bartowski/HuatuoGPT-o1-8B-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/HuatuoGPT-o1-8B-GGUF
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-07-21 14:19:07 +08:00
commit 86c5c570ce
27 changed files with 309 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

59
.gitattributes vendored Normal file
View File

@@ -0,0 +1,59 @@
*.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
HuatuoGPT-o1-8B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
HuatuoGPT-o1-8B-Q6_K_L.gguf filter=lfs diff=lfs merge=lfs -text
HuatuoGPT-o1-8B-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
HuatuoGPT-o1-8B-Q5_K_L.gguf filter=lfs diff=lfs merge=lfs -text
HuatuoGPT-o1-8B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
HuatuoGPT-o1-8B-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
HuatuoGPT-o1-8B-Q4_K_L.gguf filter=lfs diff=lfs merge=lfs -text
HuatuoGPT-o1-8B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
HuatuoGPT-o1-8B-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
HuatuoGPT-o1-8B-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text
HuatuoGPT-o1-8B-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
HuatuoGPT-o1-8B-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text
HuatuoGPT-o1-8B-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
HuatuoGPT-o1-8B-Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
HuatuoGPT-o1-8B-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
HuatuoGPT-o1-8B-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
HuatuoGPT-o1-8B-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
HuatuoGPT-o1-8B-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
HuatuoGPT-o1-8B-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
HuatuoGPT-o1-8B-Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text
HuatuoGPT-o1-8B-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
HuatuoGPT-o1-8B-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text
HuatuoGPT-o1-8B-f16.gguf filter=lfs diff=lfs merge=lfs -text
HuatuoGPT-o1-8B.imatrix filter=lfs diff=lfs merge=lfs -text

3
HuatuoGPT-o1-8B-IQ2_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:6705dd4d6b7b223a916c76230f1ad5da6ce5fbfe39c40367eadc20eb68a5b4a0
size 2948286592

3
HuatuoGPT-o1-8B-IQ3_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:7472c1fa286d890c0ff9e574efeb49a57d7b0ae463376665d65d85d77217225e
size 3784829056

3
HuatuoGPT-o1-8B-IQ3_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:dccfa87061aa5480a0f56dad75aa56c2006b019bb7fb97fd1c6fc1015d837fe1
size 3518752896

3
HuatuoGPT-o1-8B-IQ4_NL.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:8508d6dbc786b8a3f5e86fbefc26ea3f38521d1434b21c709c9c23920326570e
size 4677994624

3
HuatuoGPT-o1-8B-IQ4_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d44a410cb3cf5aac506cab532045ec96bda098d050d9d62eab9d7446b1657405
size 4447668352

3
HuatuoGPT-o1-8B-Q2_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1445fd0fecef09e9e16c3e72c9d6d74104c08c9ca32abb084520f27cf184c947
size 3179137152

3
HuatuoGPT-o1-8B-Q2_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b00e72eee35c460ae77f04e6d934bb7f8898eb767e08573c7c737affcadaa8f8
size 3692161152

3
HuatuoGPT-o1-8B-Q3_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:14563173650a5db029ec929c5ed55a435d4f057dfca02ab4d0c8a6aac950538b
size 4321962112

3
HuatuoGPT-o1-8B-Q3_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:31033d3d1567c5af2d730d95b093c04d14beee2bc05328b69edf54b2febcc6bb
size 4018923648

3
HuatuoGPT-o1-8B-Q3_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:4dbba2b7fde117d3a5534cc505bd1dc2c683b200be1e71c28d368063fe26d765
size 3664504960

3
HuatuoGPT-o1-8B-Q3_K_XL.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1d363cda6ccebddd688427221252cdce37c86d96a8c2ffa88f71cc4d29bb7de1
size 4781631616

3
HuatuoGPT-o1-8B-Q4_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3f4a84dc3a4312790fc0fd89fe9e509b09eaa6e61676f1a01b6b37fbb7506a0e
size 4675897472

3
HuatuoGPT-o1-8B-Q4_1.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:363a8e318f066235567bad687687995d8ee7213714a99f271a6e227f38095876
size 5130258560

3
HuatuoGPT-o1-8B-Q4_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c0b1ff795c97e3b42d80fea0e5376ff332df506501073f5eb681e6722933705a
size 5310638208

3
HuatuoGPT-o1-8B-Q4_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3e1ef35fc230182d96ae2d6c7436a2e8250c21a4278e798e1aa45790ba82006b
size 4920739968

3
HuatuoGPT-o1-8B-Q4_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:4654c4025c6a6bf05de24a15ad5131bddb216249981e1975c827f3fa5b13f802
size 4692674688

3
HuatuoGPT-o1-8B-Q5_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f5492874cb8af44f5567c5dd133f94e09d99421e8b9932f829184d2ebd16da15
size 6057224320

3
HuatuoGPT-o1-8B-Q5_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:711568862532bbae5a2878a9be0e3d68a81ade8a5aca9d3c33c35d85d00c4c5b
size 5732993152

3
HuatuoGPT-o1-8B-Q5_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:01b329415496f6e489d7fbd8025a0bd98780fd1779601d4d7208384df0a1d039
size 5599299712

3
HuatuoGPT-o1-8B-Q6_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:39e8d8b51cddc7049efcb468238f7b9556e6594b1db86e865e6cf8d731b5dc40
size 6596012160

3
HuatuoGPT-o1-8B-Q6_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5baf9091761d2b3863a922ddc33ffb40d68bb8d73784e86405183328ad4ee562
size 6850472064

3
HuatuoGPT-o1-8B-Q8_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d71caab948405aec28234c6adc0fcfd68526d3ff2f96fbfb4a02d5de439f358d
size 8540776576

3
HuatuoGPT-o1-8B-f16.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:6d426b91145c3287c42bb6076875e80f1c7165232246fc9fb271383c6b820d52
size 16068896640

3
HuatuoGPT-o1-8B.imatrix Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:245bd7f2e55bb80845956f0ace69467fe81e7ebe297fa5d38fbc3d9d4239c9a1
size 4988170

177
README.md Normal file
View File

@@ -0,0 +1,177 @@
---
quantized_by: bartowski
pipeline_tag: text-generation
base_model: FreedomIntelligence/HuatuoGPT-o1-8B
datasets:
- FreedomIntelligence/medical-o1-reasoning-SFT
- FreedomIntelligence/medical-o1-verifiable-problem
license: apache-2.0
tags:
- medical
language:
- en
---
## Llamacpp imatrix Quantizations of HuatuoGPT-o1-8B
Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b4381">b4381</a> for quantization.
Original model: https://huggingface.co/FreedomIntelligence/HuatuoGPT-o1-8B
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 |
| -------- | ---------- | --------- | ----- | ----------- |
| [HuatuoGPT-o1-8B-f16.gguf](https://huggingface.co/bartowski/HuatuoGPT-o1-8B-GGUF/blob/main/HuatuoGPT-o1-8B-f16.gguf) | f16 | 16.07GB | false | Full F16 weights. |
| [HuatuoGPT-o1-8B-Q8_0.gguf](https://huggingface.co/bartowski/HuatuoGPT-o1-8B-GGUF/blob/main/HuatuoGPT-o1-8B-Q8_0.gguf) | Q8_0 | 8.54GB | false | Extremely high quality, generally unneeded but max available quant. |
| [HuatuoGPT-o1-8B-Q6_K_L.gguf](https://huggingface.co/bartowski/HuatuoGPT-o1-8B-GGUF/blob/main/HuatuoGPT-o1-8B-Q6_K_L.gguf) | Q6_K_L | 6.85GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. |
| [HuatuoGPT-o1-8B-Q6_K.gguf](https://huggingface.co/bartowski/HuatuoGPT-o1-8B-GGUF/blob/main/HuatuoGPT-o1-8B-Q6_K.gguf) | Q6_K | 6.60GB | false | Very high quality, near perfect, *recommended*. |
| [HuatuoGPT-o1-8B-Q5_K_L.gguf](https://huggingface.co/bartowski/HuatuoGPT-o1-8B-GGUF/blob/main/HuatuoGPT-o1-8B-Q5_K_L.gguf) | Q5_K_L | 6.06GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. |
| [HuatuoGPT-o1-8B-Q5_K_M.gguf](https://huggingface.co/bartowski/HuatuoGPT-o1-8B-GGUF/blob/main/HuatuoGPT-o1-8B-Q5_K_M.gguf) | Q5_K_M | 5.73GB | false | High quality, *recommended*. |
| [HuatuoGPT-o1-8B-Q5_K_S.gguf](https://huggingface.co/bartowski/HuatuoGPT-o1-8B-GGUF/blob/main/HuatuoGPT-o1-8B-Q5_K_S.gguf) | Q5_K_S | 5.60GB | false | High quality, *recommended*. |
| [HuatuoGPT-o1-8B-Q4_K_L.gguf](https://huggingface.co/bartowski/HuatuoGPT-o1-8B-GGUF/blob/main/HuatuoGPT-o1-8B-Q4_K_L.gguf) | Q4_K_L | 5.31GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. |
| [HuatuoGPT-o1-8B-Q4_1.gguf](https://huggingface.co/bartowski/HuatuoGPT-o1-8B-GGUF/blob/main/HuatuoGPT-o1-8B-Q4_1.gguf) | Q4_1 | 5.13GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. |
| [HuatuoGPT-o1-8B-Q4_K_M.gguf](https://huggingface.co/bartowski/HuatuoGPT-o1-8B-GGUF/blob/main/HuatuoGPT-o1-8B-Q4_K_M.gguf) | Q4_K_M | 4.92GB | false | Good quality, default size for most use cases, *recommended*. |
| [HuatuoGPT-o1-8B-Q3_K_XL.gguf](https://huggingface.co/bartowski/HuatuoGPT-o1-8B-GGUF/blob/main/HuatuoGPT-o1-8B-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. |
| [HuatuoGPT-o1-8B-Q4_K_S.gguf](https://huggingface.co/bartowski/HuatuoGPT-o1-8B-GGUF/blob/main/HuatuoGPT-o1-8B-Q4_K_S.gguf) | Q4_K_S | 4.69GB | false | Slightly lower quality with more space savings, *recommended*. |
| [HuatuoGPT-o1-8B-Q4_0.gguf](https://huggingface.co/bartowski/HuatuoGPT-o1-8B-GGUF/blob/main/HuatuoGPT-o1-8B-Q4_0.gguf) | Q4_0 | 4.68GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. |
| [HuatuoGPT-o1-8B-IQ4_NL.gguf](https://huggingface.co/bartowski/HuatuoGPT-o1-8B-GGUF/blob/main/HuatuoGPT-o1-8B-IQ4_NL.gguf) | IQ4_NL | 4.68GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. |
| [HuatuoGPT-o1-8B-IQ4_XS.gguf](https://huggingface.co/bartowski/HuatuoGPT-o1-8B-GGUF/blob/main/HuatuoGPT-o1-8B-IQ4_XS.gguf) | IQ4_XS | 4.45GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
| [HuatuoGPT-o1-8B-Q3_K_L.gguf](https://huggingface.co/bartowski/HuatuoGPT-o1-8B-GGUF/blob/main/HuatuoGPT-o1-8B-Q3_K_L.gguf) | Q3_K_L | 4.32GB | false | Lower quality but usable, good for low RAM availability. |
| [HuatuoGPT-o1-8B-Q3_K_M.gguf](https://huggingface.co/bartowski/HuatuoGPT-o1-8B-GGUF/blob/main/HuatuoGPT-o1-8B-Q3_K_M.gguf) | Q3_K_M | 4.02GB | false | Low quality. |
| [HuatuoGPT-o1-8B-IQ3_M.gguf](https://huggingface.co/bartowski/HuatuoGPT-o1-8B-GGUF/blob/main/HuatuoGPT-o1-8B-IQ3_M.gguf) | IQ3_M | 3.78GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
| [HuatuoGPT-o1-8B-Q2_K_L.gguf](https://huggingface.co/bartowski/HuatuoGPT-o1-8B-GGUF/blob/main/HuatuoGPT-o1-8B-Q2_K_L.gguf) | Q2_K_L | 3.69GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. |
| [HuatuoGPT-o1-8B-Q3_K_S.gguf](https://huggingface.co/bartowski/HuatuoGPT-o1-8B-GGUF/blob/main/HuatuoGPT-o1-8B-Q3_K_S.gguf) | Q3_K_S | 3.66GB | false | Low quality, not recommended. |
| [HuatuoGPT-o1-8B-IQ3_XS.gguf](https://huggingface.co/bartowski/HuatuoGPT-o1-8B-GGUF/blob/main/HuatuoGPT-o1-8B-IQ3_XS.gguf) | IQ3_XS | 3.52GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
| [HuatuoGPT-o1-8B-Q2_K.gguf](https://huggingface.co/bartowski/HuatuoGPT-o1-8B-GGUF/blob/main/HuatuoGPT-o1-8B-Q2_K.gguf) | Q2_K | 3.18GB | false | Very low quality but surprisingly usable. |
| [HuatuoGPT-o1-8B-IQ2_M.gguf](https://huggingface.co/bartowski/HuatuoGPT-o1-8B-GGUF/blob/main/HuatuoGPT-o1-8B-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.
## 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/HuatuoGPT-o1-8B-GGUF --include "HuatuoGPT-o1-8B-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/HuatuoGPT-o1-8B-GGUF --include "HuatuoGPT-o1-8B-Q8_0/*" --local-dir ./
```
You can either specify a new local-dir (HuatuoGPT-o1-8B-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/ggerganov/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/ggerganov/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/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 (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/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}