q5_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:649a54f6bf033e167674e279ac9e22aecfd074c5e8782a35ed0d4e14eee0aa2a
size 5732992288

3
Llama-3.1-Hawkish-8B-Q5_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1c3c1fe1b80d6a1a1ed4779ff3927cc2d349886b16923a98c2e8cfa72214df95
size 5599298848

3
Llama-3.1-Hawkish-8B-Q6_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e57ef4201f4b3fbf2929363493a52a749a976f3895ca6fde398027fa4dd87ea6
size 6596011296

3
Llama-3.1-Hawkish-8B-Q6_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f111b1898d2ab6ab1462d77ba9a0423aef01324b6ac5f191f286a7ed1421adac
size 6850471200

3
Llama-3.1-Hawkish-8B-Q8_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c279e9d52595e0779d5da18e5f9ada1975bffb428f3c439d82d405d598e7893e
size 8540775712

3
Llama-3.1-Hawkish-8B-f16.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:400cf85e7d4c35e5e30343038c80d9110b5caa833d2585429c36a9bca076aae6
size 16068895744

3
Llama-3.1-Hawkish-8B.imatrix Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0be0f7a86aea85b93a686b9142b597875abe0cd60716c93e345c595a7413aa37
size 4988170

137
README.md Normal file
View File

@@ -0,0 +1,137 @@
---
base_model: mukaj/Llama-3.1-Hawkish-8B
language:
- en
license: other
pipeline_tag: text-generation
tags:
- llama-3.1
- finance
- economics
- math
- reasoning
- finetuning
quantized_by: bartowski
---
## Llamacpp imatrix Quantizations of Llama-3.1-Hawkish-8B
Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b3972">b3972</a> for quantization.
Original model: https://huggingface.co/mukaj/Llama-3.1-Hawkish-8B
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
```
<|begin_of_text|><|start_header_id|>system<|end_header_id|>
Cutting Knowledge Date: December 2023
Today Date: 26 Jul 2024
{system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>
{prompt}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
```
## Download a file (not the whole branch) from below:
| Filename | Quant type | File Size | Split | Description |
| -------- | ---------- | --------- | ----- | ----------- |
| [Llama-3.1-Hawkish-8B-f16.gguf](https://huggingface.co/bartowski/Llama-3.1-Hawkish-8B-GGUF/blob/main/Llama-3.1-Hawkish-8B-f16.gguf) | f16 | 16.07GB | false | Full F16 weights. |
| [Llama-3.1-Hawkish-8B-Q8_0.gguf](https://huggingface.co/bartowski/Llama-3.1-Hawkish-8B-GGUF/blob/main/Llama-3.1-Hawkish-8B-Q8_0.gguf) | Q8_0 | 8.54GB | false | Extremely high quality, generally unneeded but max available quant. |
| [Llama-3.1-Hawkish-8B-Q6_K_L.gguf](https://huggingface.co/bartowski/Llama-3.1-Hawkish-8B-GGUF/blob/main/Llama-3.1-Hawkish-8B-Q6_K_L.gguf) | Q6_K_L | 6.85GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. |
| [Llama-3.1-Hawkish-8B-Q6_K.gguf](https://huggingface.co/bartowski/Llama-3.1-Hawkish-8B-GGUF/blob/main/Llama-3.1-Hawkish-8B-Q6_K.gguf) | Q6_K | 6.60GB | false | Very high quality, near perfect, *recommended*. |
| [Llama-3.1-Hawkish-8B-Q5_K_L.gguf](https://huggingface.co/bartowski/Llama-3.1-Hawkish-8B-GGUF/blob/main/Llama-3.1-Hawkish-8B-Q5_K_L.gguf) | Q5_K_L | 6.06GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. |
| [Llama-3.1-Hawkish-8B-Q5_K_M.gguf](https://huggingface.co/bartowski/Llama-3.1-Hawkish-8B-GGUF/blob/main/Llama-3.1-Hawkish-8B-Q5_K_M.gguf) | Q5_K_M | 5.73GB | false | High quality, *recommended*. |
| [Llama-3.1-Hawkish-8B-Q5_K_S.gguf](https://huggingface.co/bartowski/Llama-3.1-Hawkish-8B-GGUF/blob/main/Llama-3.1-Hawkish-8B-Q5_K_S.gguf) | Q5_K_S | 5.60GB | false | High quality, *recommended*. |
| [Llama-3.1-Hawkish-8B-Q4_K_L.gguf](https://huggingface.co/bartowski/Llama-3.1-Hawkish-8B-GGUF/blob/main/Llama-3.1-Hawkish-8B-Q4_K_L.gguf) | Q4_K_L | 5.31GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. |
| [Llama-3.1-Hawkish-8B-Q4_K_M.gguf](https://huggingface.co/bartowski/Llama-3.1-Hawkish-8B-GGUF/blob/main/Llama-3.1-Hawkish-8B-Q4_K_M.gguf) | Q4_K_M | 4.92GB | false | Good quality, default size for must use cases, *recommended*. |
| [Llama-3.1-Hawkish-8B-Q3_K_XL.gguf](https://huggingface.co/bartowski/Llama-3.1-Hawkish-8B-GGUF/blob/main/Llama-3.1-Hawkish-8B-Q3_K_XL.gguf) | Q3_K_XL | 4.78GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. |
| [Llama-3.1-Hawkish-8B-Q4_K_S.gguf](https://huggingface.co/bartowski/Llama-3.1-Hawkish-8B-GGUF/blob/main/Llama-3.1-Hawkish-8B-Q4_K_S.gguf) | Q4_K_S | 4.69GB | false | Slightly lower quality with more space savings, *recommended*. |
| [Llama-3.1-Hawkish-8B-Q4_0.gguf](https://huggingface.co/bartowski/Llama-3.1-Hawkish-8B-GGUF/blob/main/Llama-3.1-Hawkish-8B-Q4_0.gguf) | Q4_0 | 4.68GB | false | Legacy format, generally not worth using over similarly sized formats |
| [Llama-3.1-Hawkish-8B-Q4_0_8_8.gguf](https://huggingface.co/bartowski/Llama-3.1-Hawkish-8B-GGUF/blob/main/Llama-3.1-Hawkish-8B-Q4_0_8_8.gguf) | Q4_0_8_8 | 4.66GB | false | Optimized for ARM inference. Requires 'sve' support (see link below). *Don't use on Mac or Windows*. |
| [Llama-3.1-Hawkish-8B-Q4_0_4_8.gguf](https://huggingface.co/bartowski/Llama-3.1-Hawkish-8B-GGUF/blob/main/Llama-3.1-Hawkish-8B-Q4_0_4_8.gguf) | Q4_0_4_8 | 4.66GB | false | Optimized for ARM inference. Requires 'i8mm' support (see link below). *Don't use on Mac or Windows*. |
| [Llama-3.1-Hawkish-8B-Q4_0_4_4.gguf](https://huggingface.co/bartowski/Llama-3.1-Hawkish-8B-GGUF/blob/main/Llama-3.1-Hawkish-8B-Q4_0_4_4.gguf) | Q4_0_4_4 | 4.66GB | 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*. |
| [Llama-3.1-Hawkish-8B-IQ4_XS.gguf](https://huggingface.co/bartowski/Llama-3.1-Hawkish-8B-GGUF/blob/main/Llama-3.1-Hawkish-8B-IQ4_XS.gguf) | IQ4_XS | 4.45GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
| [Llama-3.1-Hawkish-8B-Q3_K_L.gguf](https://huggingface.co/bartowski/Llama-3.1-Hawkish-8B-GGUF/blob/main/Llama-3.1-Hawkish-8B-Q3_K_L.gguf) | Q3_K_L | 4.32GB | false | Lower quality but usable, good for low RAM availability. |
| [Llama-3.1-Hawkish-8B-Q3_K_M.gguf](https://huggingface.co/bartowski/Llama-3.1-Hawkish-8B-GGUF/blob/main/Llama-3.1-Hawkish-8B-Q3_K_M.gguf) | Q3_K_M | 4.02GB | false | Low quality. |
| [Llama-3.1-Hawkish-8B-IQ3_M.gguf](https://huggingface.co/bartowski/Llama-3.1-Hawkish-8B-GGUF/blob/main/Llama-3.1-Hawkish-8B-IQ3_M.gguf) | IQ3_M | 3.78GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
| [Llama-3.1-Hawkish-8B-Q2_K_L.gguf](https://huggingface.co/bartowski/Llama-3.1-Hawkish-8B-GGUF/blob/main/Llama-3.1-Hawkish-8B-Q2_K_L.gguf) | Q2_K_L | 3.69GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. |
| [Llama-3.1-Hawkish-8B-Q3_K_S.gguf](https://huggingface.co/bartowski/Llama-3.1-Hawkish-8B-GGUF/blob/main/Llama-3.1-Hawkish-8B-Q3_K_S.gguf) | Q3_K_S | 3.66GB | false | Low quality, not recommended. |
| [Llama-3.1-Hawkish-8B-IQ3_XS.gguf](https://huggingface.co/bartowski/Llama-3.1-Hawkish-8B-GGUF/blob/main/Llama-3.1-Hawkish-8B-IQ3_XS.gguf) | IQ3_XS | 3.52GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
| [Llama-3.1-Hawkish-8B-Q2_K.gguf](https://huggingface.co/bartowski/Llama-3.1-Hawkish-8B-GGUF/blob/main/Llama-3.1-Hawkish-8B-Q2_K.gguf) | Q2_K | 3.18GB | false | Very low quality but surprisingly usable. |
| [Llama-3.1-Hawkish-8B-IQ2_M.gguf](https://huggingface.co/bartowski/Llama-3.1-Hawkish-8B-GGUF/blob/main/Llama-3.1-Hawkish-8B-IQ2_M.gguf) | IQ2_M | 2.95GB | false | Relatively low quality, uses SOTA techniques to be 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.
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/Llama-3.1-Hawkish-8B-GGUF --include "Llama-3.1-Hawkish-8B-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/Llama-3.1-Hawkish-8B-GGUF --include "Llama-3.1-Hawkish-8B-Q8_0/*" --local-dir ./
```
You can either specify a new local-dir (Llama-3.1-Hawkish-8B-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}