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
Click to view download instructions
First, make sure you have hugginface-cli installed:
You can either specify a new local-dir (Mistral-Large-Instruct-2411-Q8_0) or download them all in place (./)
Q4_0_X_X information
These are
NOT
for Metal (Apple) or GPU (nvidia/AMD/intel) offloading, only ARM chips (and certain AVX2/AVX512 CPUs).
If you're using an ARM chip, the Q4_0_X_X quants will have a substantial speedup. Check out Q4_0_4_4 speed comparisons
on the original pull request
To check which one would work best for your ARM chip, you can check
AArch64 SoC features
(thanks EloyOn!).
If you're using a CPU that supports AVX2 or AVX512 (typically server CPUs and AMD's latest Zen5 CPUs) and are not offloading to a GPU, the Q4_0_8_8 may offer a nice speed as well:
Click to view benchmarks on an AVX2 system (EPYC7702)
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
Which file should I choose?
Click here for details
A great write up with charts showing various performances is provided by Artefact2
here
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:
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.
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.
Mistral-Large-Instruct-2411-GGUF huggingface.co is an AI model on huggingface.co that provides Mistral-Large-Instruct-2411-GGUF's model effect (), which can be used instantly with this bartowski Mistral-Large-Instruct-2411-GGUF model. huggingface.co supports a free trial of the Mistral-Large-Instruct-2411-GGUF model, and also provides paid use of the Mistral-Large-Instruct-2411-GGUF. Support call Mistral-Large-Instruct-2411-GGUF model through api, including Node.js, Python, http.
Mistral-Large-Instruct-2411-GGUF huggingface.co is an online trial and call api platform, which integrates Mistral-Large-Instruct-2411-GGUF's modeling effects, including api services, and provides a free online trial of Mistral-Large-Instruct-2411-GGUF, you can try Mistral-Large-Instruct-2411-GGUF online for free by clicking the link below.
bartowski Mistral-Large-Instruct-2411-GGUF online free url in huggingface.co:
Mistral-Large-Instruct-2411-GGUF is an open source model from GitHub that offers a free installation service, and any user can find Mistral-Large-Instruct-2411-GGUF on GitHub to install. At the same time, huggingface.co provides the effect of Mistral-Large-Instruct-2411-GGUF install, users can directly use Mistral-Large-Instruct-2411-GGUF installed effect in huggingface.co for debugging and trial. It also supports api for free installation.
Mistral-Large-Instruct-2411-GGUF install url in huggingface.co: