bartowski/Falcon3-3B-Base-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-Base-GGUF
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-09-16 06:08:12 +08:00
commit 736e81adf6
27 changed files with 302 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
Falcon3-3B-Base-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
Falcon3-3B-Base-Q6_K_L.gguf filter=lfs diff=lfs merge=lfs -text
Falcon3-3B-Base-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
Falcon3-3B-Base-Q5_K_L.gguf filter=lfs diff=lfs merge=lfs -text
Falcon3-3B-Base-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
Falcon3-3B-Base-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
Falcon3-3B-Base-Q4_K_L.gguf filter=lfs diff=lfs merge=lfs -text
Falcon3-3B-Base-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
Falcon3-3B-Base-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
Falcon3-3B-Base-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text
Falcon3-3B-Base-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
Falcon3-3B-Base-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text
Falcon3-3B-Base-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
Falcon3-3B-Base-Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
Falcon3-3B-Base-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
Falcon3-3B-Base-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
Falcon3-3B-Base-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
Falcon3-3B-Base-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
Falcon3-3B-Base-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
Falcon3-3B-Base-Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text
Falcon3-3B-Base-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
Falcon3-3B-Base-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text
Falcon3-3B-Base-f16.gguf filter=lfs diff=lfs merge=lfs -text
Falcon3-3B-Base.imatrix filter=lfs diff=lfs merge=lfs -text

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

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:27752cc926c9231468e682d907de38bc5e75f37170441fc4edadf4457554f4fb
size 1267468416

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

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:13793f045bfcfcf21b92c467e15b47b643e9cb934b27b313108a5e34b5589d28
size 1593690240

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

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:4ce2ccff870392a71674ce1a3aacf904dede4539428e734a5ba992ca55e82668
size 1491306624

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

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:62fa3a95c8652bbabcb4f58be693b88c735cb892300dd7fe9642b0ea6c4e9617
size 1924581504

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

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5fe6e18955a1acd1e1b16d475b0d0e7a4b899bf5f3b6eb3b6cc6b535bfa865b6
size 1836304512

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

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:7a0f8c916474fa39289d071d1021390c1d206cdf48fd6fc489006e34de69cba2
size 1353877632

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

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d2fe6d16ed098689057aa822f42bed40a3607e6bc709eec139a9b6899a74ddc4
size 1747093632

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

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1442d7cdfa4209b4f7bc795764bec44af964cb3dd08bf3e4b6baa91183423b6d
size 1781352576

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

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:7e69f29a6ed592ae3af58e9c8ca7af9b01ca54359ee8508879c40348882c67a3
size 1673218176

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

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:01893d7378b8626836c3b0de559077bf2069360c65ad2d4750a78576934a8234
size 1549404288

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

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c33df23f661a554a4cb858dafafe22c6c975a5927d04423525cc8c837780d9a4
size 2133674112

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

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e051bcd1378b927a4a083a53e12a191700078104cc8a49b939bbcd6be5a1ca58
size 1928120448

3
Falcon3-3B-Base-Q4_1.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f35abc6967bb1f87f5274c8448d7fa2345fe8ea980b51aff2de93faa8c2d1ecf
size 2101135488

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

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:6b1ee677ead5f2734a5ae643c2787eaab552ca8b8f1db1cf3fcf595bcd100e69
size 2304526464

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

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:fe2edfa65babd2f6d9c2847b647b831d7e1f74a4dd28810456f3654615f274d5
size 2005682304

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

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d0c4fb615e0679364c7eb4b7f1f4a18b54b31829f1f37936fb1e9e283812732c
size 1933232256

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

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:bd8c30901c3409910108f19b5bba2a5d45568def91e7e662c3f62b6a26903567
size 2567981184

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

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e6a5d6ca2b5700c2a58d5d1107867597b89955263cb4617b7af93955cbee8810
size 2319468672

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

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:43dfe47f1543fa0660b29b0dd08bc9b009d1fe11adc56783bace4d9ee995c665
size 2277689472

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

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:496dc0b28210229aa6296aa8c7a51761e50ce2d80f0a03dda1a5d7e00d276b71
size 2652866688

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

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b922221199ac74398905e766b82ea8d8ed108faab40c84e229ee2ac351f9117b
size 2847901824

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

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f828d7bf0df9f33d83a01b381b3a5b023b56a7b813449db4c54b8e8236e1a4d6
size 3434530944

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

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2bbe95388ee7baba7444485fc3807fae6774209dacfc8718b09973cb83a88c9c
size 6460327808

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

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e640102daa98ab5bf11f3afe6d78635c2af5f4235fb1716dcd3f701f5181fdb8
size 2438128

170
README.md Normal file
View File

@@ -0,0 +1,170 @@
---
quantized_by: bartowski
pipeline_tag: text-generation
license_name: falcon-llm-license
language:
- en
- fr
- es
- pt
license_link: https://falconllm.tii.ae/falcon-terms-and-conditions.html
base_model: tiiuae/Falcon3-3B-Base
license: other
tags:
- falcon3
---
## Llamacpp imatrix Quantizations of Falcon3-3B-Base
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-Base
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
No prompt format found, check original model page
## Download a file (not the whole branch) from below:
| Filename | Quant type | File Size | Split | Description |
| -------- | ---------- | --------- | ----- | ----------- |
| [Falcon3-3B-Base-f16.gguf](https://huggingface.co/bartowski/Falcon3-3B-Base-GGUF/blob/main/Falcon3-3B-Base-f16.gguf) | f16 | 6.46GB | false | Full F16 weights. |
| [Falcon3-3B-Base-Q8_0.gguf](https://huggingface.co/bartowski/Falcon3-3B-Base-GGUF/blob/main/Falcon3-3B-Base-Q8_0.gguf) | Q8_0 | 3.43GB | false | Extremely high quality, generally unneeded but max available quant. |
| [Falcon3-3B-Base-Q6_K_L.gguf](https://huggingface.co/bartowski/Falcon3-3B-Base-GGUF/blob/main/Falcon3-3B-Base-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-Base-Q6_K.gguf](https://huggingface.co/bartowski/Falcon3-3B-Base-GGUF/blob/main/Falcon3-3B-Base-Q6_K.gguf) | Q6_K | 2.65GB | false | Very high quality, near perfect, *recommended*. |
| [Falcon3-3B-Base-Q5_K_L.gguf](https://huggingface.co/bartowski/Falcon3-3B-Base-GGUF/blob/main/Falcon3-3B-Base-Q5_K_L.gguf) | Q5_K_L | 2.57GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. |
| [Falcon3-3B-Base-Q5_K_M.gguf](https://huggingface.co/bartowski/Falcon3-3B-Base-GGUF/blob/main/Falcon3-3B-Base-Q5_K_M.gguf) | Q5_K_M | 2.32GB | false | High quality, *recommended*. |
| [Falcon3-3B-Base-Q4_K_L.gguf](https://huggingface.co/bartowski/Falcon3-3B-Base-GGUF/blob/main/Falcon3-3B-Base-Q4_K_L.gguf) | Q4_K_L | 2.30GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. |
| [Falcon3-3B-Base-Q5_K_S.gguf](https://huggingface.co/bartowski/Falcon3-3B-Base-GGUF/blob/main/Falcon3-3B-Base-Q5_K_S.gguf) | Q5_K_S | 2.28GB | false | High quality, *recommended*. |
| [Falcon3-3B-Base-Q3_K_XL.gguf](https://huggingface.co/bartowski/Falcon3-3B-Base-GGUF/blob/main/Falcon3-3B-Base-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-Base-Q4_1.gguf](https://huggingface.co/bartowski/Falcon3-3B-Base-GGUF/blob/main/Falcon3-3B-Base-Q4_1.gguf) | Q4_1 | 2.10GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. |
| [Falcon3-3B-Base-Q4_K_M.gguf](https://huggingface.co/bartowski/Falcon3-3B-Base-GGUF/blob/main/Falcon3-3B-Base-Q4_K_M.gguf) | Q4_K_M | 2.01GB | false | Good quality, default size for most use cases, *recommended*. |
| [Falcon3-3B-Base-Q4_K_S.gguf](https://huggingface.co/bartowski/Falcon3-3B-Base-GGUF/blob/main/Falcon3-3B-Base-Q4_K_S.gguf) | Q4_K_S | 1.93GB | false | Slightly lower quality with more space savings, *recommended*. |
| [Falcon3-3B-Base-Q4_0.gguf](https://huggingface.co/bartowski/Falcon3-3B-Base-GGUF/blob/main/Falcon3-3B-Base-Q4_0.gguf) | Q4_0 | 1.93GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. |
| [Falcon3-3B-Base-IQ4_NL.gguf](https://huggingface.co/bartowski/Falcon3-3B-Base-GGUF/blob/main/Falcon3-3B-Base-IQ4_NL.gguf) | IQ4_NL | 1.92GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. |
| [Falcon3-3B-Base-IQ4_XS.gguf](https://huggingface.co/bartowski/Falcon3-3B-Base-GGUF/blob/main/Falcon3-3B-Base-IQ4_XS.gguf) | IQ4_XS | 1.84GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
| [Falcon3-3B-Base-Q3_K_L.gguf](https://huggingface.co/bartowski/Falcon3-3B-Base-GGUF/blob/main/Falcon3-3B-Base-Q3_K_L.gguf) | Q3_K_L | 1.78GB | false | Lower quality but usable, good for low RAM availability. |
| [Falcon3-3B-Base-Q2_K_L.gguf](https://huggingface.co/bartowski/Falcon3-3B-Base-GGUF/blob/main/Falcon3-3B-Base-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-Base-Q3_K_M.gguf](https://huggingface.co/bartowski/Falcon3-3B-Base-GGUF/blob/main/Falcon3-3B-Base-Q3_K_M.gguf) | Q3_K_M | 1.67GB | false | Low quality. |
| [Falcon3-3B-Base-IQ3_M.gguf](https://huggingface.co/bartowski/Falcon3-3B-Base-GGUF/blob/main/Falcon3-3B-Base-IQ3_M.gguf) | IQ3_M | 1.59GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
| [Falcon3-3B-Base-Q3_K_S.gguf](https://huggingface.co/bartowski/Falcon3-3B-Base-GGUF/blob/main/Falcon3-3B-Base-Q3_K_S.gguf) | Q3_K_S | 1.55GB | false | Low quality, not recommended. |
| [Falcon3-3B-Base-IQ3_XS.gguf](https://huggingface.co/bartowski/Falcon3-3B-Base-GGUF/blob/main/Falcon3-3B-Base-IQ3_XS.gguf) | IQ3_XS | 1.49GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
| [Falcon3-3B-Base-Q2_K.gguf](https://huggingface.co/bartowski/Falcon3-3B-Base-GGUF/blob/main/Falcon3-3B-Base-Q2_K.gguf) | Q2_K | 1.35GB | false | Very low quality but surprisingly usable. |
| [Falcon3-3B-Base-IQ2_M.gguf](https://huggingface.co/bartowski/Falcon3-3B-Base-GGUF/blob/main/Falcon3-3B-Base-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-Base-GGUF --include "Falcon3-3B-Base-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-Base-GGUF --include "Falcon3-3B-Base-Q8_0/*" --local-dir ./
```
You can either specify a new local-dir (Falcon3-3B-Base-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}