bartowski/Qwen_Qwen3-4B-Instruct-2507-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/Qwen_Qwen3-4B-Instruct-2507-GGUF
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-07-14 13:54:06 +08:00
commit 625430cf6c
28 changed files with 293 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

47
.gitattributes vendored Normal file
View File

@@ -0,0 +1,47 @@
*.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
*.gguf* 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

3
Qwen_Qwen3-4B-Instruct-2507-IQ2_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2b576b3c5483dd8a87eca98d84f83c653a755ccb48ab31b6567a69e207ee233b
size 1512983776

3
Qwen_Qwen3-4B-Instruct-2507-IQ3_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b458203e8ad6d3f9b82c1190cbd77e8502f4f763985cefdbe85ed18947fcac9d
size 1962896096

3
Qwen_Qwen3-4B-Instruct-2507-IQ3_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:8192110d563f7f7bfde15a961c5cc6a86cc8db38f4d83d11f904ae745a2dc411
size 1814375136

3
Qwen_Qwen3-4B-Instruct-2507-IQ3_XXS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:fbb60c3369dec665b2f922dd027464f1c1e5c1e1af62b48f34d9dc811404c65f
size 1670188256

3
Qwen_Qwen3-4B-Instruct-2507-IQ4_NL.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:8bcd60be4de4e2423cfa8db4f3207e54602bf85584b97ef364be044bfd9826ac
size 2381343456

3
Qwen_Qwen3-4B-Instruct-2507-IQ4_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c33ca3b360e1b2f018e31bead52888e83566bb22fc9ef783efa991a00364420d
size 2270751456

3
Qwen_Qwen3-4B-Instruct-2507-Q2_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:7f9efe8a86c1d200139801642dcf8c0d9f2cf09c89ef4e8f0ea525536368c4ca
size 1669499616

3
Qwen_Qwen3-4B-Instruct-2507-Q2_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:be4d99fbd1139f0b9a9fd44dae65ed0a4523df39112211cf87bbea1a1ac9b842
size 1763699936

3
Qwen_Qwen3-4B-Instruct-2507-Q3_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c2e1b8c30d2ba9ea7957ae6e201cef5296766281e0fcba100048335c0c799bc5
size 2239785696

3
Qwen_Qwen3-4B-Instruct-2507-Q3_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:35295e9a0a42eff5ebc592412c754991c0b6cc36bf4f282b2a491b211476752d
size 2075618016

3
Qwen_Qwen3-4B-Instruct-2507-Q3_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:68e5c8cb8ac33cb5b86c1dc31885a772782b42699d144fcfbe353489d9b289db
size 1886997216

3
Qwen_Qwen3-4B-Instruct-2507-Q3_K_XL.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:6bd04c2178d45160802b813a0e0cc82553ce84a6db7ed6615aac858f4551415c
size 2333986016

3
Qwen_Qwen3-4B-Instruct-2507-Q4_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b2198e1e35b98e2e126a00d9e853a53bc3a4bcca5f82cfbf2a03b38a91f2662c
size 2375772896

3
Qwen_Qwen3-4B-Instruct-2507-Q4_1.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2c6d59300fe2abd6d68883fe0af72e5b528aa275cd5e8bed7d73ff38ba920f22
size 2596629216

3
Qwen_Qwen3-4B-Instruct-2507-Q4_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:438820a7284cab964b48312bd4750ca35627e5e74dc51d05bd4efa3cb8616d1a
size 2591481056

3
Qwen_Qwen3-4B-Instruct-2507-Q4_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2fde00ce69dd4899c70d020845e2638353015bba0fdf161b3eb965f2bca4464e
size 2497280736

3
Qwen_Qwen3-4B-Instruct-2507-Q4_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:952af947c6aabf7b72f7d8e279e76f7bf4b0d12431eb3abb588ef312865622d8
size 2383309536

3
Qwen_Qwen3-4B-Instruct-2507-Q5_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:396a1eaba8407efe0ca6d91fc5a9d4e2f64714db64380fd5166ad0005dc1da5d
size 2983714016

3
Qwen_Qwen3-4B-Instruct-2507-Q5_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:66713ce35a58a82fe87642d4ec13425bf9b9a46800fff5c49a665ef5701439dc
size 2889513696

3
Qwen_Qwen3-4B-Instruct-2507-Q5_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2c43a3155890ec4543dc5868e3859a2eca19b708bc1efd7bf0c0af3f057268d2
size 2823711456

3
Qwen_Qwen3-4B-Instruct-2507-Q6_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:324bcc583feabe9485df2521099bf913e2613048e7aa2bdcdbfe74f1acc7531e
size 3306261216

3
Qwen_Qwen3-4B-Instruct-2507-Q6_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a3ca50571641ea44bc0c3c63901eb29cc1b641e327242e0a5e5a95690f7ec3c5
size 3400461536

3
Qwen_Qwen3-4B-Instruct-2507-Q8_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:260b5b5b6ad73e44df81a43ea1f5c11c37007b6bac18eb3cd2016e8667c19662
size 4280405216

3
Qwen_Qwen3-4B-Instruct-2507-bf16.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:75c31072dd3f6a5f2d3cdf13f1c72f61fddc1dd084b77a50620b289d71521774
size 8051284928

3
Qwen_Qwen3-4B-Instruct-2507-imatrix.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:82f4b42f83986c180f866551e24d227bbc5a3aba7263c3282a44580d818b9ce2
size 3872640

170
README.md Normal file
View File

@@ -0,0 +1,170 @@
---
quantized_by: bartowski
pipeline_tag: text-generation
base_model_relation: quantized
base_model: Qwen/Qwen3-4B-Instruct-2507
---
## Llamacpp imatrix Quantizations of Qwen3-4B-Instruct-2507 by Qwen
Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b6096">b6096</a> for quantization.
Original model: https://huggingface.co/Qwen/Qwen3-4B-Instruct-2507
All quants made using imatrix option with dataset from [here](https://gist.github.com/bartowski1182/eb213dccb3571f863da82e99418f81e8)
Run them in [LM Studio](https://lmstudio.ai/)
Run them directly with [llama.cpp](https://github.com/ggerganov/llama.cpp), or any other llama.cpp based project
## Prompt format
```
<|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 |
| -------- | ---------- | --------- | ----- | ----------- |
| [Qwen3-4B-Instruct-2507-bf16.gguf](https://huggingface.co/bartowski/Qwen_Qwen3-4B-Instruct-2507-GGUF/blob/main/Qwen_Qwen3-4B-Instruct-2507-bf16.gguf) | bf16 | 8.05GB | false | Full BF16 weights. |
| [Qwen3-4B-Instruct-2507-Q8_0.gguf](https://huggingface.co/bartowski/Qwen_Qwen3-4B-Instruct-2507-GGUF/blob/main/Qwen_Qwen3-4B-Instruct-2507-Q8_0.gguf) | Q8_0 | 4.28GB | false | Extremely high quality, generally unneeded but max available quant. |
| [Qwen3-4B-Instruct-2507-Q6_K_L.gguf](https://huggingface.co/bartowski/Qwen_Qwen3-4B-Instruct-2507-GGUF/blob/main/Qwen_Qwen3-4B-Instruct-2507-Q6_K_L.gguf) | Q6_K_L | 3.40GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. |
| [Qwen3-4B-Instruct-2507-Q6_K.gguf](https://huggingface.co/bartowski/Qwen_Qwen3-4B-Instruct-2507-GGUF/blob/main/Qwen_Qwen3-4B-Instruct-2507-Q6_K.gguf) | Q6_K | 3.31GB | false | Very high quality, near perfect, *recommended*. |
| [Qwen3-4B-Instruct-2507-Q5_K_L.gguf](https://huggingface.co/bartowski/Qwen_Qwen3-4B-Instruct-2507-GGUF/blob/main/Qwen_Qwen3-4B-Instruct-2507-Q5_K_L.gguf) | Q5_K_L | 2.98GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. |
| [Qwen3-4B-Instruct-2507-Q5_K_M.gguf](https://huggingface.co/bartowski/Qwen_Qwen3-4B-Instruct-2507-GGUF/blob/main/Qwen_Qwen3-4B-Instruct-2507-Q5_K_M.gguf) | Q5_K_M | 2.89GB | false | High quality, *recommended*. |
| [Qwen3-4B-Instruct-2507-Q5_K_S.gguf](https://huggingface.co/bartowski/Qwen_Qwen3-4B-Instruct-2507-GGUF/blob/main/Qwen_Qwen3-4B-Instruct-2507-Q5_K_S.gguf) | Q5_K_S | 2.82GB | false | High quality, *recommended*. |
| [Qwen3-4B-Instruct-2507-Q4_1.gguf](https://huggingface.co/bartowski/Qwen_Qwen3-4B-Instruct-2507-GGUF/blob/main/Qwen_Qwen3-4B-Instruct-2507-Q4_1.gguf) | Q4_1 | 2.60GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. |
| [Qwen3-4B-Instruct-2507-Q4_K_L.gguf](https://huggingface.co/bartowski/Qwen_Qwen3-4B-Instruct-2507-GGUF/blob/main/Qwen_Qwen3-4B-Instruct-2507-Q4_K_L.gguf) | Q4_K_L | 2.59GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. |
| [Qwen3-4B-Instruct-2507-Q4_K_M.gguf](https://huggingface.co/bartowski/Qwen_Qwen3-4B-Instruct-2507-GGUF/blob/main/Qwen_Qwen3-4B-Instruct-2507-Q4_K_M.gguf) | Q4_K_M | 2.50GB | false | Good quality, default size for most use cases, *recommended*. |
| [Qwen3-4B-Instruct-2507-Q4_K_S.gguf](https://huggingface.co/bartowski/Qwen_Qwen3-4B-Instruct-2507-GGUF/blob/main/Qwen_Qwen3-4B-Instruct-2507-Q4_K_S.gguf) | Q4_K_S | 2.38GB | false | Slightly lower quality with more space savings, *recommended*. |
| [Qwen3-4B-Instruct-2507-Q4_0.gguf](https://huggingface.co/bartowski/Qwen_Qwen3-4B-Instruct-2507-GGUF/blob/main/Qwen_Qwen3-4B-Instruct-2507-Q4_0.gguf) | Q4_0 | 2.38GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. |
| [Qwen3-4B-Instruct-2507-IQ4_NL.gguf](https://huggingface.co/bartowski/Qwen_Qwen3-4B-Instruct-2507-GGUF/blob/main/Qwen_Qwen3-4B-Instruct-2507-IQ4_NL.gguf) | IQ4_NL | 2.38GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. |
| [Qwen3-4B-Instruct-2507-Q3_K_XL.gguf](https://huggingface.co/bartowski/Qwen_Qwen3-4B-Instruct-2507-GGUF/blob/main/Qwen_Qwen3-4B-Instruct-2507-Q3_K_XL.gguf) | Q3_K_XL | 2.33GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. |
| [Qwen3-4B-Instruct-2507-IQ4_XS.gguf](https://huggingface.co/bartowski/Qwen_Qwen3-4B-Instruct-2507-GGUF/blob/main/Qwen_Qwen3-4B-Instruct-2507-IQ4_XS.gguf) | IQ4_XS | 2.27GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
| [Qwen3-4B-Instruct-2507-Q3_K_L.gguf](https://huggingface.co/bartowski/Qwen_Qwen3-4B-Instruct-2507-GGUF/blob/main/Qwen_Qwen3-4B-Instruct-2507-Q3_K_L.gguf) | Q3_K_L | 2.24GB | false | Lower quality but usable, good for low RAM availability. |
| [Qwen3-4B-Instruct-2507-Q3_K_M.gguf](https://huggingface.co/bartowski/Qwen_Qwen3-4B-Instruct-2507-GGUF/blob/main/Qwen_Qwen3-4B-Instruct-2507-Q3_K_M.gguf) | Q3_K_M | 2.08GB | false | Low quality. |
| [Qwen3-4B-Instruct-2507-IQ3_M.gguf](https://huggingface.co/bartowski/Qwen_Qwen3-4B-Instruct-2507-GGUF/blob/main/Qwen_Qwen3-4B-Instruct-2507-IQ3_M.gguf) | IQ3_M | 1.96GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
| [Qwen3-4B-Instruct-2507-Q3_K_S.gguf](https://huggingface.co/bartowski/Qwen_Qwen3-4B-Instruct-2507-GGUF/blob/main/Qwen_Qwen3-4B-Instruct-2507-Q3_K_S.gguf) | Q3_K_S | 1.89GB | false | Low quality, not recommended. |
| [Qwen3-4B-Instruct-2507-IQ3_XS.gguf](https://huggingface.co/bartowski/Qwen_Qwen3-4B-Instruct-2507-GGUF/blob/main/Qwen_Qwen3-4B-Instruct-2507-IQ3_XS.gguf) | IQ3_XS | 1.81GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
| [Qwen3-4B-Instruct-2507-Q2_K_L.gguf](https://huggingface.co/bartowski/Qwen_Qwen3-4B-Instruct-2507-GGUF/blob/main/Qwen_Qwen3-4B-Instruct-2507-Q2_K_L.gguf) | Q2_K_L | 1.76GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. |
| [Qwen3-4B-Instruct-2507-IQ3_XXS.gguf](https://huggingface.co/bartowski/Qwen_Qwen3-4B-Instruct-2507-GGUF/blob/main/Qwen_Qwen3-4B-Instruct-2507-IQ3_XXS.gguf) | IQ3_XXS | 1.67GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. |
| [Qwen3-4B-Instruct-2507-Q2_K.gguf](https://huggingface.co/bartowski/Qwen_Qwen3-4B-Instruct-2507-GGUF/blob/main/Qwen_Qwen3-4B-Instruct-2507-Q2_K.gguf) | Q2_K | 1.67GB | false | Very low quality but surprisingly usable. |
| [Qwen3-4B-Instruct-2507-IQ2_M.gguf](https://huggingface.co/bartowski/Qwen_Qwen3-4B-Instruct-2507-GGUF/blob/main/Qwen_Qwen3-4B-Instruct-2507-IQ2_M.gguf) | IQ2_M | 1.51GB | 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/Qwen_Qwen3-4B-Instruct-2507-GGUF --include "Qwen_Qwen3-4B-Instruct-2507-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/Qwen_Qwen3-4B-Instruct-2507-GGUF --include "Qwen_Qwen3-4B-Instruct-2507-Q8_0/*" --local-dir ./
```
You can either specify a new local-dir (Qwen_Qwen3-4B-Instruct-2507-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, 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}