bartowski/Llama-Chat-Summary-3.2-3B-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-Chat-Summary-3.2-3B-GGUF
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-06-18 00:18:13 +08:00
commit 24c1d65f64
26 changed files with 309 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

58
.gitattributes vendored Normal file
View File

@@ -0,0 +1,58 @@
*.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-Chat-Summary-3.2-3B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
Llama-Chat-Summary-3.2-3B-Q6_K_L.gguf filter=lfs diff=lfs merge=lfs -text
Llama-Chat-Summary-3.2-3B-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
Llama-Chat-Summary-3.2-3B-Q5_K_L.gguf filter=lfs diff=lfs merge=lfs -text
Llama-Chat-Summary-3.2-3B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
Llama-Chat-Summary-3.2-3B-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
Llama-Chat-Summary-3.2-3B-Q4_K_L.gguf filter=lfs diff=lfs merge=lfs -text
Llama-Chat-Summary-3.2-3B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
Llama-Chat-Summary-3.2-3B-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
Llama-Chat-Summary-3.2-3B-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
Llama-Chat-Summary-3.2-3B-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text
Llama-Chat-Summary-3.2-3B-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
Llama-Chat-Summary-3.2-3B-Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
Llama-Chat-Summary-3.2-3B-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
Llama-Chat-Summary-3.2-3B-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
Llama-Chat-Summary-3.2-3B-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
Llama-Chat-Summary-3.2-3B-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
Llama-Chat-Summary-3.2-3B-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
Llama-Chat-Summary-3.2-3B-Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text
Llama-Chat-Summary-3.2-3B-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
Llama-Chat-Summary-3.2-3B-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text
Llama-Chat-Summary-3.2-3B-f16.gguf filter=lfs diff=lfs merge=lfs -text
Llama-Chat-Summary-3.2-3B.imatrix filter=lfs diff=lfs merge=lfs -text

3
Llama-Chat-Summary-3.2-3B-IQ2_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:80d14c949955cbb2dbe0d9c1482f301434103576138225e3a400cc9eed75e936
size 1229037760

3
Llama-Chat-Summary-3.2-3B-IQ3_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e9bc5f460f4f60eda355f6f9c3a286b84d68c2fd62b181dfd91cb8393372e84f
size 1599674560

3
Llama-Chat-Summary-3.2-3B-IQ3_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0d0f313e9304483c5cb4417d1482c5a728c505b68e46b2a5b5e3e967918b7d3c
size 1476794560

3
Llama-Chat-Summary-3.2-3B-IQ4_NL.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f699de025721bdb26d54e17df502fecdd3f4922cd252aa046a29b1dcd50464d5
size 1917196480

3
Llama-Chat-Summary-3.2-3B-IQ4_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:bf8a7c699866314e624c928d8a2bcde983c501677e7c50ec5c60f326a1ab765a
size 1829116096

3
Llama-Chat-Summary-3.2-3B-Q2_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:75a102b44f923ecf6484fbc12ee4b345a804d17e876132bc27a75ff00d623eb2
size 1363941568

3
Llama-Chat-Summary-3.2-3B-Q2_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e465263439b2e4dfa02eb551926fe240b5f85125d5016d2053fe2064e8a06b22
size 1459364032

3
Llama-Chat-Summary-3.2-3B-Q3_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a38b621e3e753cee42fc30cda3637c7df931d416c8c66376a49a9fe17f653459
size 1815353536

3
Llama-Chat-Summary-3.2-3B-Q3_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0f2d77987f07f10d882e1479a745a8abe02832549ecd26f64bc89e343c48f78e
size 1687165120

3
Llama-Chat-Summary-3.2-3B-Q3_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a2f51dfb9a1000660c7c048c2e0d198b7573f980f48cd19b61c64e279ac521a6
size 1542854848

3
Llama-Chat-Summary-3.2-3B-Q3_K_XL.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9390fd7b29ef5ec9e17d5b70568999041ba09aa94ea65e110a95b60b6b8d9fb7
size 1910776000

3
Llama-Chat-Summary-3.2-3B-Q4_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f561ed50fe4836c31681dbfe2b9748012405e793d6b2d5ec7b11a197ba0886b6
size 1921915072

3
Llama-Chat-Summary-3.2-3B-Q4_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e1fac3faccf80d49f0e9458f6086ef6ca87b0b92b5e44657384a75612ccf16df
size 2114805952

3
Llama-Chat-Summary-3.2-3B-Q4_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ed1be20d2374aa6db9940923f41fa229bd7ebe13d41b1ff1ff18a6f87e99df79
size 2019383488

3
Llama-Chat-Summary-3.2-3B-Q4_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3600812af99aa6e35a2d17d235b7354e2e19bd00e90ef5b9001812851ac9b165
size 1928206528

3
Llama-Chat-Summary-3.2-3B-Q5_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:13bbec9207b1b99a9df06583eeb6d1938e8089640584786262c4f94ebb7f8bd4
size 2417582272

3
Llama-Chat-Summary-3.2-3B-Q5_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5902d85d20229a2e40ab78a03d823c7424fe5182956839dbec4424ab2a7936df
size 2322159808

3
Llama-Chat-Summary-3.2-3B-Q5_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:99b9dbcf7c9e1d3806c9612e9378d2b90206944f4a300287c8586334d33c50d4
size 2269518016

3
Llama-Chat-Summary-3.2-3B-Q6_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e1870b36f65e1fc1be06f9cc87171e56b013cb2fceb4d4129638695ca44ed348
size 2643859648

3
Llama-Chat-Summary-3.2-3B-Q6_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9a150ece6a6debbd67f5ca7086fb6eac45758e0aebfc15924b8d8014026dd502
size 2739282112

3
Llama-Chat-Summary-3.2-3B-Q8_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b63a97446243c0f4b65690b88fa7c3ffe74d9fe8d116e5b7005ec7ddd6cda5e2
size 3421905088

3
Llama-Chat-Summary-3.2-3B-f16.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1612d2903d4fc40ad0ebd8b433aa40973961430d9462e1fdddf9f3b2786b79da
size 6433693600

3
Llama-Chat-Summary-3.2-3B.imatrix Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:02cbb863f7e24b2dddbda938260ad6e000f18fed9c2a102bec2367ac89ac8f39
size 2988390

181
README.md Normal file
View File

@@ -0,0 +1,181 @@
---
quantized_by: bartowski
pipeline_tag: text-generation
tags:
- safetensors
- chat-summary
- 3B
- Ollama
- text-generation-inference
- trl
- Llama3.2
license: creativeml-openrail-m
base_model: prithivMLmods/Llama-Chat-Summary-3.2-3B
datasets:
- prithivMLmods/Context-Based-Chat-Summary-Plus
language:
- en
---
## Llamacpp imatrix Quantizations of Llama-Chat-Summary-3.2-3B
Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b4341">b4341</a> for quantization.
Original model: https://huggingface.co/prithivMLmods/Llama-Chat-Summary-3.2-3B
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 July 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 |
| -------- | ---------- | --------- | ----- | ----------- |
| [Llama-Chat-Summary-3.2-3B-f16.gguf](https://huggingface.co/bartowski/Llama-Chat-Summary-3.2-3B-GGUF/blob/main/Llama-Chat-Summary-3.2-3B-f16.gguf) | f16 | 6.43GB | false | Full F16 weights. |
| [Llama-Chat-Summary-3.2-3B-Q8_0.gguf](https://huggingface.co/bartowski/Llama-Chat-Summary-3.2-3B-GGUF/blob/main/Llama-Chat-Summary-3.2-3B-Q8_0.gguf) | Q8_0 | 3.42GB | false | Extremely high quality, generally unneeded but max available quant. |
| [Llama-Chat-Summary-3.2-3B-Q6_K_L.gguf](https://huggingface.co/bartowski/Llama-Chat-Summary-3.2-3B-GGUF/blob/main/Llama-Chat-Summary-3.2-3B-Q6_K_L.gguf) | Q6_K_L | 2.74GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. |
| [Llama-Chat-Summary-3.2-3B-Q6_K.gguf](https://huggingface.co/bartowski/Llama-Chat-Summary-3.2-3B-GGUF/blob/main/Llama-Chat-Summary-3.2-3B-Q6_K.gguf) | Q6_K | 2.64GB | false | Very high quality, near perfect, *recommended*. |
| [Llama-Chat-Summary-3.2-3B-Q5_K_L.gguf](https://huggingface.co/bartowski/Llama-Chat-Summary-3.2-3B-GGUF/blob/main/Llama-Chat-Summary-3.2-3B-Q5_K_L.gguf) | Q5_K_L | 2.42GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. |
| [Llama-Chat-Summary-3.2-3B-Q5_K_M.gguf](https://huggingface.co/bartowski/Llama-Chat-Summary-3.2-3B-GGUF/blob/main/Llama-Chat-Summary-3.2-3B-Q5_K_M.gguf) | Q5_K_M | 2.32GB | false | High quality, *recommended*. |
| [Llama-Chat-Summary-3.2-3B-Q5_K_S.gguf](https://huggingface.co/bartowski/Llama-Chat-Summary-3.2-3B-GGUF/blob/main/Llama-Chat-Summary-3.2-3B-Q5_K_S.gguf) | Q5_K_S | 2.27GB | false | High quality, *recommended*. |
| [Llama-Chat-Summary-3.2-3B-Q4_K_L.gguf](https://huggingface.co/bartowski/Llama-Chat-Summary-3.2-3B-GGUF/blob/main/Llama-Chat-Summary-3.2-3B-Q4_K_L.gguf) | Q4_K_L | 2.11GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. |
| [Llama-Chat-Summary-3.2-3B-Q4_K_M.gguf](https://huggingface.co/bartowski/Llama-Chat-Summary-3.2-3B-GGUF/blob/main/Llama-Chat-Summary-3.2-3B-Q4_K_M.gguf) | Q4_K_M | 2.02GB | false | Good quality, default size for most use cases, *recommended*. |
| [Llama-Chat-Summary-3.2-3B-Q4_K_S.gguf](https://huggingface.co/bartowski/Llama-Chat-Summary-3.2-3B-GGUF/blob/main/Llama-Chat-Summary-3.2-3B-Q4_K_S.gguf) | Q4_K_S | 1.93GB | false | Slightly lower quality with more space savings, *recommended*. |
| [Llama-Chat-Summary-3.2-3B-Q4_0.gguf](https://huggingface.co/bartowski/Llama-Chat-Summary-3.2-3B-GGUF/blob/main/Llama-Chat-Summary-3.2-3B-Q4_0.gguf) | Q4_0 | 1.92GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. |
| [Llama-Chat-Summary-3.2-3B-IQ4_NL.gguf](https://huggingface.co/bartowski/Llama-Chat-Summary-3.2-3B-GGUF/blob/main/Llama-Chat-Summary-3.2-3B-IQ4_NL.gguf) | IQ4_NL | 1.92GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. |
| [Llama-Chat-Summary-3.2-3B-Q3_K_XL.gguf](https://huggingface.co/bartowski/Llama-Chat-Summary-3.2-3B-GGUF/blob/main/Llama-Chat-Summary-3.2-3B-Q3_K_XL.gguf) | Q3_K_XL | 1.91GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. |
| [Llama-Chat-Summary-3.2-3B-IQ4_XS.gguf](https://huggingface.co/bartowski/Llama-Chat-Summary-3.2-3B-GGUF/blob/main/Llama-Chat-Summary-3.2-3B-IQ4_XS.gguf) | IQ4_XS | 1.83GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
| [Llama-Chat-Summary-3.2-3B-Q3_K_L.gguf](https://huggingface.co/bartowski/Llama-Chat-Summary-3.2-3B-GGUF/blob/main/Llama-Chat-Summary-3.2-3B-Q3_K_L.gguf) | Q3_K_L | 1.82GB | false | Lower quality but usable, good for low RAM availability. |
| [Llama-Chat-Summary-3.2-3B-Q3_K_M.gguf](https://huggingface.co/bartowski/Llama-Chat-Summary-3.2-3B-GGUF/blob/main/Llama-Chat-Summary-3.2-3B-Q3_K_M.gguf) | Q3_K_M | 1.69GB | false | Low quality. |
| [Llama-Chat-Summary-3.2-3B-IQ3_M.gguf](https://huggingface.co/bartowski/Llama-Chat-Summary-3.2-3B-GGUF/blob/main/Llama-Chat-Summary-3.2-3B-IQ3_M.gguf) | IQ3_M | 1.60GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
| [Llama-Chat-Summary-3.2-3B-Q3_K_S.gguf](https://huggingface.co/bartowski/Llama-Chat-Summary-3.2-3B-GGUF/blob/main/Llama-Chat-Summary-3.2-3B-Q3_K_S.gguf) | Q3_K_S | 1.54GB | false | Low quality, not recommended. |
| [Llama-Chat-Summary-3.2-3B-IQ3_XS.gguf](https://huggingface.co/bartowski/Llama-Chat-Summary-3.2-3B-GGUF/blob/main/Llama-Chat-Summary-3.2-3B-IQ3_XS.gguf) | IQ3_XS | 1.48GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
| [Llama-Chat-Summary-3.2-3B-Q2_K_L.gguf](https://huggingface.co/bartowski/Llama-Chat-Summary-3.2-3B-GGUF/blob/main/Llama-Chat-Summary-3.2-3B-Q2_K_L.gguf) | Q2_K_L | 1.46GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. |
| [Llama-Chat-Summary-3.2-3B-Q2_K.gguf](https://huggingface.co/bartowski/Llama-Chat-Summary-3.2-3B-GGUF/blob/main/Llama-Chat-Summary-3.2-3B-Q2_K.gguf) | Q2_K | 1.36GB | false | Very low quality but surprisingly usable. |
| [Llama-Chat-Summary-3.2-3B-IQ2_M.gguf](https://huggingface.co/bartowski/Llama-Chat-Summary-3.2-3B-GGUF/blob/main/Llama-Chat-Summary-3.2-3B-IQ2_M.gguf) | IQ2_M | 1.23GB | 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/Llama-Chat-Summary-3.2-3B-GGUF --include "Llama-Chat-Summary-3.2-3B-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-Chat-Summary-3.2-3B-GGUF --include "Llama-Chat-Summary-3.2-3B-Q8_0/*" --local-dir ./
```
You can either specify a new local-dir (Llama-Chat-Summary-3.2-3B-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}