FitMyLLM
APPLE· M5

Apple M5 (16GB)

USABLE MEMORY
10.7 GB
ENTRY-LEVEL
BANDWIDTH
120
GB/S
MODELS Q4
233/449
52%
7B Q4 SPEED
~15
GOOD
▸ MODEL COVERAGE @ Q452% OF ALL
▸ ESTIMATED SPEED· BY MODEL SIZE @ Q4

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

3B
~36
TOK/S
7B
~15
TOK/S
14B
~8
TOK/S
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
10.7 GB of 16
BANDWIDTH
120 GB/s
FP16 COMPUTE
5.5 TFLOPS
TDP
15W
MEMORY
Unified
ARCHITECTURE
M5
89
FAST MODELS · >30 TOK/S
Real-time chat speed
221
USABLE · >10 TOK/S
Comfortable for all tasks
233
TOTAL COMPATIBLE
Fit in usable memory at Q4
▸ DON’T WANT TO BUY?

Test M5 (16GB) (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· 233
S
Falcon-H1R Tiny 90M0.09B
FALCON·256K CTX· CHAT· REASONING
1185
TOK/S · 5% MEM
S
SmolLM2 135M0.135B
SMOLLM·2K CTX· CHAT
790
TOK/S · 5% MEM
S
nomic-embed-text-v1.5 100M0.14B
EMBEDDING·8K CTX· CHAT
762
TOK/S · 5% MEM
S
GPT-2 124M0.14B
GPT2·1K CTX· CHAT
762
TOK/S · 5% MEM
S
SmolVLM 256M0.256B
SMOLLM·8K CTX· CHAT· VISION
417
TOK/S · 6% MEM
S
Gemma 3 270M0.27B
GEMMA·32K CTX· CHAT
395
TOK/S · 6% MEM
S
Snowflake Arctic Embed M v2.00.305B
EMBEDDING·8K CTX· EMBEDDING· MULTILINGUAL
350
TOK/S · 6% MEM
S
bge-large-en-v1.5 335M0.335B
EMBEDDING·1K CTX· CHAT
318
TOK/S · 7% MEM
S
mxbai-embed-large-v10.335B
EMBEDDING·1K CTX· EMBEDDING
318
TOK/S · 7% MEM
S
Snowflake Arctic Embed L0.335B
EMBEDDING·1K CTX· EMBEDDING
318
TOK/S · 7% MEM
S
LFM2 350M0.35B
LFM·125K CTX· CHAT· TOOL_USE
305
TOK/S · 7% MEM
S
SmolLM2 360M0.36B
SMOLLM·8K CTX· CHAT
296
TOK/S · 7% MEM
S
GPT-2 Medium 345M0.38B
GPT2·1K CTX· CHAT
281
TOK/S · 7% MEM
S
Qwen 2.5 0.5B0.5B
QWEN·32K CTX· CHAT
213
TOK/S · 7% MEM
S
SmolVLM 500M0.5B
SMOLLM·8K CTX· CHAT· VISION
213
TOK/S · 7% MEM
S
Falcon-H1 0.5B0.52B
FALCON·128K CTX· CHAT
205
TOK/S · 8% MEM
S
BGE-M30.568B
EMBEDDING·8K CTX· EMBEDDING
188
TOK/S · 8% MEM
S
Snowflake Arctic Embed L v2.00.568B
EMBEDDING·8K CTX· EMBEDDING· MULTILINGUAL
188
TOK/S · 8% MEM
S
Qwen3-Embedding 0.6B0.6B
EMBEDDING·32K CTX· EMBEDDING· MULTILINGUAL
178
TOK/S · 8% MEM
S
Falcon-H1R Tiny 0.6B0.6B
FALCON·32K CTX· CHAT· REASONING
178
TOK/S · 8% MEM
S
Falcon Perception 0.6B0.6B
FALCON·4K CTX· VISION
178
TOK/S · 8% MEM
S
Qwen 1.5 0.5B0.62B
QWEN·32K CTX· CHAT
172
TOK/S · 8% MEM
S
LFM2 700M0.74B
LFM·125K CTX· CHAT· TOOL_USE
144
TOK/S · 9% MEM
S
Qwen3 0.6B0.75B
QWEN·32K CTX· CHAT· REASONING
142
TOK/S · 9% MEM
S
GPT-2 Large 774M0.81B
GPT2·1K CTX· CHAT
132
TOK/S · 9% MEM
S
Qwen 3.5 0.8B0.87B
QWEN·256K CTX· CHAT· CODING· MULTILINGUAL
123
TOK/S · 10% MEM
S
InternVL3 1B0.94B
OTHER·32K CTX· CHAT· VISION
113
TOK/S · 10% MEM
S
MiniCPM5 1B1.08B
MINICPM·128K CTX· CHAT· REASONING· MULTILINGUAL
99
TOK/S · 11% MEM
S
TinyLlama 1.1B1.1B
LLAMA·2K CTX· CHAT
97
TOK/S · 11% MEM
S
LFM2.5-1.2B-Thinking1.2B
LFM·122K CTX· CHAT· REASONING· TOOL_USE
89
TOK/S · 11% MEM
S
Llama-3.2-1B1.2B
LLAMA·4K CTX· CHAT
89
TOK/S · 11% MEM
S
LFM2 1.2B1.2B
LFM·125K CTX· CHAT· TOOL_USE· MULTILINGUAL
89
TOK/S · 11% MEM
S
Zamba2 1.2B1.2B
OTHER·4K CTX· CHAT
89
TOK/S · 11% MEM
S
EXAONE-4.0-1.2B1.3B
EXAONE·64K CTX· CHAT
82
TOK/S · 12% MEM
S
OPT 1.3B1.3B
OPT·2K CTX· CHAT
82
TOK/S · 12% MEM
S
MiniCPM-V 4.61.3B
OTHER·256K CTX· CHAT· VISION
82
TOK/S · 12% MEM
S
DeepSeek Coder 1.3B1.35B
DEEPSEEK·16K CTX· CODING
79
TOK/S · 12% MEM
S
Phi-1 1.3B1.42B
PHI·2K CTX· CODING
75
TOK/S · 13% MEM
S
Phi-1.5 1.3B1.42B
PHI·2K CTX· CHAT· CODING
75
TOK/S · 13% MEM
S
LFM2 8B A1B8.3BMoE
LFM·125K CTX· CHAT· TOOL_USE· MULTILINGUAL
71
TOK/S · 52% MEM
▸ NEXT STEP

Get personalized recommendations.

See ranked models with benchmark scores, run commands, and precise speed estimates for your Apple M5 (16GB).

WHAT THIS CARD IS WORTH

M5 (16GB) holds 233 of the models in our catalogue and is, in practice, a IQ4_XS card — the largest it takes is Phi-3-medium-14b at IQ4_XS.

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
Phi-3-medium-14b14B · IQ4_XS9.4 GB12 tok/sEST
Ministral 3 14B Reasoning13.95B · IQ4_XS9.3 GB12 tok/sEST
Mistral-Nemo 12.2B12.2B · Q4_K_M9.0 GB12 tok/sEST
Dolly v2 12B12B · Q4_K_M9.1 GB12 tok/sEST
StableLM 2 12B12B · Q4_K_M9.0 GB12 tok/sEST
Falcon2 11B11B · Q5_K_S9.5 GB12 tok/sEST
Llama-3.2-11B-Vision-Instruct11B · Q4_K_S9.4 GB14 tok/sEST
SOLAR-10.7B10.7B · Q5_K_M9.3 GB12 tok/sEST
AGAINST CARDS OF SIMILAR MEMORY
M3 Pro (18GB)12 GB$1,5991.5 tok/s per $100
M1 Pro (16GB)11 GB$9992.9 tok/s per $100
M2 Pro (16GB)11 GB$1,2992.2 tok/s per $100
M5 (16GB)11 GB
M4 (16GB)11 GB$4994.0 tok/s per $100

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 M5 (16GB) — 16 GB unified, 10.7 GB usable.

APPLE M5 (16GB) SPEC
BRAND
Apple
UNIFIED MEMORY
16 GB
USABLE BY A MODEL
10.7 GB
BANDWIDTH
120 GB/s
FP16 COMPUTE
5.5 TFLOPS
TDP
15 W
ARCHITECTURE
M5
▸ AI CAPABILITY
233/ 449 models @ Q4

With 10.7 GB of its 16 GB reaching a model and 120 GB/s bandwidth, this machine handles models up to 13B parameters.

Speed ≈ bandwidth / model_size × efficiency. A 7B model at Q4 runs at ~14 tok/s.

RENT IT — LIVE PRICES
Checking what the clouds are charging…
§ 01TOP MODELS FOR APPLE M5 (16GB)
233 FIT · SHOWING 20
MODELSIZEVRAM Q4TOK/SAVG
Baichuan2 13B13B8.4 GB823.6
Llama 2 13B13B8.4 GB817.2
CodeLlama 13B13B8.4 GB819.7
Vicuna 13B13B8.4 GB811.8
LLaMA 1 13B13B8.4 GB832.9
OPT 13B13B8.4 GB835.8
Orca 2 13B13B8.4 GB825.4
WizardCoder Python 13B13B8.4 GB860.1
WizardLM 13B13B8.4 GB819.5
Mistral-Nemo 12.2B12.2B7.9 GB922.4
Dolly v2 12B12B7.8 GB96.4
StableLM 2 12B12B7.8 GB921.3
Falcon2 11B11B7.2 GB1033.2
SOLAR-10.7B10.7B7.0 GB1028.2
Falcon3-10B10.3B6.8 GB1038.2
GLM-4.1V 9B Thinking10.29B6.8 GB10
Bamba 9B v29.78B6.5 GB1126.1
Qwen 3.5 9B9.65B6.4 GB1150.6
RecurrentGemma 9B9.63B6.4 GB1135.0
glm-4-9b9.4B6.2 GB1120.5