bartowski/Llama-3.1-8B-ArliAI-RPMax-v1.1-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-3.1-8B-ArliAI-RPMax-v1.1-GGUF
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-08-06 03:35:12 +08:00
commit 0358af9033
28 changed files with 261 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-3.1-8B-ArliAI-RPMax-v1.1-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
Llama-3.1-8B-ArliAI-RPMax-v1.1-Q6_K_L.gguf filter=lfs diff=lfs merge=lfs -text
Llama-3.1-8B-ArliAI-RPMax-v1.1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
Llama-3.1-8B-ArliAI-RPMax-v1.1-Q5_K_L.gguf filter=lfs diff=lfs merge=lfs -text
Llama-3.1-8B-ArliAI-RPMax-v1.1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
Llama-3.1-8B-ArliAI-RPMax-v1.1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
Llama-3.1-8B-ArliAI-RPMax-v1.1-Q4_K_L.gguf filter=lfs diff=lfs merge=lfs -text
Llama-3.1-8B-ArliAI-RPMax-v1.1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
Llama-3.1-8B-ArliAI-RPMax-v1.1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
Llama-3.1-8B-ArliAI-RPMax-v1.1-Q4_0_8_8.gguf filter=lfs diff=lfs merge=lfs -text
Llama-3.1-8B-ArliAI-RPMax-v1.1-Q4_0_4_8.gguf filter=lfs diff=lfs merge=lfs -text
Llama-3.1-8B-ArliAI-RPMax-v1.1-Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text
Llama-3.1-8B-ArliAI-RPMax-v1.1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
Llama-3.1-8B-ArliAI-RPMax-v1.1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
Llama-3.1-8B-ArliAI-RPMax-v1.1-Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
Llama-3.1-8B-ArliAI-RPMax-v1.1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
Llama-3.1-8B-ArliAI-RPMax-v1.1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
Llama-3.1-8B-ArliAI-RPMax-v1.1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
Llama-3.1-8B-ArliAI-RPMax-v1.1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
Llama-3.1-8B-ArliAI-RPMax-v1.1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
Llama-3.1-8B-ArliAI-RPMax-v1.1-Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text
Llama-3.1-8B-ArliAI-RPMax-v1.1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
Llama-3.1-8B-ArliAI-RPMax-v1.1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text
Llama-3.1-8B-ArliAI-RPMax-v1.1-f16.gguf filter=lfs diff=lfs merge=lfs -text
Llama-3.1-8B-ArliAI-RPMax-v1.1.imatrix filter=lfs diff=lfs merge=lfs -text

3
Llama-3.1-8B-ArliAI-RPMax-v1.1-IQ2_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:7dd476f05fd6e989fc5e23803fca86ef003bd62295e482d12f58b6d024193679
size 2948281440

3
Llama-3.1-8B-ArliAI-RPMax-v1.1-IQ3_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5f33b16f963b8b087e171a99f3345fd317064b7ac0b60b2417e9f53fb6d0be93
size 3784823904

3
Llama-3.1-8B-ArliAI-RPMax-v1.1-IQ3_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c37f4b81f8b50f97addda561a6ff7103aa76a0337c37cc0de2d831ee52aec63e
size 3518747744

3
Llama-3.1-8B-ArliAI-RPMax-v1.1-IQ4_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5053ab532805e788a7ae97c58d317efe065269f59ca2f0a2e77dbd4046bfa53b
size 4447663200

3
Llama-3.1-8B-ArliAI-RPMax-v1.1-Q2_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:413fd12929c5673e7924c3b7953c0645776c8d8a51594ecd70894ab77fe0e5cd
size 3179132000

3
Llama-3.1-8B-ArliAI-RPMax-v1.1-Q2_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:875353c72f5b11ff7ab77d192f71f2145fe275029dc32739028497906e815661
size 3692156000

3
Llama-3.1-8B-ArliAI-RPMax-v1.1-Q3_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:100160e1a6733e2ca65bf31276140462c27e1472c2ba7aaabe6e4a87d523b627
size 4321956960

3
Llama-3.1-8B-ArliAI-RPMax-v1.1-Q3_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:be504790cd24be99ee000bb39ebd92a711d54790162c0982fa54cc45d71b9627
size 4018918496

3
Llama-3.1-8B-ArliAI-RPMax-v1.1-Q3_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d08e3a6be353159a877f7ded59002b5cdd2be989e4c0f20dc61e07ed3b770b3a
size 3664499808

3
Llama-3.1-8B-ArliAI-RPMax-v1.1-Q3_K_XL.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:894f1be08a8b020e61d00164b795b2835a46cf5aae942cdebfc90fde772ac28c
size 4781626464

3
Llama-3.1-8B-ArliAI-RPMax-v1.1-Q4_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:6c1198b05dad4c2d610b3353202ddc0b9b742eef75961a7fefdbe0ae961b4d09
size 4675892320

3
Llama-3.1-8B-ArliAI-RPMax-v1.1-Q4_0_4_4.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:58a2a44e842b1a51fb23624d661d280f8d2b7ac3b596375ef65240a6c76c965e
size 4661212256

3
Llama-3.1-8B-ArliAI-RPMax-v1.1-Q4_0_4_8.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:98be04094d52a0000975ebc0952edeb5ce30816b5fd54818438cfce4854cba6b
size 4661212256

3
Llama-3.1-8B-ArliAI-RPMax-v1.1-Q4_0_8_8.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5f7e954fc74a27e5c2aceca96af129a1bbe1695250ce0c46ed32919e33bb75c5
size 4661212256

3
Llama-3.1-8B-ArliAI-RPMax-v1.1-Q4_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:eabe7c76d96e34c64fafa8a88a84dd6184d4d4035cb9a3de316b2e1f61cca194
size 5310633056

3
Llama-3.1-8B-ArliAI-RPMax-v1.1-Q4_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0a601c7341228d9160332965298d799369a1dc2b7080771fb8051bdeb556b30c
size 4920734816

3
Llama-3.1-8B-ArliAI-RPMax-v1.1-Q4_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e78a05e369b262b9ef01c11c8d27a88ebfb0e7213ede5f23b09c887a52d8a829
size 4692669536

3
Llama-3.1-8B-ArliAI-RPMax-v1.1-Q5_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:6355003d59fdbe63fdc0b860848aba402b50abbcebe7ac32df1de905fd11b823
size 6057219168

3
Llama-3.1-8B-ArliAI-RPMax-v1.1-Q5_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:96b25497b852476de34283d4dfcb0924b84d165c46d933f78e5b7ea1e92c4425
size 5732988000

3
Llama-3.1-8B-ArliAI-RPMax-v1.1-Q5_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:61fe724e3aa8f384108ec747826231b85df0a0ea5d593fd5f8d024960aebc719
size 5599294560

3
Llama-3.1-8B-ArliAI-RPMax-v1.1-Q6_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3d5854b7cd3864ddef62916d9926b54a21753f225f6149288e0ef3239ad9ed96
size 6596007008

3
Llama-3.1-8B-ArliAI-RPMax-v1.1-Q6_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3a2b1839b42964ad273c06df43a0ae48019a138fb51415fd42d3c8b70b996d86
size 6850466912

3
Llama-3.1-8B-ArliAI-RPMax-v1.1-Q8_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9cd3bc637decde961c777e4a6b5e02f06e70171ba39c897f9e0856b5b3191c21
size 8540771424

3
Llama-3.1-8B-ArliAI-RPMax-v1.1-f16.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:11fe4fc078754dabdff017e286d19cb3bc8ac99e3c9559aede28c6cbd4dc45b6
size 16068891424

3
Llama-3.1-8B-ArliAI-RPMax-v1.1.imatrix Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0d0f6d3da1b1ebfd2a21109350605994b9940fb7c535a4aef84ebcbc7cc4c822
size 4988170

125
README.md Normal file
View File

@@ -0,0 +1,125 @@
---
base_model: ArliAI/Llama-3.1-8B-ArliAI-RPMax-v1.1
license: llama3
pipeline_tag: text-generation
quantized_by: bartowski
---
## Llamacpp imatrix Quantizations of Llama-3.1-8B-ArliAI-RPMax-v1.1
Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b3715">b3715</a> for quantization.
Original model: https://huggingface.co/ArliAI/Llama-3.1-8B-ArliAI-RPMax-v1.1
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|>
{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-3.1-8B-ArliAI-RPMax-v1.1-f16.gguf](https://huggingface.co/bartowski/Llama-3.1-8B-ArliAI-RPMax-v1.1-GGUF/blob/main/Llama-3.1-8B-ArliAI-RPMax-v1.1-f16.gguf) | f16 | 16.07GB | false | Full F16 weights. |
| [Llama-3.1-8B-ArliAI-RPMax-v1.1-Q8_0.gguf](https://huggingface.co/bartowski/Llama-3.1-8B-ArliAI-RPMax-v1.1-GGUF/blob/main/Llama-3.1-8B-ArliAI-RPMax-v1.1-Q8_0.gguf) | Q8_0 | 8.54GB | false | Extremely high quality, generally unneeded but max available quant. |
| [Llama-3.1-8B-ArliAI-RPMax-v1.1-Q6_K_L.gguf](https://huggingface.co/bartowski/Llama-3.1-8B-ArliAI-RPMax-v1.1-GGUF/blob/main/Llama-3.1-8B-ArliAI-RPMax-v1.1-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-3.1-8B-ArliAI-RPMax-v1.1-Q6_K.gguf](https://huggingface.co/bartowski/Llama-3.1-8B-ArliAI-RPMax-v1.1-GGUF/blob/main/Llama-3.1-8B-ArliAI-RPMax-v1.1-Q6_K.gguf) | Q6_K | 6.60GB | false | Very high quality, near perfect, *recommended*. |
| [Llama-3.1-8B-ArliAI-RPMax-v1.1-Q5_K_L.gguf](https://huggingface.co/bartowski/Llama-3.1-8B-ArliAI-RPMax-v1.1-GGUF/blob/main/Llama-3.1-8B-ArliAI-RPMax-v1.1-Q5_K_L.gguf) | Q5_K_L | 6.06GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. |
| [Llama-3.1-8B-ArliAI-RPMax-v1.1-Q5_K_M.gguf](https://huggingface.co/bartowski/Llama-3.1-8B-ArliAI-RPMax-v1.1-GGUF/blob/main/Llama-3.1-8B-ArliAI-RPMax-v1.1-Q5_K_M.gguf) | Q5_K_M | 5.73GB | false | High quality, *recommended*. |
| [Llama-3.1-8B-ArliAI-RPMax-v1.1-Q5_K_S.gguf](https://huggingface.co/bartowski/Llama-3.1-8B-ArliAI-RPMax-v1.1-GGUF/blob/main/Llama-3.1-8B-ArliAI-RPMax-v1.1-Q5_K_S.gguf) | Q5_K_S | 5.60GB | false | High quality, *recommended*. |
| [Llama-3.1-8B-ArliAI-RPMax-v1.1-Q4_K_L.gguf](https://huggingface.co/bartowski/Llama-3.1-8B-ArliAI-RPMax-v1.1-GGUF/blob/main/Llama-3.1-8B-ArliAI-RPMax-v1.1-Q4_K_L.gguf) | Q4_K_L | 5.31GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. |
| [Llama-3.1-8B-ArliAI-RPMax-v1.1-Q4_K_M.gguf](https://huggingface.co/bartowski/Llama-3.1-8B-ArliAI-RPMax-v1.1-GGUF/blob/main/Llama-3.1-8B-ArliAI-RPMax-v1.1-Q4_K_M.gguf) | Q4_K_M | 4.92GB | false | Good quality, default size for must use cases, *recommended*. |
| [Llama-3.1-8B-ArliAI-RPMax-v1.1-Q3_K_XL.gguf](https://huggingface.co/bartowski/Llama-3.1-8B-ArliAI-RPMax-v1.1-GGUF/blob/main/Llama-3.1-8B-ArliAI-RPMax-v1.1-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-3.1-8B-ArliAI-RPMax-v1.1-Q4_K_S.gguf](https://huggingface.co/bartowski/Llama-3.1-8B-ArliAI-RPMax-v1.1-GGUF/blob/main/Llama-3.1-8B-ArliAI-RPMax-v1.1-Q4_K_S.gguf) | Q4_K_S | 4.69GB | false | Slightly lower quality with more space savings, *recommended*. |
| [Llama-3.1-8B-ArliAI-RPMax-v1.1-Q4_0.gguf](https://huggingface.co/bartowski/Llama-3.1-8B-ArliAI-RPMax-v1.1-GGUF/blob/main/Llama-3.1-8B-ArliAI-RPMax-v1.1-Q4_0.gguf) | Q4_0 | 4.68GB | false | Legacy format, generally not worth using over similarly sized formats |
| [Llama-3.1-8B-ArliAI-RPMax-v1.1-Q4_0_8_8.gguf](https://huggingface.co/bartowski/Llama-3.1-8B-ArliAI-RPMax-v1.1-GGUF/blob/main/Llama-3.1-8B-ArliAI-RPMax-v1.1-Q4_0_8_8.gguf) | Q4_0_8_8 | 4.66GB | false | Optimized for ARM inference. Requires 'sve' support (see link below). |
| [Llama-3.1-8B-ArliAI-RPMax-v1.1-Q4_0_4_8.gguf](https://huggingface.co/bartowski/Llama-3.1-8B-ArliAI-RPMax-v1.1-GGUF/blob/main/Llama-3.1-8B-ArliAI-RPMax-v1.1-Q4_0_4_8.gguf) | Q4_0_4_8 | 4.66GB | false | Optimized for ARM inference. Requires 'i8mm' support (see link below). |
| [Llama-3.1-8B-ArliAI-RPMax-v1.1-Q4_0_4_4.gguf](https://huggingface.co/bartowski/Llama-3.1-8B-ArliAI-RPMax-v1.1-GGUF/blob/main/Llama-3.1-8B-ArliAI-RPMax-v1.1-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. |
| [Llama-3.1-8B-ArliAI-RPMax-v1.1-IQ4_XS.gguf](https://huggingface.co/bartowski/Llama-3.1-8B-ArliAI-RPMax-v1.1-GGUF/blob/main/Llama-3.1-8B-ArliAI-RPMax-v1.1-IQ4_XS.gguf) | IQ4_XS | 4.45GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
| [Llama-3.1-8B-ArliAI-RPMax-v1.1-Q3_K_L.gguf](https://huggingface.co/bartowski/Llama-3.1-8B-ArliAI-RPMax-v1.1-GGUF/blob/main/Llama-3.1-8B-ArliAI-RPMax-v1.1-Q3_K_L.gguf) | Q3_K_L | 4.32GB | false | Lower quality but usable, good for low RAM availability. |
| [Llama-3.1-8B-ArliAI-RPMax-v1.1-Q3_K_M.gguf](https://huggingface.co/bartowski/Llama-3.1-8B-ArliAI-RPMax-v1.1-GGUF/blob/main/Llama-3.1-8B-ArliAI-RPMax-v1.1-Q3_K_M.gguf) | Q3_K_M | 4.02GB | false | Low quality. |
| [Llama-3.1-8B-ArliAI-RPMax-v1.1-IQ3_M.gguf](https://huggingface.co/bartowski/Llama-3.1-8B-ArliAI-RPMax-v1.1-GGUF/blob/main/Llama-3.1-8B-ArliAI-RPMax-v1.1-IQ3_M.gguf) | IQ3_M | 3.78GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
| [Llama-3.1-8B-ArliAI-RPMax-v1.1-Q2_K_L.gguf](https://huggingface.co/bartowski/Llama-3.1-8B-ArliAI-RPMax-v1.1-GGUF/blob/main/Llama-3.1-8B-ArliAI-RPMax-v1.1-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-3.1-8B-ArliAI-RPMax-v1.1-Q3_K_S.gguf](https://huggingface.co/bartowski/Llama-3.1-8B-ArliAI-RPMax-v1.1-GGUF/blob/main/Llama-3.1-8B-ArliAI-RPMax-v1.1-Q3_K_S.gguf) | Q3_K_S | 3.66GB | false | Low quality, not recommended. |
| [Llama-3.1-8B-ArliAI-RPMax-v1.1-IQ3_XS.gguf](https://huggingface.co/bartowski/Llama-3.1-8B-ArliAI-RPMax-v1.1-GGUF/blob/main/Llama-3.1-8B-ArliAI-RPMax-v1.1-IQ3_XS.gguf) | IQ3_XS | 3.52GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
| [Llama-3.1-8B-ArliAI-RPMax-v1.1-Q2_K.gguf](https://huggingface.co/bartowski/Llama-3.1-8B-ArliAI-RPMax-v1.1-GGUF/blob/main/Llama-3.1-8B-ArliAI-RPMax-v1.1-Q2_K.gguf) | Q2_K | 3.18GB | false | Very low quality but surprisingly usable. |
| [Llama-3.1-8B-ArliAI-RPMax-v1.1-IQ2_M.gguf](https://huggingface.co/bartowski/Llama-3.1-8B-ArliAI-RPMax-v1.1-GGUF/blob/main/Llama-3.1-8B-ArliAI-RPMax-v1.1-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-3.1-8B-ArliAI-RPMax-v1.1-GGUF --include "Llama-3.1-8B-ArliAI-RPMax-v1.1-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-3.1-8B-ArliAI-RPMax-v1.1-GGUF --include "Llama-3.1-8B-ArliAI-RPMax-v1.1-Q8_0/*" --local-dir ./
```
You can either specify a new local-dir (Llama-3.1-8B-ArliAI-RPMax-v1.1-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}