FitMyLLM
APPLE· Apple GPU 4-core

Apple A14 GPU

Running LLMs on the Apple A14 GPU — the long read: which models fit at which quantisation, and the settings worth changing. · Or what a budget buys

Usable memory
1 GB
Budget
Bandwidth
25.6
GB/s
Models Q4
4/498
1%
7B Q4 speed
~3
Slow
Model coverage at Q41% of all
Estimated speed· By model size at Q4

Average speeds at Q4 quantization. Actual performance varies by model architecture and context length.

3B
—
1.7GB needed
7B
—
3.9GB needed
14B
—
7.9GB needed
32B
—
18.0GB needed
70B
—
39.4GB needed
Measured rig reports

We rent the machine and time every model on it: decode, VRAM peak, concurrency, watts and cost per million tokens. Yours may already be one of them — and two are free to read in full.

See the reports →
Specifications
Usable memory
1 GB of 4
Bandwidth
25.6 GB/s
FP16 Compute
1 TFLOPS
TDP
5W
Memory
Shared
Architecture
Apple GPU 4-core
4
Fast models · >30 tok/s
Real-time chat speed
4
Usable · >10 tok/s
Comfortable for all tasks
4
Total compatible
Fit in usable memory at Q4
Don’t want to buy?

Test A14 GPU (or anything bigger) without committing. Pay by the second, cancel anytime.

Spin up in ~60s. Pay by the second. Cancel anytime.

Some links are affiliate links — we may earn a small commission at no extra cost to you. This helps keep FitMyLLM free and independent.

Compatible models· 4
S
Falcon-H1R Tiny 90M0.09B
Falcon·256K ctx· chat· reasoning
253
tok/s · 54% mem
›
S
SmolLM2 135M0.135B
Smollm·2K ctx· chat
169
tok/s · 57% mem
›
S
nomic-embed-text-v1.5 100M0.14B
Embedding·8K ctx· chat
163
tok/s · 57% mem
›
S
GPT-2 124M0.14B
Gpt2·1K ctx· chat
163
tok/s · 57% mem
›
Next step

Get personalized recommendations.

See ranked models with benchmark scores, run commands, and precise speed estimates for your Apple A14 GPU.

What this card is worth

A14 GPU holds 4 of the models in our catalogue and is, in practice, a Q4_K_M card — the largest it takes is Qwen 3.5 0.8B at Q4_K_M.

Tokens/sec per $100
—
8B at Q4_K_M, so cards compare like for like
Usable memory per $100
—
what memory costs on this card
The biggest it takes
Qwen 3.5 0.8B0.87B · Q4_K_M0.9 GB36 tok/sest
LFM2 700M0.74B · Q4_K_M0.9 GB42 tok/sest
Falcon-H1R Tiny 0.6B0.6B · Q6_K0.9 GB39 tok/sest
Falcon Perception 0.6B0.6B · Q5_K_S0.9 GB46 tok/sest
Falcon-H1 0.5B0.52B · Q6_K0.8 GB45 tok/sest
Qwen 2.5 0.5B0.5B · Q8_00.9 GB36 tok/sest
SmolVLM 500M0.5B · Q6_K0.9 GB47 tok/sest
SmolLM2 360M0.36B · Q8_00.8 GB50 tok/sest
Against cards of similar memory
M2 (8GB)5 GB$5992.8 tok/s per $100
M3 (8GB)5 GB$5992.8 tok/s per $100
M1 (8GB)5 GB$4992.2 tok/s per $100
Radeon RX 6600S4 GB$175—
A14 GPU1 GB——

Neighbours in memory rather than in price: memory decides whether a card can do the job at all, so two cards of the same size at different prices is the comparison you are making. Ordered by memory, then bandwidth — not by the value column, which is worked out from bandwidth and price alone and therefore rewards a cheap card whatever its software stack does to that bandwidth in practice. Read it as one input, not as a ranking.

Device under test

Apple A14 GPU — 4 GB unified, 1 GB usable.

Apple A14 GPU spec
Brand
Apple
Unified memory
4 GB
Usable by a model
1 GB
Bandwidth
25.6 GB/s
FP16 Compute
1 TFLOPS
TDP
5 W
Architecture
Apple GPU 4-core
AI capability
4/ 498 models @ Q4

With 1 GB of its 4 GB reaching a model and 25.6 GB/s bandwidth, this machine handles models up to 0.14B parameters.

Speed ≈ bandwidth / model_size × efficiency. A 7B model at Q4 runs at ~3 tok/s.

Top models for Apple A14 GPU
4 fit · showing 4
ModelSizeVRAM Q4tok/sAvg
nomic-embed-text-v1.5 100M0.14B0.6 GB16348.0
GPT-2 124M0.14B0.6 GB1636.5
SmolLM2 135M0.135B0.6 GB1697.0
Falcon-H1R Tiny 90M0.09B0.5 GB253—