News:

Willkommen im Notebookcheck.com Forum! Hier können Sie über alle unsere Artikel und allgemein über notebookrelevante Dinge diskutieren. Viel Spass!

Main Menu

Post reply

Other options
Verification:
Please leave this box empty:
Shortcuts: ALT+S post or ALT+P preview

Topic summary

Posted by OLED 90 Hz when, APPLE
 - Today at 08:26:38
Supposedly BetterDisplay and Stillcolor (note: github.com/aiaf/Stillcolor/issues/27) can disable FRC.
Posted by OLED 90 Hz when, APPLE
 - Today at 08:17:35
Quote from: QuantumDot on Today at 05:47:15* FRC
* Temporal dithering
* KSF phosphor filter
Maybe going OLED can fix it [and not using PWM].

Also, would u bet ur life that you can notice FRC/temporal dithering most of the time?

Also, maybe Apple's implementation of these is made in such a way, that it's less on the eyes, because I can imagine Apple would care and minimize it, if it's a big issue?
Posted by QuantumDot
 - Today at 05:47:15
This laptop may not have PWM, but that is not the only eye strain factor.

There are also:

* FRC
* Temporal dithering
* KSF phosphor filter
Posted by Annabel_S
 - April 15, 2026, 10:17:49
You got the screen resolution wrong. It is 2880 x 1864.
Posted by some llama.cpp benchmarks
 - April 12, 2026, 12:36:48
On battery saving mode (for no battery saving mode, you guessed it, just like above, multiply by ~2):
Code Select
/Users/../llama-b8740/llama-bench --no-warmup -m /Users/../Qwen3.5-9B-UD-Q4_K_XL.gguf -p 64 -n 64 -t 1-12

| model                          |      size |    params | backend    | threads |            test |                  t/s |
| ------------------------------ | ---------: | ---------: | ---------- | ------: | --------------: | -------------------: |
| qwen35 9B Q4_K - Medium        |  5.55 GiB |    8.95 B | MTL,BLAS  |      1 |            pp64 |        107.20 ± 6.39 |
| qwen35 9B Q4_K - Medium        |  5.55 GiB |    8.95 B | MTL,BLAS  |      1 |            tg64 |          9.75 ± 0.06 |
| qwen35 9B Q4_K - Medium        |  5.55 GiB |    8.95 B | MTL,BLAS  |      2 |            pp64 |        109.29 ± 0.92 |
| qwen35 9B Q4_K - Medium        |  5.55 GiB |    8.95 B | MTL,BLAS  |      2 |            tg64 |          9.62 ± 0.01 |
| qwen35 9B Q4_K - Medium        |  5.55 GiB |    8.95 B | MTL,BLAS  |      3 |            pp64 |        109.05 ± 0.96 |
| qwen35 9B Q4_K - Medium        |  5.55 GiB |    8.95 B | MTL,BLAS  |      3 |            tg64 |          9.47 ± 0.00 |
| qwen35 9B Q4_K - Medium        |  5.55 GiB |    8.95 B | MTL,BLAS  |      4 |            pp64 |        108.81 ± 0.81 |
| qwen35 9B Q4_K - Medium        |  5.55 GiB |    8.95 B | MTL,BLAS  |      4 |            tg64 |          9.23 ± 0.13 |
| qwen35 9B Q4_K - Medium        |  5.55 GiB |    8.95 B | MTL,BLAS  |      5 |            pp64 |        108.59 ± 0.62 |
| qwen35 9B Q4_K - Medium        |  5.55 GiB |    8.95 B | MTL,BLAS  |      5 |            tg64 |          9.20 ± 0.01 |
| qwen35 9B Q4_K - Medium        |  5.55 GiB |    8.95 B | MTL,BLAS  |      6 |            pp64 |        108.57 ± 1.21 |
| qwen35 9B Q4_K - Medium        |  5.55 GiB |    8.95 B | MTL,BLAS  |      6 |            tg64 |          9.12 ± 0.01 |
| qwen35 9B Q4_K - Medium        |  5.55 GiB |    8.95 B | MTL,BLAS  |      7 |            pp64 |        108.34 ± 1.24 |
| qwen35 9B Q4_K - Medium        |  5.55 GiB |    8.95 B | MTL,BLAS  |      7 |            tg64 |          9.02 ± 0.04 |
| qwen35 9B Q4_K - Medium        |  5.55 GiB |    8.95 B | MTL,BLAS  |      8 |            pp64 |        108.07 ± 1.57 |
| qwen35 9B Q4_K - Medium        |  5.55 GiB |    8.95 B | MTL,BLAS  |      8 |            tg64 |          8.97 ± 0.01 |
| qwen35 9B Q4_K - Medium        |  5.55 GiB |    8.95 B | MTL,BLAS  |      9 |            pp64 |        107.81 ± 0.76 |
| qwen35 9B Q4_K - Medium        |  5.55 GiB |    8.95 B | MTL,BLAS  |      9 |            tg64 |          8.76 ± 0.15 |
| qwen35 9B Q4_K - Medium        |  5.55 GiB |    8.95 B | MTL,BLAS  |      10 |            pp64 |        107.75 ± 0.58 |
| qwen35 9B Q4_K - Medium        |  5.55 GiB |    8.95 B | MTL,BLAS  |      10 |            tg64 |          8.82 ± 0.03 |
| qwen35 9B Q4_K - Medium        |  5.55 GiB |    8.95 B | MTL,BLAS  |      11 |            pp64 |        107.64 ± 0.44 |
| qwen35 9B Q4_K - Medium        |  5.55 GiB |    8.95 B | MTL,BLAS  |      11 |            tg64 |          8.71 ± 0.03 |
| qwen35 9B Q4_K - Medium        |  5.55 GiB |    8.95 B | MTL,BLAS  |      12 |            pp64 |        107.18 ± 0.34 |
| qwen35 9B Q4_K - Medium        |  5.55 GiB |    8.95 B | MTL,BLAS  |      12 |            tg64 |          8.67 ± 0.05 |
This confirms that the number of threads doesn't matter. On my desktop 7800X3D 4 threads gives pretty much the fastest tokens per second.
Posted by some llama.cpp benchmarks
 - April 10, 2026, 16:59:33
First I confirmed that the CPU and GPU scores of my new Air 15 M5 align with what is expected.

Here are some llama.cpp's llama-bench benchmarks:
First with battery saving mode on:
Code Select
/Users/../llama-b8740/llama-bench --no-warmup -m /Users/../Qwen3.5-9B-UD-Q4_K_XL.gguf -p 128 -n 256 -t 1,2,3,4
ggml_metal_device_init: testing tensor API for f16 support
ggml_metal_library_init_from_source: error compiling source
ggml_metal_device_init: - the tensor API is not supported in this environment - disabling
ggml_metal_library_init: using embedded metal library
ggml_metal_library_init: loaded in 0.013 sec
ggml_metal_rsets_init: creating a residency set collection (keep_alive = 180 s)
ggml_metal_device_init: GPU name:  MTL0
ggml_metal_device_init: GPU family: MTLGPUFamilyApple10  (1010)
ggml_metal_device_init: GPU family: MTLGPUFamilyCommon3 (3003)
ggml_metal_device_init: GPU family: MTLGPUFamilyMetal4  (5002)
ggml_metal_device_init: simdgroup reduction  = true
ggml_metal_device_init: simdgroup matrix mul. = true
ggml_metal_device_init: has unified memory    = true
ggml_metal_device_init: has bfloat            = true
ggml_metal_device_init: has tensor            = false
ggml_metal_device_init: use residency sets    = true
ggml_metal_device_init: use shared buffers    = true
ggml_metal_device_init: recommendedMaxWorkingSetSize  = 12713.12 MB
| model                          |      size |    params | backend    | threads |            test |                  t/s |
| ------------------------------ | ---------: | ---------: | ---------- | ------: | --------------: | -------------------: |
| qwen35 9B Q4_K - Medium        |  5.55 GiB |    8.95 B | MTL,BLAS  |      1 |          pp128 |        110.11 ± 4.18 |
| qwen35 9B Q4_K - Medium        |  5.55 GiB |    8.95 B | MTL,BLAS  |      1 |          tg256 |          9.50 ± 0.30 |
| qwen35 9B Q4_K - Medium        |  5.55 GiB |    8.95 B | MTL,BLAS  |      2 |          pp128 |        107.58 ± 6.53 |
| qwen35 9B Q4_K - Medium        |  5.55 GiB |    8.95 B | MTL,BLAS  |      2 |          tg256 |          9.45 ± 0.08 |
| qwen35 9B Q4_K - Medium        |  5.55 GiB |    8.95 B | MTL,BLAS  |      3 |          pp128 |        110.79 ± 1.14 |
| qwen35 9B Q4_K - Medium        |  5.55 GiB |    8.95 B | MTL,BLAS  |      3 |          tg256 |          9.29 ± 0.09 |
| qwen35 9B Q4_K - Medium        |  5.55 GiB |    8.95 B | MTL,BLAS  |      4 |          pp128 |        110.78 ± 1.42 |
| qwen35 9B Q4_K - Medium        |  5.55 GiB |    8.95 B | MTL,BLAS  |      4 |          tg256 |          8.75 ± 0.95 |With the default no battery saving mode:
Code Select
/Users/../llama-b8740/llama-bench --no-warmup -m /Users/../Qwen3.5-9B-UD-Q4_K_XL.gguf -p 128 -n 256 -t 1,2,3,4
[..]
| model                          |      size |    params | backend    | threads |            test |                  t/s |
| ------------------------------ | ---------: | ---------: | ---------- | ------: | --------------: | -------------------: |
| qwen35 9B Q4_K - Medium        |  5.55 GiB |    8.95 B | MTL,BLAS  |      1 |          pp128 |        216.04 ± 8.47 |
| qwen35 9B Q4_K - Medium        |  5.55 GiB |    8.95 B | MTL,BLAS  |      1 |          tg256 |        20.17 ± 0.04 |
| qwen35 9B Q4_K - Medium        |  5.55 GiB |    8.95 B | MTL,BLAS  |      2 |          pp128 |        209.43 ± 0.35 |
| qwen35 9B Q4_K - Medium        |  5.55 GiB |    8.95 B | MTL,BLAS  |      2 |          tg256 |        20.21 ± 0.03 |
| qwen35 9B Q4_K - Medium        |  5.55 GiB |    8.95 B | MTL,BLAS  |      3 |          pp128 |        196.55 ± 5.79 |
| qwen35 9B Q4_K - Medium        |  5.55 GiB |    8.95 B | MTL,BLAS  |      3 |          tg256 |        18.34 ± 3.22 |
| qwen35 9B Q4_K - Medium        |  5.55 GiB |    8.95 B | MTL,BLAS  |      4 |          pp128 |        193.50 ± 2.13 |
| qwen35 9B Q4_K - Medium        |  5.55 GiB |    8.95 B | MTL,BLAS  |      4 |          tg256 |        19.57 ± 0.18 |
Posted by only bandwidth = more tg
 - March 16, 2026, 12:05:46
Or look up the 153.6 GB/s and 120 GB/s values here: en.wikipedia.org/wiki/Apple_silicon#M-series_SoCs.
Posted by only bandwidth = more tg
 - March 16, 2026, 12:04:31
As expected, a vid by Alex Ziskind (youtube.com/watch?v=XGe7ldwFLSE), in this case, proves that Apples's claim of
Quote from: en.wikipedia.org/wiki/Apple_M5#PerformancePeak GPU AI compute: over 4× faster
does not apply to running 3rd party LLMs and only the RAM/unified memory bandwidth increase increases the token generation (28% = 1.28 = 153.6 GB/s (M5) / 120 GB/s (M4)). (153.6 GB/s = 128-bit * 9600 MT/s / 1000 / 8)
Posted by Interesting for reviewers
 - March 16, 2026, 11:07:12
This may be interesting for reviewers:
Quote from: youtube.com/watch?v=HKxIGgyeISMApple's Energy Model - Deconstructed

In this video, I reverse engineer Apple's Energy Model on the Mac Studio M4 Max. In the process I explain why and how measured DC power can appear up to 3 times higher than reported M4 Max GPU power.

[..]
Posted by How tastes differ
 - March 13, 2026, 09:35:10
Quote from: juri on March 13, 2026, 03:09:11and still no matte option for the screen, so idiotic without any reason.
It's not 12W, look again. Maybe the matte coating on your screen played a prank on you ;)
And I'm so glad that it's glossy (richer colors, sharper text). Mind that while it's glossy, the anti-reflective coating/ability is very good.
Posted by juri
 - March 13, 2026, 03:09:11
12W average in idle?? how can that be, lunar lake is only a third of this.
why are you not doing the battery test with idle and video playback any more??

and still no matte option for the screen, so idiotic without any reason.
until then i wont consider an air.
Posted by Will MBAir fit 27B quants
 - March 11, 2026, 18:15:54
Quote from: not_anton on March 11, 2026, 17:16:44
Quote from: Will MBAir fit 27B quants on March 11, 2026, 12:23:33Will the 24 GB RAM option fit Qwen3.5-27B-UD-Q4_K_XL.gguf (17.6 GB) or Qwen3.5-27B-UD-Q5_K_XL.gguf (20.2 GB)? (huggingface.co/unsloth/Qwen3.5-27B-GGUF) (I know there's mlx-community/Qwen3.5-27B-4bit (16.1 GB) too, but I don't know if its perplexity is good)

I have a 15" M2 Air with 24GB RAM, but it can only run 3B models max because of overheating. Work is fine, gaming is fine, but LLMs throttle it to 0.4GHz on GPU in a minute. Sorry, you would need something with a fan or two to make those models useful.
Good to know, but will those quants fit (if I had ot guess I'd say yes)? There's also sysctl iogpu.wired_limit_mb=<MB> (I know not to assign too much to the VRAM (1-3 GB may be ok), as the OS may start to write/swap to the SSD).
Posted by not_anton
 - March 11, 2026, 17:16:44
Quote from: Will MBAir fit 27B quants on March 11, 2026, 12:23:33Will the 24 GB RAM option fit Qwen3.5-27B-UD-Q4_K_XL.gguf (17.6 GB) or Qwen3.5-27B-UD-Q5_K_XL.gguf (20.2 GB)? (huggingface.co/unsloth/Qwen3.5-27B-GGUF) (I know there's mlx-community/Qwen3.5-27B-4bit (16.1 GB) too, but I don't know if its perplexity is good)

I have a 15" M2 Air with 24GB RAM, but it can only run 3B models max because of overheating. Work is fine, gaming is fine, but LLMs throttle it to 0.4GHz on GPU in a minute. Sorry, you would need something with a fan or two to make those models useful.
Posted by Will MBAir fit 27B quants
 - March 11, 2026, 12:23:33
Will the 24 GB RAM option fit Qwen3.5-27B-UD-Q4_K_XL.gguf (17.6 GB) or Qwen3.5-27B-UD-Q5_K_XL.gguf (20.2 GB)? (huggingface.co/unsloth/Qwen3.5-27B-GGUF) (I know there's mlx-community/Qwen3.5-27B-4bit (16.1 GB) too, but I don't know if its perplexity is good)
Posted by h
 - March 09, 2026, 16:25:21
screen contrast is lower so much than m4 15 macbook air ,is a defective one or m5 just had bad panel, we need more example