bartowski/FuseChat-Llama-3.2-1B-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/FuseChat-Llama-3.2-1B-Instruct-GGUF
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-08-06 05:55:12 +08:00
commit d6a2e7a898
30 changed files with 314 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

62
.gitattributes vendored Normal file
View File

@@ -0,0 +1,62 @@
*.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
FuseChat-Llama-3.2-1B-Instruct-f16.gguf filter=lfs diff=lfs merge=lfs -text
FuseChat-Llama-3.2-1B-Instruct-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
FuseChat-Llama-3.2-1B-Instruct-Q6_K_L.gguf filter=lfs diff=lfs merge=lfs -text
FuseChat-Llama-3.2-1B-Instruct-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
FuseChat-Llama-3.2-1B-Instruct-Q5_K_L.gguf filter=lfs diff=lfs merge=lfs -text
FuseChat-Llama-3.2-1B-Instruct-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
FuseChat-Llama-3.2-1B-Instruct-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
FuseChat-Llama-3.2-1B-Instruct-Q4_K_L.gguf filter=lfs diff=lfs merge=lfs -text
FuseChat-Llama-3.2-1B-Instruct-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
FuseChat-Llama-3.2-1B-Instruct-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
FuseChat-Llama-3.2-1B-Instruct-Q4_0_8_8.gguf filter=lfs diff=lfs merge=lfs -text
FuseChat-Llama-3.2-1B-Instruct-Q4_0_4_8.gguf filter=lfs diff=lfs merge=lfs -text
FuseChat-Llama-3.2-1B-Instruct-Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text
FuseChat-Llama-3.2-1B-Instruct-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
FuseChat-Llama-3.2-1B-Instruct-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text
FuseChat-Llama-3.2-1B-Instruct-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
FuseChat-Llama-3.2-1B-Instruct-Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
FuseChat-Llama-3.2-1B-Instruct-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
FuseChat-Llama-3.2-1B-Instruct-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
FuseChat-Llama-3.2-1B-Instruct-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
FuseChat-Llama-3.2-1B-Instruct-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
FuseChat-Llama-3.2-1B-Instruct-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
FuseChat-Llama-3.2-1B-Instruct-Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text
FuseChat-Llama-3.2-1B-Instruct-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
FuseChat-Llama-3.2-1B-Instruct-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text
FuseChat-Llama-3.2-1B-Instruct-f32.gguf filter=lfs diff=lfs merge=lfs -text
FuseChat-Llama-3.2-1B-Instruct.imatrix filter=lfs diff=lfs merge=lfs -text

3
FuseChat-Llama-3.2-1B-Instruct-IQ2_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1c9ad404ea4b677dc794d4a944602365b1ad7592d0b00758ec3711f6dad8fca7
size 515445312

3
FuseChat-Llama-3.2-1B-Instruct-IQ3_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:438693ef74cd7a1a3fef4f68f09be1e57bd934b7667ca79ec8e8c5c8ee786ec8
size 657285696

3
FuseChat-Llama-3.2-1B-Instruct-IQ3_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2af3339a1cce440d504bf470e2bf4cce1d6569a5eedd3ba5f8ea7df3f93c972b
size 621109824

3
FuseChat-Llama-3.2-1B-Instruct-IQ4_NL.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:181833826cefe41e88102b11782b5ebdd554080c45524d22330ba9b5cc9b7578
size 773022272

3
FuseChat-Llama-3.2-1B-Instruct-IQ4_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:94edda85876a2f619c4142311c61b450b4cc87532b07286fa45725a2011ae2e3
size 743137856

3
FuseChat-Llama-3.2-1B-Instruct-Q2_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:eb8f84610c581a52009b01aefaf9e16212d61d1e160598ebb9a69d8d0e0051db
size 580870720

3
FuseChat-Llama-3.2-1B-Instruct-Q2_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b39e6dd449de11202d164840fd6fdaeb04ef45035e45f16eb3ab516253476467
size 644485696

3
FuseChat-Llama-3.2-1B-Instruct-Q3_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:526b4fe26a5b94a88840e87a9ecc006b819441650da7fbfff1d35c1799546542
size 732521024

3
FuseChat-Llama-3.2-1B-Instruct-Q3_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:8ec43b1c251047bc809e0cdf338fe4f7f0a7a5018148fd7ee06e1ee94be4cd34
size 690840128

3
FuseChat-Llama-3.2-1B-Instruct-Q3_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:640677a40f15f3aab670a51eb10ef3d2d2d516f0842bffc96a7cb3f59e3d0ed5
size 641688128

3
FuseChat-Llama-3.2-1B-Instruct-Q3_K_XL.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:fcbe84701769d2b3702cabddc074b25c8ba911cbbaa3740d3c3bf5dc022c55f4
size 796136000

3
FuseChat-Llama-3.2-1B-Instruct-Q4_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:6430d9d3d017a13d2613fe56aee847aebb03729d8ea09d40521ad14dd8db05c0
size 773022272

3
FuseChat-Llama-3.2-1B-Instruct-Q4_0_4_4.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9b5f0a1640dc6fb917dff268edbec21628d7f69bd4c3ecbe05e8484068a0f4f5
size 770925120

3
FuseChat-Llama-3.2-1B-Instruct-Q4_0_4_8.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:7cea3e11cbaf0ccd2593f60800b9ef6f48aab0a6a67383f24e6483a9a31899df
size 770925120

3
FuseChat-Llama-3.2-1B-Instruct-Q4_0_8_8.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:437d267f03b1c1f77f0470e822024f7e5e7aeb119de0e1a2e42e6f3713602e93
size 770925120

3
FuseChat-Llama-3.2-1B-Instruct-Q4_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:4dc56302a577e75b2d51d7998c576e12874907b7a1ac63a577dcbef073f63b4a
size 871305792

3
FuseChat-Llama-3.2-1B-Instruct-Q4_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:8bcd46580c2eb069fde82b4c16f8f2981901d653fea1340ec560b6097f08f97a
size 807690816

3
FuseChat-Llama-3.2-1B-Instruct-Q4_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:264ddbee0d791afab8c8a1cbc995333db8b07e0e8396a85b40276d22d9b71b71
size 775643712

3
FuseChat-Llama-3.2-1B-Instruct-Q5_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:127ece9d106156dee5ce5a0d39b1c42bac1734c10c1dbd04fd717a15025870fa
size 975114816

3
FuseChat-Llama-3.2-1B-Instruct-Q5_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9e5847cc29e5cc3fea955432ee21bd5c1151c026193fc2ec8d72ca4e72356392
size 911499840

3
FuseChat-Llama-3.2-1B-Instruct-Q5_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:6374293aa5436a6eb2e5c4d662a7aeb2edc94320626747c37b08a0488f6175f5
size 892559936

3
FuseChat-Llama-3.2-1B-Instruct-Q6_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:14c5361f1273dcb23ebec91613f6c24e5b3425aabe31ea278b02d83e6f08d59c
size 1021796928

3
FuseChat-Llama-3.2-1B-Instruct-Q6_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:8905481f68b85fa869e50fafd99a7eb97b270bd81426553e3af0757718ef47b7
size 1085411904

3
FuseChat-Llama-3.2-1B-Instruct-Q8_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c7db2b30d2b176998db90304d1ac6dd259379bd75f9ea8b6a094be88ea47b1b4
size 1321079360

3
FuseChat-Llama-3.2-1B-Instruct-f16.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:110c8c20b7b9626123755d1098cc5e37e57e19432b000b808d1cbad005bfbda6
size 2479592000

3
FuseChat-Llama-3.2-1B-Instruct-f32.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d12227e30d4fbae2c38e56a3566416a9a327e1f8a6577bdda5a199f0294a9fe6
size 4951085312

3
FuseChat-Llama-3.2-1B-Instruct.imatrix Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d1f6fb96990cc9481ca28cabd143ea880b826c1ca6fecf710c3ba3473d84708d
size 1314426

170
README.md Normal file
View File

@@ -0,0 +1,170 @@
---
quantized_by: bartowski
pipeline_tag: text-generation
base_model: FuseAI/FuseChat-Llama-3.2-1B-Instruct
---
## Llamacpp imatrix Quantizations of FuseChat-Llama-3.2-1B-Instruct
Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b4273">b4273</a> for quantization.
Original model: https://huggingface.co/FuseAI/FuseChat-Llama-3.2-1B-Instruct
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 |
| -------- | ---------- | --------- | ----- | ----------- |
| [FuseChat-Llama-3.2-1B-Instruct-f32.gguf](https://huggingface.co/bartowski/FuseChat-Llama-3.2-1B-Instruct-GGUF/blob/main/FuseChat-Llama-3.2-1B-Instruct-f32.gguf) | f32 | 4.95GB | false | Full F32 weights. |
| [FuseChat-Llama-3.2-1B-Instruct-f16.gguf](https://huggingface.co/bartowski/FuseChat-Llama-3.2-1B-Instruct-GGUF/blob/main/FuseChat-Llama-3.2-1B-Instruct-f16.gguf) | f16 | 2.48GB | false | Full F16 weights. |
| [FuseChat-Llama-3.2-1B-Instruct-Q8_0.gguf](https://huggingface.co/bartowski/FuseChat-Llama-3.2-1B-Instruct-GGUF/blob/main/FuseChat-Llama-3.2-1B-Instruct-Q8_0.gguf) | Q8_0 | 1.32GB | false | Extremely high quality, generally unneeded but max available quant. |
| [FuseChat-Llama-3.2-1B-Instruct-Q6_K_L.gguf](https://huggingface.co/bartowski/FuseChat-Llama-3.2-1B-Instruct-GGUF/blob/main/FuseChat-Llama-3.2-1B-Instruct-Q6_K_L.gguf) | Q6_K_L | 1.09GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. |
| [FuseChat-Llama-3.2-1B-Instruct-Q6_K.gguf](https://huggingface.co/bartowski/FuseChat-Llama-3.2-1B-Instruct-GGUF/blob/main/FuseChat-Llama-3.2-1B-Instruct-Q6_K.gguf) | Q6_K | 1.02GB | false | Very high quality, near perfect, *recommended*. |
| [FuseChat-Llama-3.2-1B-Instruct-Q5_K_L.gguf](https://huggingface.co/bartowski/FuseChat-Llama-3.2-1B-Instruct-GGUF/blob/main/FuseChat-Llama-3.2-1B-Instruct-Q5_K_L.gguf) | Q5_K_L | 0.98GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. |
| [FuseChat-Llama-3.2-1B-Instruct-Q5_K_M.gguf](https://huggingface.co/bartowski/FuseChat-Llama-3.2-1B-Instruct-GGUF/blob/main/FuseChat-Llama-3.2-1B-Instruct-Q5_K_M.gguf) | Q5_K_M | 0.91GB | false | High quality, *recommended*. |
| [FuseChat-Llama-3.2-1B-Instruct-Q5_K_S.gguf](https://huggingface.co/bartowski/FuseChat-Llama-3.2-1B-Instruct-GGUF/blob/main/FuseChat-Llama-3.2-1B-Instruct-Q5_K_S.gguf) | Q5_K_S | 0.89GB | false | High quality, *recommended*. |
| [FuseChat-Llama-3.2-1B-Instruct-Q4_K_L.gguf](https://huggingface.co/bartowski/FuseChat-Llama-3.2-1B-Instruct-GGUF/blob/main/FuseChat-Llama-3.2-1B-Instruct-Q4_K_L.gguf) | Q4_K_L | 0.87GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. |
| [FuseChat-Llama-3.2-1B-Instruct-Q4_K_M.gguf](https://huggingface.co/bartowski/FuseChat-Llama-3.2-1B-Instruct-GGUF/blob/main/FuseChat-Llama-3.2-1B-Instruct-Q4_K_M.gguf) | Q4_K_M | 0.81GB | false | Good quality, default size for most use cases, *recommended*. |
| [FuseChat-Llama-3.2-1B-Instruct-Q3_K_XL.gguf](https://huggingface.co/bartowski/FuseChat-Llama-3.2-1B-Instruct-GGUF/blob/main/FuseChat-Llama-3.2-1B-Instruct-Q3_K_XL.gguf) | Q3_K_XL | 0.80GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. |
| [FuseChat-Llama-3.2-1B-Instruct-Q4_K_S.gguf](https://huggingface.co/bartowski/FuseChat-Llama-3.2-1B-Instruct-GGUF/blob/main/FuseChat-Llama-3.2-1B-Instruct-Q4_K_S.gguf) | Q4_K_S | 0.78GB | false | Slightly lower quality with more space savings, *recommended*. |
| [FuseChat-Llama-3.2-1B-Instruct-Q4_0_8_8.gguf](https://huggingface.co/bartowski/FuseChat-Llama-3.2-1B-Instruct-GGUF/blob/main/FuseChat-Llama-3.2-1B-Instruct-Q4_0_8_8.gguf) | Q4_0_8_8 | 0.77GB | false | Optimized for ARM and AVX inference. Requires 'sve' support for ARM (see details below). *Don't use on Mac*. |
| [FuseChat-Llama-3.2-1B-Instruct-Q4_0_4_8.gguf](https://huggingface.co/bartowski/FuseChat-Llama-3.2-1B-Instruct-GGUF/blob/main/FuseChat-Llama-3.2-1B-Instruct-Q4_0_4_8.gguf) | Q4_0_4_8 | 0.77GB | false | Optimized for ARM inference. Requires 'i8mm' support (see details below). *Don't use on Mac*. |
| [FuseChat-Llama-3.2-1B-Instruct-Q4_0_4_4.gguf](https://huggingface.co/bartowski/FuseChat-Llama-3.2-1B-Instruct-GGUF/blob/main/FuseChat-Llama-3.2-1B-Instruct-Q4_0_4_4.gguf) | Q4_0_4_4 | 0.77GB | false | Optimized for ARM inference. Should work well on all ARM chips, not for use with GPUs. *Don't use on Mac*. |
| [FuseChat-Llama-3.2-1B-Instruct-Q4_0.gguf](https://huggingface.co/bartowski/FuseChat-Llama-3.2-1B-Instruct-GGUF/blob/main/FuseChat-Llama-3.2-1B-Instruct-Q4_0.gguf) | Q4_0 | 0.77GB | false | Legacy format, offers online repacking for ARM CPU inference. |
| [FuseChat-Llama-3.2-1B-Instruct-IQ4_NL.gguf](https://huggingface.co/bartowski/FuseChat-Llama-3.2-1B-Instruct-GGUF/blob/main/FuseChat-Llama-3.2-1B-Instruct-IQ4_NL.gguf) | IQ4_NL | 0.77GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. |
| [FuseChat-Llama-3.2-1B-Instruct-IQ4_XS.gguf](https://huggingface.co/bartowski/FuseChat-Llama-3.2-1B-Instruct-GGUF/blob/main/FuseChat-Llama-3.2-1B-Instruct-IQ4_XS.gguf) | IQ4_XS | 0.74GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
| [FuseChat-Llama-3.2-1B-Instruct-Q3_K_L.gguf](https://huggingface.co/bartowski/FuseChat-Llama-3.2-1B-Instruct-GGUF/blob/main/FuseChat-Llama-3.2-1B-Instruct-Q3_K_L.gguf) | Q3_K_L | 0.73GB | false | Lower quality but usable, good for low RAM availability. |
| [FuseChat-Llama-3.2-1B-Instruct-Q3_K_M.gguf](https://huggingface.co/bartowski/FuseChat-Llama-3.2-1B-Instruct-GGUF/blob/main/FuseChat-Llama-3.2-1B-Instruct-Q3_K_M.gguf) | Q3_K_M | 0.69GB | false | Low quality. |
| [FuseChat-Llama-3.2-1B-Instruct-IQ3_M.gguf](https://huggingface.co/bartowski/FuseChat-Llama-3.2-1B-Instruct-GGUF/blob/main/FuseChat-Llama-3.2-1B-Instruct-IQ3_M.gguf) | IQ3_M | 0.66GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
| [FuseChat-Llama-3.2-1B-Instruct-Q3_K_S.gguf](https://huggingface.co/bartowski/FuseChat-Llama-3.2-1B-Instruct-GGUF/blob/main/FuseChat-Llama-3.2-1B-Instruct-Q3_K_S.gguf) | Q3_K_S | 0.64GB | false | Low quality, not recommended. |
| [FuseChat-Llama-3.2-1B-Instruct-Q2_K_L.gguf](https://huggingface.co/bartowski/FuseChat-Llama-3.2-1B-Instruct-GGUF/blob/main/FuseChat-Llama-3.2-1B-Instruct-Q2_K_L.gguf) | Q2_K_L | 0.64GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. |
| [FuseChat-Llama-3.2-1B-Instruct-IQ3_XS.gguf](https://huggingface.co/bartowski/FuseChat-Llama-3.2-1B-Instruct-GGUF/blob/main/FuseChat-Llama-3.2-1B-Instruct-IQ3_XS.gguf) | IQ3_XS | 0.62GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
| [FuseChat-Llama-3.2-1B-Instruct-Q2_K.gguf](https://huggingface.co/bartowski/FuseChat-Llama-3.2-1B-Instruct-GGUF/blob/main/FuseChat-Llama-3.2-1B-Instruct-Q2_K.gguf) | Q2_K | 0.58GB | false | Very low quality but surprisingly usable. |
| [FuseChat-Llama-3.2-1B-Instruct-IQ2_M.gguf](https://huggingface.co/bartowski/FuseChat-Llama-3.2-1B-Instruct-GGUF/blob/main/FuseChat-Llama-3.2-1B-Instruct-IQ2_M.gguf) | IQ2_M | 0.52GB | 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/FuseChat-Llama-3.2-1B-Instruct-GGUF --include "FuseChat-Llama-3.2-1B-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/FuseChat-Llama-3.2-1B-Instruct-GGUF --include "FuseChat-Llama-3.2-1B-Instruct-Q8_0/*" --local-dir ./
```
You can either specify a new local-dir (FuseChat-Llama-3.2-1B-Instruct-Q8_0) or download them all in place (./)
</details>
## Q4_0_X_X information
New: Thanks to efforts made to have online repacking of weights in [this PR](https://github.com/ggerganov/llama.cpp/pull/9921), you can now just use Q4_0 if your llama.cpp has been compiled for your ARM device.
Similarly, if you want to get slightly better performance, you can use IQ4_NL thanks to [this PR](https://github.com/ggerganov/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</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}