IngiaFungua pochi

M5 Pro yenye GB 64 inaweza kuendesha nini?

Modeli huria 34 kati ya 73 zinaenda vizuri juu yake. Kwa chaguo-msingi GPU inaweza kutumia takriban GB 48 kati ya GB 64 zake, na husoma kumbukumbu kwa 307 GB/s, jambo linaloamua kasi yake ya kuandika. Inapatikana katika: MacBook Pro (14-inch, M5 Pro or M5 Max), MacBook Pro (16-inch, M5 Pro or M5 Max), Mac mini (M6 or M5 Pro).

Yenye akili zaidi inayoenda vizuriNemotron 3.5 Bolt 74B A9B4-bit · 41.6 GB · 27–48 tok/sKubwa zaidi inayoenda vizuriNemotron 3.5 Bolt 74B A9B4-bit · 41.6 GB · 27–48 tok/sKwa kuandika codeQwen3 Coder 30B A3B Instruct8-bit · 32.4 GB · 39–70 tok/s

Zinaenda vizuri 42

Inatosha na kubakiza nafasi ya context, kwa tokeni 10 au zaidi kwa sekunde.

ModeliToleoKumbukumbuTokeni/s
Nemotron 3.5 Bolt 74B A9B74B · 9B zinazotumika · Akili 21.44-bit41.6 GB27–48
Qwen3.6 35B A3B35B · 3B zinazotumika · Akili 18.28-bit37.2 GB43–77
Nemotron 3.5 Lightning 30B A3B30B · 3B zinazotumika · Akili 12.98-bit31.9 GB43–77
MiniCPM5 2B2.52B · Akili 12.58-bit2.7 GB51–91
Qwen3.5 9B9B · Akili 11.28-bit9.6 GB14–26
Granite 4.2 8B8B · Akili 11.18-bit8.5 GB16–29
Granite 4.2 3B3B · Akili 9.18-bit3.2 GB43–77
gpt-oss-20b21B · 3.6B zinazotumika · Akili 94.25-bit asili13.8 GB73–129
Nemotron 3 Nano 30B A3B30B · 3.5B zinazotumika · Akili 8.98-bit31.9 GB37–66
Gemma 4 E4B8B · Akili 8.98-bit8.5 GB29–51
Ministral 3 8B8.9B · Akili 5.58-bit9.5 GB15–26
Nemotron 3 Nano 4B3.97B · Akili 4.88-bit4.2 GB33–58
Qwen3 Coder 30B A3B Instruct30.5B · 3.3B zinazotumika8-bit32.4 GB39–70
GLM-4.7 Flash30B · 3B zinazotumika8-bit31.9 GB43–77
Gemma 4 26B A4B25.2B · 3.8B zinazotumika8-bit26.8 GB35–61
Devstral Small 2 (24B)24B4-bit13.5 GB10–18
Magistral Small 1.2 (2509)24B4-bit13.5 GB10–18
Mistral Small 3.2 (24B)24B4-bit13.5 GB10–18
LFM2.5 24B A2B24B · 2B zinazotumika8-bit25.5 GB66–117
Phi-4 Reasoning Vision 15B15B6-bit12.2 GB11–20
Phi-4 (14B)14B6-bit11.4 GB12–22
Gemma 4 12B Unified12B8-bit12.7 GB11–19
Qwen3 8B8.2B8-bit8.7 GB16–28
Llama 3.1 8B Instruct8B8-bit8.5 GB16–29
Gemma 4 E2B5.1B8-bit5.4 GB58–102
Qwen3.5 4B4B8-bit4.3 GB32–57
Phi-4 mini instruct3.8B8-bit4 GB35–61
Llama 3.2 3B Instruct3.21B8-bit3.4 GB41–72
SmolLM3 3B3B8-bit3.2 GB43–77
LFM2.5 2.6B2.69B8-bit2.9 GB48–85
Qwen3.5 2B2B8-bit2.1 GB66–117
Llama 3.2 1B Instruct1.23B8-bit1.3 GB106–189
Qwen3.5 0.8B0.8B8-bit0.9 GB154–273
Qwen3 0.6B0.6B8-bit0.6 GB230–409
Qwen3.5 122B A10B122B · 10B zinazotumika · Akili 15.62-bit ubora wa chini38.1 GB45–79
gpt-oss-120b117B · 5.1B zinazotumika · Akili 11.62-bit ubora wa chini36.6 GB86–154
Mistral Small 4 (119B)119B · 6.5B zinazotumika · Akili 11.32-bit ubora wa chini37.2 GB69–123
Qwen3 Coder Next80B · 3B zinazotumika · Akili 9.23-bit ubora wa chini35 GB106–189
Llama 4 Scout 17B-16E Instruct109B · 17B zinazotumika · Akili 6.52-bit ubora wa chini34.1 GB26–46
Ornith 1.5 122B122B · 10B zinazotumika2-bit ubora wa chini38.1 GB45–79
Nemotron 3 Super 120B A12B120B · 12B zinazotumika2-bit ubora wa chini37.5 GB36–65
GLM-4.5 Air106B · 12B zinazotumika2-bit ubora wa chini33.1 GB36–65

Zinaenda, lakini polepole 8

Inatosha, lakini chini ya tokeni 10 kwa sekunde: sawa kwa kazi za kundi, polepole kwa mazungumzo.

ModeliToleoKumbukumbuTokeni/s
Qwen3.8 27B27B · Akili 33.78-bit28.7 GB5–9
Muse Glimmer 30B29.6B · Akili 17.58-bit31.5 GB4–8
Gemma 4 31B30.7B · Akili 14.78-bit32.6 GB4–8
Granite 4.2 30B30B · Akili 12.78-bit31.9 GB4–8
Llama 3.3 70B Instruct70B4-bit39.4 GB4–6
Qwen3.6 27B27B8-bit28.7 GB5–9
Mistral Medium 3.5 (128B)128B · Akili 14.22-bit ubora wa chini40 GB3–6
Devstral 2 (123B)123B2-bit ubora wa chini38.4 GB4–6

Kubwa mno 23

Inahitaji kumbukumbu zaidi ya GB 64, hata kwa biti 2.

Mac nyingine

Kila Mac yenye GB 64, ya chipu yoyote.

M5 Pro yenye kumbukumbu zaidi au kidogo:

Chipu jirani:

Ana kwa ana:

Ilinganishe na Mac au GPU yoyote · M5 Pro kwa AI ya ndani ya kifaa · Mac bora kwa LLM za ndani · Kila Mac

Maswali

LLM ipi ni bora kwa M5 Pro yenye GB 64?
Miongoni mwa modeli zenye Intelligence Index iliyochapishwa, Nemotron 3.5 Bolt 74B A9B ina alama ya juu zaidi kati ya zile zinazoenda vizuri hapa: 4-bit, takriban tokeni 27–48 kwa sekunde.
Je, M5 Pro yenye GB 64 inaweza kuendesha Llama 3.3 70B?
Ndiyo, lakini polepole: 4-bit, kwa takriban tokeni 4–6 kwa sekunde.
gpt-oss-20b ina kasi gani kwenye M5 Pro?
Takriban tokeni 73–129 kwa sekunde (4.25-bit asili), kutokana na bandwidth ya kumbukumbu ya chipu ya 307 GB/s.

Ziendeshe kwa MLX Harness (bure, open source) au mlx-lm ya Apple ndani ya Terminal: hatua kwa hatua.

Jinsi inavyokokotolewa

Kumbukumbu: vigezo vya modeli kwa biti 8, 6, 4, 3 au 2 kwa kila weight pamoja na group scales za MLX (nusu biti kwa kila weight), au muundo wake asili, pamoja na nafasi ya context juu yake. Kwa chaguo-msingi macOS huiruhusu GPU kutumia takriban 75% ya unified memory. Kasi: bandwidth ya kumbukumbu ikigawanywa kwa baiti zinazosomwa kwa kila tokeni ndiyo kikomo cha juu kwa mazungumzo moja; katika benchmarks za umma za llama.cpp kwenye Apple Silicon uendeshaji halisi hufikia takriban 45% hadi 80% yake, na huo ndio upana unaoonyeshwa. Haya ni makadirio, si vipimo: pima Mac yako mwenyewe kwenye MLX Bench. Takwimu za modeli ni kutoka kwa kadi rasmi ya kila modeli, takwimu za chipu ni kutoka Tech Specs za Apple. Imekaguliwa 2026-10-19. Data ileile ya mlx.app/compare.

M5 Pro yenye GB 64 inaendesha LLM zipi? Modeli na kasi