bartowski/Falcon3-3B-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/Falcon3-3B-Instruct-GGUF
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-07-28 22:21:05 +08:00
commit 73215bd42d
26 changed files with 307 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
Falcon3-3B-Instruct-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
Falcon3-3B-Instruct-Q6_K_L.gguf filter=lfs diff=lfs merge=lfs -text
Falcon3-3B-Instruct-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
Falcon3-3B-Instruct-Q5_K_L.gguf filter=lfs diff=lfs merge=lfs -text
Falcon3-3B-Instruct-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
Falcon3-3B-Instruct-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
Falcon3-3B-Instruct-Q4_K_L.gguf filter=lfs diff=lfs merge=lfs -text
Falcon3-3B-Instruct-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
Falcon3-3B-Instruct-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
Falcon3-3B-Instruct-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
Falcon3-3B-Instruct-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text
Falcon3-3B-Instruct-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
Falcon3-3B-Instruct-Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
Falcon3-3B-Instruct-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
Falcon3-3B-Instruct-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
Falcon3-3B-Instruct-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
Falcon3-3B-Instruct-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
Falcon3-3B-Instruct-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
Falcon3-3B-Instruct-Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text
Falcon3-3B-Instruct-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
Falcon3-3B-Instruct-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text
Falcon3-3B-Instruct-f16.gguf filter=lfs diff=lfs merge=lfs -text
Falcon3-3B-Instruct.imatrix filter=lfs diff=lfs merge=lfs -text

3
Falcon3-3B-Instruct-IQ2_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2dfe076c47897ddee684371e26b65dc3f78c69b7ba151d6c91eda49d143d3dab
size 1267470592

3
Falcon3-3B-Instruct-IQ3_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1f1957c541378e0bfb07485380a4d841a255dfaba70e15e988c6c3e5013efa66
size 1593692416

3
Falcon3-3B-Instruct-IQ3_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:818403bbf7bab0aa918a94b31e4241e91217d94bdbba86383d47d56c872f5790
size 1491308800

3
Falcon3-3B-Instruct-IQ4_NL.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:046c1763fcdb17be682b1eec45e46383f979b34554ef2da6e3489849309dde79
size 1924583680

3
Falcon3-3B-Instruct-IQ4_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0346c7c016c6a8bc4c81d4656410ab6d26223c3c47b6e2e230469f44f9d6a026
size 1836306688

3
Falcon3-3B-Instruct-Q2_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:6cfe3e8cdf8b0b0efb87b92b75cab4ecc2668fe0456ea5229f38868a0db583ec
size 1353879808

3
Falcon3-3B-Instruct-Q2_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:988afa54ec4045040e2a24469d9bcc6aec28288b68521bd38cd6e2acde074cec
size 1747095808

3
Falcon3-3B-Instruct-Q3_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:8840e161e92eb87f809e148db5fafcdd3b04cf71387b6bba0497abb845a0b02f
size 1781354752

3
Falcon3-3B-Instruct-Q3_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a34e02edea04abb57fb58091beebccfae3b46c10d6f143bbfbf69bd0f19c0d41
size 1673220352

3
Falcon3-3B-Instruct-Q3_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:8506bc017fecce490245144de667b8e283c0e966481597a69216f2e875b4f844
size 1549406464

3
Falcon3-3B-Instruct-Q3_K_XL.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2df8ea88dc88dec05417348fc420716a0c5eb76362f96e04ef4141932d9e7612
size 2133676288

3
Falcon3-3B-Instruct-Q4_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:71a842aae68bcf513623aac25caa4efd4885cc4b32d7b2f386d12ca2e18bf9b7
size 1928122624

3
Falcon3-3B-Instruct-Q4_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:30a0a77545e66815c771b5441d799566dc9e1823674de924645b7a184800bd3c
size 2304528640

3
Falcon3-3B-Instruct-Q4_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:6ea6cecba144fe5b711ca07ae4263ccdf6ee6419807a46220419189da8446557
size 2005684480

3
Falcon3-3B-Instruct-Q4_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:4625f5f6eab921d7a2657236aa73ce6cc430749fc313216f4b255106912be70f
size 1933234432

3
Falcon3-3B-Instruct-Q5_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3ba27374c40b6f3f417faa7d39d25ae42a83245077ec023b33a8514ed571a442
size 2567983360

3
Falcon3-3B-Instruct-Q5_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f7567d3a45b11b35390122ff5dfe3258857df4378ff1c69a8dc529bef9eaf897
size 2319470848

3
Falcon3-3B-Instruct-Q5_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:4cc2398df3c54339a606bdb07438be603240c4ddb6a2c93238e76b24dabadf5a
size 2277691648

3
Falcon3-3B-Instruct-Q6_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ca0423537676d83e8c5b5c8f5eac0e64bf052e636e4b9c367ba867c234015a38
size 2652868864

3
Falcon3-3B-Instruct-Q6_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:7e00b981f0734545ee6ff2958dc59b8fea47f2f3f20d7cb01f7c66ee89ba32e6
size 2847904000

3
Falcon3-3B-Instruct-Q8_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3ee29e5bf395568a64353d862b00ecc8f9a0501002084fba0c0254b07cad3b8a
size 3434533120

3
Falcon3-3B-Instruct-f16.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:af36dadd20254f8c7af536e984cfc719b341e38a64165020254744f26f656615
size 6460329984

3
Falcon3-3B-Instruct.imatrix Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c6d92675a9a8da4a05427cf3d14a98bcffeba46a51d1503ae1d6def485fce3ad
size 2438128

179
README.md Normal file
View File

@@ -0,0 +1,179 @@
---
quantized_by: bartowski
pipeline_tag: text-generation
language:
- en
- fr
- es
- pt
license_name: falcon-llm-license
tags:
- falcon3
license_link: https://falconllm.tii.ae/falcon-terms-and-conditions.html
license: other
base_model: tiiuae/Falcon3-3B-Instruct
---
## Llamacpp imatrix Quantizations of Falcon3-3B-Instruct
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/tiiuae/Falcon3-3B-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
```
<|system|>
{system_prompt}
<|user|>
{prompt}
<|assistant|>
```
## What's new:
Fix tokenizer
## Download a file (not the whole branch) from below:
| Filename | Quant type | File Size | Split | Description |
| -------- | ---------- | --------- | ----- | ----------- |
| [Falcon3-3B-Instruct-f16.gguf](https://huggingface.co/bartowski/Falcon3-3B-Instruct-GGUF/blob/main/Falcon3-3B-Instruct-f16.gguf) | f16 | 6.46GB | false | Full F16 weights. |
| [Falcon3-3B-Instruct-Q8_0.gguf](https://huggingface.co/bartowski/Falcon3-3B-Instruct-GGUF/blob/main/Falcon3-3B-Instruct-Q8_0.gguf) | Q8_0 | 3.43GB | false | Extremely high quality, generally unneeded but max available quant. |
| [Falcon3-3B-Instruct-Q6_K_L.gguf](https://huggingface.co/bartowski/Falcon3-3B-Instruct-GGUF/blob/main/Falcon3-3B-Instruct-Q6_K_L.gguf) | Q6_K_L | 2.85GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. |
| [Falcon3-3B-Instruct-Q6_K.gguf](https://huggingface.co/bartowski/Falcon3-3B-Instruct-GGUF/blob/main/Falcon3-3B-Instruct-Q6_K.gguf) | Q6_K | 2.65GB | false | Very high quality, near perfect, *recommended*. |
| [Falcon3-3B-Instruct-Q5_K_L.gguf](https://huggingface.co/bartowski/Falcon3-3B-Instruct-GGUF/blob/main/Falcon3-3B-Instruct-Q5_K_L.gguf) | Q5_K_L | 2.57GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. |
| [Falcon3-3B-Instruct-Q5_K_M.gguf](https://huggingface.co/bartowski/Falcon3-3B-Instruct-GGUF/blob/main/Falcon3-3B-Instruct-Q5_K_M.gguf) | Q5_K_M | 2.32GB | false | High quality, *recommended*. |
| [Falcon3-3B-Instruct-Q4_K_L.gguf](https://huggingface.co/bartowski/Falcon3-3B-Instruct-GGUF/blob/main/Falcon3-3B-Instruct-Q4_K_L.gguf) | Q4_K_L | 2.30GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. |
| [Falcon3-3B-Instruct-Q5_K_S.gguf](https://huggingface.co/bartowski/Falcon3-3B-Instruct-GGUF/blob/main/Falcon3-3B-Instruct-Q5_K_S.gguf) | Q5_K_S | 2.28GB | false | High quality, *recommended*. |
| [Falcon3-3B-Instruct-Q3_K_XL.gguf](https://huggingface.co/bartowski/Falcon3-3B-Instruct-GGUF/blob/main/Falcon3-3B-Instruct-Q3_K_XL.gguf) | Q3_K_XL | 2.13GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. |
| [Falcon3-3B-Instruct-Q4_K_M.gguf](https://huggingface.co/bartowski/Falcon3-3B-Instruct-GGUF/blob/main/Falcon3-3B-Instruct-Q4_K_M.gguf) | Q4_K_M | 2.01GB | false | Good quality, default size for most use cases, *recommended*. |
| [Falcon3-3B-Instruct-Q4_K_S.gguf](https://huggingface.co/bartowski/Falcon3-3B-Instruct-GGUF/blob/main/Falcon3-3B-Instruct-Q4_K_S.gguf) | Q4_K_S | 1.93GB | false | Slightly lower quality with more space savings, *recommended*. |
| [Falcon3-3B-Instruct-Q4_0.gguf](https://huggingface.co/bartowski/Falcon3-3B-Instruct-GGUF/blob/main/Falcon3-3B-Instruct-Q4_0.gguf) | Q4_0 | 1.93GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. |
| [Falcon3-3B-Instruct-IQ4_NL.gguf](https://huggingface.co/bartowski/Falcon3-3B-Instruct-GGUF/blob/main/Falcon3-3B-Instruct-IQ4_NL.gguf) | IQ4_NL | 1.92GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. |
| [Falcon3-3B-Instruct-IQ4_XS.gguf](https://huggingface.co/bartowski/Falcon3-3B-Instruct-GGUF/blob/main/Falcon3-3B-Instruct-IQ4_XS.gguf) | IQ4_XS | 1.84GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
| [Falcon3-3B-Instruct-Q3_K_L.gguf](https://huggingface.co/bartowski/Falcon3-3B-Instruct-GGUF/blob/main/Falcon3-3B-Instruct-Q3_K_L.gguf) | Q3_K_L | 1.78GB | false | Lower quality but usable, good for low RAM availability. |
| [Falcon3-3B-Instruct-Q2_K_L.gguf](https://huggingface.co/bartowski/Falcon3-3B-Instruct-GGUF/blob/main/Falcon3-3B-Instruct-Q2_K_L.gguf) | Q2_K_L | 1.75GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. |
| [Falcon3-3B-Instruct-Q3_K_M.gguf](https://huggingface.co/bartowski/Falcon3-3B-Instruct-GGUF/blob/main/Falcon3-3B-Instruct-Q3_K_M.gguf) | Q3_K_M | 1.67GB | false | Low quality. |
| [Falcon3-3B-Instruct-IQ3_M.gguf](https://huggingface.co/bartowski/Falcon3-3B-Instruct-GGUF/blob/main/Falcon3-3B-Instruct-IQ3_M.gguf) | IQ3_M | 1.59GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
| [Falcon3-3B-Instruct-Q3_K_S.gguf](https://huggingface.co/bartowski/Falcon3-3B-Instruct-GGUF/blob/main/Falcon3-3B-Instruct-Q3_K_S.gguf) | Q3_K_S | 1.55GB | false | Low quality, not recommended. |
| [Falcon3-3B-Instruct-IQ3_XS.gguf](https://huggingface.co/bartowski/Falcon3-3B-Instruct-GGUF/blob/main/Falcon3-3B-Instruct-IQ3_XS.gguf) | IQ3_XS | 1.49GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
| [Falcon3-3B-Instruct-Q2_K.gguf](https://huggingface.co/bartowski/Falcon3-3B-Instruct-GGUF/blob/main/Falcon3-3B-Instruct-Q2_K.gguf) | Q2_K | 1.35GB | false | Very low quality but surprisingly usable. |
| [Falcon3-3B-Instruct-IQ2_M.gguf](https://huggingface.co/bartowski/Falcon3-3B-Instruct-GGUF/blob/main/Falcon3-3B-Instruct-IQ2_M.gguf) | IQ2_M | 1.27GB | 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/Falcon3-3B-Instruct-GGUF --include "Falcon3-3B-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/Falcon3-3B-Instruct-GGUF --include "Falcon3-3B-Instruct-Q8_0/*" --local-dir ./
```
You can either specify a new local-dir (Falcon3-3B-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/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}