bartowski/LiquidAI_LFM2.5-1.2B-Instruct-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_LFM2.5-1.2B-Instruct-GGUF
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-07-19 20:56:06 +08:00
commit 53a462465a
28 changed files with 342 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_LFM2.5-1.2B-Instruct-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
LiquidAI_LFM2.5-1.2B-Instruct-bf16.gguf filter=lfs diff=lfs merge=lfs -text
LiquidAI_LFM2.5-1.2B-Instruct-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text
LiquidAI_LFM2.5-1.2B-Instruct-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
LiquidAI_LFM2.5-1.2B-Instruct-Q4_K_L.gguf filter=lfs diff=lfs merge=lfs -text
LiquidAI_LFM2.5-1.2B-Instruct-Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text
LiquidAI_LFM2.5-1.2B-Instruct-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text
LiquidAI_LFM2.5-1.2B-Instruct-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
LiquidAI_LFM2.5-1.2B-Instruct-Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
LiquidAI_LFM2.5-1.2B-Instruct-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
LiquidAI_LFM2.5-1.2B-Instruct-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text
LiquidAI_LFM2.5-1.2B-Instruct-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
LiquidAI_LFM2.5-1.2B-Instruct-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
LiquidAI_LFM2.5-1.2B-Instruct-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
LiquidAI_LFM2.5-1.2B-Instruct-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
LiquidAI_LFM2.5-1.2B-Instruct-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text
LiquidAI_LFM2.5-1.2B-Instruct-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
LiquidAI_LFM2.5-1.2B-Instruct-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
LiquidAI_LFM2.5-1.2B-Instruct-imatrix.gguf filter=lfs diff=lfs merge=lfs -text
LiquidAI_LFM2.5-1.2B-Instruct-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
LiquidAI_LFM2.5-1.2B-Instruct-Q5_K_L.gguf filter=lfs diff=lfs merge=lfs -text
LiquidAI_LFM2.5-1.2B-Instruct-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
LiquidAI_LFM2.5-1.2B-Instruct-Q6_K_L.gguf filter=lfs diff=lfs merge=lfs -text
LiquidAI_LFM2.5-1.2B-Instruct-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
LiquidAI_LFM2.5-1.2B-Instruct-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text

3
LiquidAI_LFM2.5-1.2B-Instruct-IQ2_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:21bd4c41928b378578501bd4b85b3fdd643420cd605e9b2ddba036d88517904f
size 434132320

3
LiquidAI_LFM2.5-1.2B-Instruct-IQ3_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:84b10224c2d57f738d2693260da5988a39fad174330d2921d5702b371452deca
size 566793568

3
LiquidAI_LFM2.5-1.2B-Instruct-IQ3_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:54256819b3b96864c8e2fb22d56ae17284ac23ea58526f9b8332cca48f4c0d4f
size 537810272

3
LiquidAI_LFM2.5-1.2B-Instruct-IQ3_XXS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c6ddfe2cf991cea6aca304b3a73019d0d83e2a186fdcd0c47c11f6c30845e9c6
size 490984800

3
LiquidAI_LFM2.5-1.2B-Instruct-IQ4_NL.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:fd0eca2e29e6b6cd00166d2434d3a18acdff07c7b90a70c417d3756ff492df4f
size 695752032

3
LiquidAI_LFM2.5-1.2B-Instruct-IQ4_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a310da4b2d5b0604d182a30157fba22c3fe2084c8c0499e9d0bc44bb9feea115
size 663377248

3
LiquidAI_LFM2.5-1.2B-Instruct-Q2_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b6bd453f21801b3ccc703687b8f2b6e61d8bc5af699fe2c97cdce7b3871e81e8
size 483399008

3
LiquidAI_LFM2.5-1.2B-Instruct-Q2_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:35451a37110064bbb2d8e0a84571005712826c9b2c753b95e8e16b54071ed8ac
size 515904864

3
LiquidAI_LFM2.5-1.2B-Instruct-Q3_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:4a68b55c3f9e4d281f4cb728f39de1f84482ceb4a7f88ac4e3c04e595fe8799b
size 635475296

3
LiquidAI_LFM2.5-1.2B-Instruct-Q3_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:95d09f0fbb0c0ad34e0ff48c8c8dd497b4b500c030445779c8cd7d9e1bcafd8f
size 600348000

3
LiquidAI_LFM2.5-1.2B-Instruct-Q3_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:be5afdb68ac0ccaf218225b28dd3ee80686e01f328d3f9a95660197f339b68fe
size 558159200

3
LiquidAI_LFM2.5-1.2B-Instruct-Q3_K_XL.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:7bab2821aae5898d3be43d9a6f8281b3390e6c7b7e41a852dd185f802f5e7e57
size 667981152

3
LiquidAI_LFM2.5-1.2B-Instruct-Q4_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:7bbc363613e2c47a7c33ca001dd9190009417d9bebadd07b98bdcf4aa0f5553b
size 697849184

3
LiquidAI_LFM2.5-1.2B-Instruct-Q4_1.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:177e6b8bb0630ea35561f18d2844acacc80ac929fbd17e6deb6950191cf3a128
size 760501600

3
LiquidAI_LFM2.5-1.2B-Instruct-Q4_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e424c25257fdf7bdc6507d6e2b82ba7a6d4668c9f16aea2531c459f671a66482
size 763401568

3
LiquidAI_LFM2.5-1.2B-Instruct-Q4_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:baaf531531f397456e46b89554fd66f30ec84b57d5b0cfd6365785cd3db12a97
size 730895712

3
LiquidAI_LFM2.5-1.2B-Instruct-Q4_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a35bd1bcf1839b8e7a6ed7f8bb85a98340286f57144cb160963a74c86752bc91
size 700470624

3
LiquidAI_LFM2.5-1.2B-Instruct-Q5_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0ab109acbc6615b21a9a689e8df8fd0bca93bb12d03ea85a4da4134d3b6970f3
size 875861344

3
LiquidAI_LFM2.5-1.2B-Instruct-Q5_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9c679b8a8c1855937d38d643479384eeaa4ba7d3a5014c0417382fdf4f362509
size 843355488

3
LiquidAI_LFM2.5-1.2B-Instruct-Q5_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:30008e5b2ec8660f9c3d405bf9c3349ab9892721916e3a5fe4ce2d75417a9b8a
size 825251168

3
LiquidAI_LFM2.5-1.2B-Instruct-Q6_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:00334bb7ac776739b1a1167be31f8b57002ca5033b05c67eecb164d43b7d6e2a
size 962844000

3
LiquidAI_LFM2.5-1.2B-Instruct-Q6_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:bdffc7eaacf9de13e993904c9965235070173f530bf536e27a5f7ba9c3459100
size 995349856

3
LiquidAI_LFM2.5-1.2B-Instruct-Q8_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:85d94fbe158d173444ad2b95c4c90845784ec04a0c918190aa029e3c4fc2e42f
size 1246254432

3
LiquidAI_LFM2.5-1.2B-Instruct-bf16.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:800ce028a8b3af993c1292ffbd781904cdc18d7a2514d75de807ca668dabb662
size 2343326784

3
LiquidAI_LFM2.5-1.2B-Instruct-imatrix.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ecf6afd3f20515f1acb013ac2e5a0d53a6d5803a0479109fa0d756e2ed87f59c
size 1161536

193
README.md Normal file
View File

@@ -0,0 +1,193 @@
---
quantized_by: bartowski
pipeline_tag: text-generation
license_link: LICENSE
license_name: lfm1.0
tags:
- liquid
- lfm2.5
- edge
base_model_relation: quantized
base_model: LiquidAI/LFM2.5-1.2B-Instruct
license: other
language:
- en
- ar
- zh
- fr
- de
- ja
- ko
- es
---
## Llamacpp imatrix Quantizations of LFM2.5-1.2B-Instruct 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/b7610">b7610</a> for quantization.
Original model: https://huggingface.co/LiquidAI/LFM2.5-1.2B-Instruct
All quants made using imatrix option with dataset from [here](https://gist.github.com/bartowski1182/82ae9b520227f57d79ba04add13d0d0d)
Run them in your choice of tools:
- [llama.cpp](https://github.com/ggml-org/llama.cpp)
- [LM Studio](https://lmstudio.ai/)
- [koboldcpp](https://github.com/LostRuins/koboldcpp)
- [Jan AI](https://www.jan.ai/)
- [Text Generation Web UI](https://github.com/oobabooga/text-generation-webui)
- [LoLLMs](https://github.com/ParisNeo/lollms)
Note: if it's a newly supported model, you may need to wait for an update from the developers.
## Prompt format
```
<|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 |
| -------- | ---------- | --------- | ----- | ----------- |
| [LFM2.5-1.2B-Instruct-bf16.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2.5-1.2B-Instruct-GGUF/blob/main/LiquidAI_LFM2.5-1.2B-Instruct-bf16.gguf) | bf16 | 2.34GB | false | Full BF16 weights. |
| [LFM2.5-1.2B-Instruct-Q8_0.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2.5-1.2B-Instruct-GGUF/blob/main/LiquidAI_LFM2.5-1.2B-Instruct-Q8_0.gguf) | Q8_0 | 1.25GB | false | Extremely high quality, generally unneeded but max available quant. |
| [LFM2.5-1.2B-Instruct-Q6_K_L.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2.5-1.2B-Instruct-GGUF/blob/main/LiquidAI_LFM2.5-1.2B-Instruct-Q6_K_L.gguf) | Q6_K_L | 1.00GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. |
| [LFM2.5-1.2B-Instruct-Q6_K.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2.5-1.2B-Instruct-GGUF/blob/main/LiquidAI_LFM2.5-1.2B-Instruct-Q6_K.gguf) | Q6_K | 0.96GB | false | Very high quality, near perfect, *recommended*. |
| [LFM2.5-1.2B-Instruct-Q5_K_L.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2.5-1.2B-Instruct-GGUF/blob/main/LiquidAI_LFM2.5-1.2B-Instruct-Q5_K_L.gguf) | Q5_K_L | 0.88GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. |
| [LFM2.5-1.2B-Instruct-Q5_K_M.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2.5-1.2B-Instruct-GGUF/blob/main/LiquidAI_LFM2.5-1.2B-Instruct-Q5_K_M.gguf) | Q5_K_M | 0.84GB | false | High quality, *recommended*. |
| [LFM2.5-1.2B-Instruct-Q5_K_S.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2.5-1.2B-Instruct-GGUF/blob/main/LiquidAI_LFM2.5-1.2B-Instruct-Q5_K_S.gguf) | Q5_K_S | 0.83GB | false | High quality, *recommended*. |
| [LFM2.5-1.2B-Instruct-Q4_K_L.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2.5-1.2B-Instruct-GGUF/blob/main/LiquidAI_LFM2.5-1.2B-Instruct-Q4_K_L.gguf) | Q4_K_L | 0.76GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. |
| [LFM2.5-1.2B-Instruct-Q4_1.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2.5-1.2B-Instruct-GGUF/blob/main/LiquidAI_LFM2.5-1.2B-Instruct-Q4_1.gguf) | Q4_1 | 0.76GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. |
| [LFM2.5-1.2B-Instruct-Q4_K_M.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2.5-1.2B-Instruct-GGUF/blob/main/LiquidAI_LFM2.5-1.2B-Instruct-Q4_K_M.gguf) | Q4_K_M | 0.73GB | false | Good quality, default size for most use cases, *recommended*. |
| [LFM2.5-1.2B-Instruct-Q4_K_S.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2.5-1.2B-Instruct-GGUF/blob/main/LiquidAI_LFM2.5-1.2B-Instruct-Q4_K_S.gguf) | Q4_K_S | 0.70GB | false | Slightly lower quality with more space savings, *recommended*. |
| [LFM2.5-1.2B-Instruct-Q4_0.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2.5-1.2B-Instruct-GGUF/blob/main/LiquidAI_LFM2.5-1.2B-Instruct-Q4_0.gguf) | Q4_0 | 0.70GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. |
| [LFM2.5-1.2B-Instruct-IQ4_NL.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2.5-1.2B-Instruct-GGUF/blob/main/LiquidAI_LFM2.5-1.2B-Instruct-IQ4_NL.gguf) | IQ4_NL | 0.70GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. |
| [LFM2.5-1.2B-Instruct-Q3_K_XL.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2.5-1.2B-Instruct-GGUF/blob/main/LiquidAI_LFM2.5-1.2B-Instruct-Q3_K_XL.gguf) | Q3_K_XL | 0.67GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. |
| [LFM2.5-1.2B-Instruct-IQ4_XS.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2.5-1.2B-Instruct-GGUF/blob/main/LiquidAI_LFM2.5-1.2B-Instruct-IQ4_XS.gguf) | IQ4_XS | 0.66GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
| [LFM2.5-1.2B-Instruct-Q3_K_L.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2.5-1.2B-Instruct-GGUF/blob/main/LiquidAI_LFM2.5-1.2B-Instruct-Q3_K_L.gguf) | Q3_K_L | 0.64GB | false | Lower quality but usable, good for low RAM availability. |
| [LFM2.5-1.2B-Instruct-Q3_K_M.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2.5-1.2B-Instruct-GGUF/blob/main/LiquidAI_LFM2.5-1.2B-Instruct-Q3_K_M.gguf) | Q3_K_M | 0.60GB | false | Low quality. |
| [LFM2.5-1.2B-Instruct-IQ3_M.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2.5-1.2B-Instruct-GGUF/blob/main/LiquidAI_LFM2.5-1.2B-Instruct-IQ3_M.gguf) | IQ3_M | 0.57GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
| [LFM2.5-1.2B-Instruct-Q3_K_S.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2.5-1.2B-Instruct-GGUF/blob/main/LiquidAI_LFM2.5-1.2B-Instruct-Q3_K_S.gguf) | Q3_K_S | 0.56GB | false | Low quality, not recommended. |
| [LFM2.5-1.2B-Instruct-IQ3_XS.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2.5-1.2B-Instruct-GGUF/blob/main/LiquidAI_LFM2.5-1.2B-Instruct-IQ3_XS.gguf) | IQ3_XS | 0.54GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
| [LFM2.5-1.2B-Instruct-Q2_K_L.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2.5-1.2B-Instruct-GGUF/blob/main/LiquidAI_LFM2.5-1.2B-Instruct-Q2_K_L.gguf) | Q2_K_L | 0.52GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. |
| [LFM2.5-1.2B-Instruct-IQ3_XXS.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2.5-1.2B-Instruct-GGUF/blob/main/LiquidAI_LFM2.5-1.2B-Instruct-IQ3_XXS.gguf) | IQ3_XXS | 0.49GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. |
| [LFM2.5-1.2B-Instruct-Q2_K.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2.5-1.2B-Instruct-GGUF/blob/main/LiquidAI_LFM2.5-1.2B-Instruct-Q2_K.gguf) | Q2_K | 0.48GB | false | Very low quality but surprisingly usable. |
| [LFM2.5-1.2B-Instruct-IQ2_M.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2.5-1.2B-Instruct-GGUF/blob/main/LiquidAI_LFM2.5-1.2B-Instruct-IQ2_M.gguf) | IQ2_M | 0.43GB | 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_LFM2.5-1.2B-Instruct-GGUF --include "LiquidAI_LFM2.5-1.2B-Instruct-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_LFM2.5-1.2B-Instruct-GGUF --include "LiquidAI_LFM2.5-1.2B-Instruct-Q8_0/*" --local-dir ./
```
You can either specify a new local-dir (LiquidAI_LFM2.5-1.2B-Instruct-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}