bartowski/LiquidAI_LFM2-8B-A1B-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/LiquidAI_LFM2-8B-A1B-GGUF
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-07-23 09:32:06 +08:00
commit c627a18de3
28 changed files with 321 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

73
.gitattributes vendored Normal file
View File

@@ -0,0 +1,73 @@
*.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
*.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
LiquidAI_LFM2-8B-A1B-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text
LiquidAI_LFM2-8B-A1B-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
LiquidAI_LFM2-8B-A1B-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
LiquidAI_LFM2-8B-A1B-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
LiquidAI_LFM2-8B-A1B-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
LiquidAI_LFM2-8B-A1B-imatrix.gguf filter=lfs diff=lfs merge=lfs -text
LiquidAI_LFM2-8B-A1B-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text
LiquidAI_LFM2-8B-A1B-Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
LiquidAI_LFM2-8B-A1B-Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text
LiquidAI_LFM2-8B-A1B-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
LiquidAI_LFM2-8B-A1B-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
LiquidAI_LFM2-8B-A1B-Q4_K_L.gguf filter=lfs diff=lfs merge=lfs -text
LiquidAI_LFM2-8B-A1B-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
LiquidAI_LFM2-8B-A1B-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
LiquidAI_LFM2-8B-A1B-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
LiquidAI_LFM2-8B-A1B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
LiquidAI_LFM2-8B-A1B-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text
LiquidAI_LFM2-8B-A1B-bf16.gguf filter=lfs diff=lfs merge=lfs -text
LiquidAI_LFM2-8B-A1B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
LiquidAI_LFM2-8B-A1B-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
LiquidAI_LFM2-8B-A1B-Q6_K_L.gguf filter=lfs diff=lfs merge=lfs -text
LiquidAI_LFM2-8B-A1B-Q5_K_L.gguf filter=lfs diff=lfs merge=lfs -text
LiquidAI_LFM2-8B-A1B-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
LiquidAI_LFM2-8B-A1B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
LiquidAI_LFM2-8B-A1B-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text

3
LiquidAI_LFM2-8B-A1B-IQ2_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b95448d7f31a12736fbf91b081f839ff4074d8bd21bbdfc494b54bd64841dede
size 2650602432

3
LiquidAI_LFM2-8B-A1B-IQ3_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:7fb4705e813c7e0b6a3814c94f8bd13c30f751ba9d806fd368022168270884e2
size 3815472064

3
LiquidAI_LFM2-8B-A1B-IQ3_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c20f3f96e01d40547bb8e81b73596aafa770b2a1d654fdd2e0ba675c8e3f08cf
size 3455400896

3
LiquidAI_LFM2-8B-A1B-IQ3_XXS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9916185bffb1d4b7d109e7c4cb65cf3de312b8d2b0d5ab49929e4c98de47cfad
size 3307322304

3
LiquidAI_LFM2-8B-A1B-IQ4_NL.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:454bdeaa30f1520e00b6113d85a3051950df5d3aa5eb7ace4c3b09dc0089eaba
size 4740185024

3
LiquidAI_LFM2-8B-A1B-IQ4_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ea3b93fb618d0def7bb702c100c05924ab5b7cd631c3cfdccefd5dfa2c73ba06
size 4484791232

3
LiquidAI_LFM2-8B-A1B-Q2_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2c5ca2740a85b8e4e052d416818550204ea90e5b07c358a189994a64347e549c
size 2947627968

3
LiquidAI_LFM2-8B-A1B-Q2_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:35b58aa042b2d3f512de73a56de101065c2d161be0b29cd63d17cf1a0e785e43
size 2980133824

3
LiquidAI_LFM2-8B-A1B-Q3_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:20646b5c085b4722135566633f941484a3e6535ca5344a656020cd6dddde65f6
size 3960241088

3
LiquidAI_LFM2-8B-A1B-Q3_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f4069ab6aa215d15ff151bc02471b95664575967383d0d097ac2e34cb1685144
size 3817569216

3
LiquidAI_LFM2-8B-A1B-Q3_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:84dd851ceef226f6d523416c1634e64d22ccdf4f4f52d40e1b0f7b4f072c83aa
size 3654761408

3
LiquidAI_LFM2-8B-A1B-Q3_K_XL.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9af4f52a7a29d0cb9a9fae3dc86e76e85938a8ec9bd1c19d7a1ffabf9c9d1301
size 3992746944

3
LiquidAI_LFM2-8B-A1B-Q4_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:382d8b20813803f82209810cbdf562f4391bf70e3c0324d86b9088f4954352cb
size 4812274624

3
LiquidAI_LFM2-8B-A1B-Q4_1.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ca0000439d19ca188a34fda75b91bf087c0d90a18db5a79eeb43283f816e8d81
size 5249399744

3
LiquidAI_LFM2-8B-A1B-Q4_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:be475ac67025430fff3ba5d46a123f8c47c1b20628924fcc95c6460444dbb8dd
size 5083577280

3
LiquidAI_LFM2-8B-A1B-Q4_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:efb59182eca2424126e9f8bde8513a1736e92d3b9a3187a2afc67968bd44512a
size 5051071424

3
LiquidAI_LFM2-8B-A1B-Q4_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a9205a193e65c8f5f8f18ba1f4206adec5e98d097768f24230b2719a2d24ea0e
size 4891179968

3
LiquidAI_LFM2-8B-A1B-Q5_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:be7507dcb97630c964ec1cf92330c7245b5cd80bc669069352e1362a7d3a34c7
size 5954419648

3
LiquidAI_LFM2-8B-A1B-Q5_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:44b1ef132884fc890d21881d292e0d95c0f9d7920c391c57a2e292e1537819a2
size 5921913792

3
LiquidAI_LFM2-8B-A1B-Q5_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ca87c8106ab9dca8c9e6af0d82a414f5f8aee1da4eb429402ad7270511b92914
size 5761760192

3
LiquidAI_LFM2-8B-A1B-Q6_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:169ea61e8bfcdb3539e5a946ca3787e0d94d26f76d39a370b41ad4d0c87a73ee
size 6850526144

3
LiquidAI_LFM2-8B-A1B-Q6_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e4dc498edf024f3866fca51236fef4371a18fa1d54383d6e29f51891523e0d55
size 6883032000

3
LiquidAI_LFM2-8B-A1B-Q8_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ac7cf13235b2f2b00387cc4e91d1085137fe23b5552991f352fbfefac6c6ddf5
size 8868428736

3
LiquidAI_LFM2-8B-A1B-bf16.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b71d63488b8aceac56c91bf641ab48160459c576ec506a472289eba66ad8074c
size 16685562560

3
LiquidAI_LFM2-8B-A1B-imatrix.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:fb7ccf3855d1cbcbda25ded6228465ab79689804dfb67f0f5431acffb3d105c7
size 17375232

172
README.md Normal file
View File

@@ -0,0 +1,172 @@
---
quantized_by: bartowski
pipeline_tag: text-generation
base_model: LiquidAI/LFM2-8B-A1B
base_model_relation: quantized
---
## Llamacpp imatrix Quantizations of LFM2-8B-A1B by LiquidAI
Using <a href="https://github.com/ggml-org/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggml-org/llama.cpp/releases/tag/b6714">b6714</a> for quantization.
Original model: https://huggingface.co/LiquidAI/LFM2-8B-A1B
All quants made using imatrix option with dataset from [here](https://gist.github.com/bartowski1182/eb213dccb3571f863da82e99418f81e8) combined with a subset of combined_all_small.parquet from Ed Addario [here](https://huggingface.co/datasets/eaddario/imatrix-calibration/blob/main/combined_all_small.parquet)
Run them in [LM Studio](https://lmstudio.ai/)
Run them directly with [llama.cpp](https://github.com/ggml-org/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.
```
<|startoftext|><|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 |
| -------- | ---------- | --------- | ----- | ----------- |
| [LFM2-8B-A1B-bf16.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-8B-A1B-GGUF/blob/main/LiquidAI_LFM2-8B-A1B-bf16.gguf) | bf16 | 16.69GB | false | Full BF16 weights. |
| [LFM2-8B-A1B-Q8_0.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-8B-A1B-GGUF/blob/main/LiquidAI_LFM2-8B-A1B-Q8_0.gguf) | Q8_0 | 8.87GB | false | Extremely high quality, generally unneeded but max available quant. |
| [LFM2-8B-A1B-Q6_K_L.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-8B-A1B-GGUF/blob/main/LiquidAI_LFM2-8B-A1B-Q6_K_L.gguf) | Q6_K_L | 6.88GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. |
| [LFM2-8B-A1B-Q6_K.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-8B-A1B-GGUF/blob/main/LiquidAI_LFM2-8B-A1B-Q6_K.gguf) | Q6_K | 6.85GB | false | Very high quality, near perfect, *recommended*. |
| [LFM2-8B-A1B-Q5_K_L.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-8B-A1B-GGUF/blob/main/LiquidAI_LFM2-8B-A1B-Q5_K_L.gguf) | Q5_K_L | 5.95GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. |
| [LFM2-8B-A1B-Q5_K_M.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-8B-A1B-GGUF/blob/main/LiquidAI_LFM2-8B-A1B-Q5_K_M.gguf) | Q5_K_M | 5.92GB | false | High quality, *recommended*. |
| [LFM2-8B-A1B-Q5_K_S.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-8B-A1B-GGUF/blob/main/LiquidAI_LFM2-8B-A1B-Q5_K_S.gguf) | Q5_K_S | 5.76GB | false | High quality, *recommended*. |
| [LFM2-8B-A1B-Q4_1.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-8B-A1B-GGUF/blob/main/LiquidAI_LFM2-8B-A1B-Q4_1.gguf) | Q4_1 | 5.25GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. |
| [LFM2-8B-A1B-Q4_K_L.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-8B-A1B-GGUF/blob/main/LiquidAI_LFM2-8B-A1B-Q4_K_L.gguf) | Q4_K_L | 5.08GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. |
| [LFM2-8B-A1B-Q4_K_M.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-8B-A1B-GGUF/blob/main/LiquidAI_LFM2-8B-A1B-Q4_K_M.gguf) | Q4_K_M | 5.05GB | false | Good quality, default size for most use cases, *recommended*. |
| [LFM2-8B-A1B-Q4_K_S.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-8B-A1B-GGUF/blob/main/LiquidAI_LFM2-8B-A1B-Q4_K_S.gguf) | Q4_K_S | 4.89GB | false | Slightly lower quality with more space savings, *recommended*. |
| [LFM2-8B-A1B-Q4_0.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-8B-A1B-GGUF/blob/main/LiquidAI_LFM2-8B-A1B-Q4_0.gguf) | Q4_0 | 4.81GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. |
| [LFM2-8B-A1B-IQ4_NL.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-8B-A1B-GGUF/blob/main/LiquidAI_LFM2-8B-A1B-IQ4_NL.gguf) | IQ4_NL | 4.74GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. |
| [LFM2-8B-A1B-IQ4_XS.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-8B-A1B-GGUF/blob/main/LiquidAI_LFM2-8B-A1B-IQ4_XS.gguf) | IQ4_XS | 4.48GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
| [LFM2-8B-A1B-Q3_K_XL.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-8B-A1B-GGUF/blob/main/LiquidAI_LFM2-8B-A1B-Q3_K_XL.gguf) | Q3_K_XL | 3.99GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. |
| [LFM2-8B-A1B-Q3_K_L.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-8B-A1B-GGUF/blob/main/LiquidAI_LFM2-8B-A1B-Q3_K_L.gguf) | Q3_K_L | 3.96GB | false | Lower quality but usable, good for low RAM availability. |
| [LFM2-8B-A1B-Q3_K_M.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-8B-A1B-GGUF/blob/main/LiquidAI_LFM2-8B-A1B-Q3_K_M.gguf) | Q3_K_M | 3.82GB | false | Low quality. |
| [LFM2-8B-A1B-IQ3_M.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-8B-A1B-GGUF/blob/main/LiquidAI_LFM2-8B-A1B-IQ3_M.gguf) | IQ3_M | 3.82GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
| [LFM2-8B-A1B-Q3_K_S.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-8B-A1B-GGUF/blob/main/LiquidAI_LFM2-8B-A1B-Q3_K_S.gguf) | Q3_K_S | 3.65GB | false | Low quality, not recommended. |
| [LFM2-8B-A1B-IQ3_XS.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-8B-A1B-GGUF/blob/main/LiquidAI_LFM2-8B-A1B-IQ3_XS.gguf) | IQ3_XS | 3.46GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
| [LFM2-8B-A1B-IQ3_XXS.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-8B-A1B-GGUF/blob/main/LiquidAI_LFM2-8B-A1B-IQ3_XXS.gguf) | IQ3_XXS | 3.31GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. |
| [LFM2-8B-A1B-Q2_K_L.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-8B-A1B-GGUF/blob/main/LiquidAI_LFM2-8B-A1B-Q2_K_L.gguf) | Q2_K_L | 2.98GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. |
| [LFM2-8B-A1B-Q2_K.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-8B-A1B-GGUF/blob/main/LiquidAI_LFM2-8B-A1B-Q2_K.gguf) | Q2_K | 2.95GB | false | Very low quality but surprisingly usable. |
| [LFM2-8B-A1B-IQ2_M.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-8B-A1B-GGUF/blob/main/LiquidAI_LFM2-8B-A1B-IQ2_M.gguf) | IQ2_M | 2.65GB | 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.
## 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/LiquidAI_LFM2-8B-A1B-GGUF --include "LiquidAI_LFM2-8B-A1B-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/LiquidAI_LFM2-8B-A1B-GGUF --include "LiquidAI_LFM2-8B-A1B-Q8_0/*" --local-dir ./
```
You can either specify a new local-dir (LiquidAI_LFM2-8B-A1B-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/ggml-org/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/ggml-org/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/ggml-org/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/ggml-org/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}