IngiaFungua pochi

M1 Ultra yenye GB 64 inaweza kuendesha nini?

Modeli huria 39 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 800 GB/s, jambo linaloamua kasi yake ya kuandika. Inapatikana katika: Mac Studio (2022).

Yenye akili zaidi inayoenda vizuriQwen3.8 27B8-bit · 28.7 GB · 13–22 tok/sKubwa zaidi inayoenda vizuriNemotron 3.5 Bolt 74B A9B4-bit · 41.6 GB · 71–125 tok/sKwa kuandika codeQwen3 Coder 30B A3B Instruct8-bit · 32.4 GB · 103–183 tok/s

Zinaenda vizuri 47

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

ModeliToleoKumbukumbuTokeni/s
Qwen3.8 27B27B · Akili 33.78-bit28.7 GB13–22
Nemotron 3.5 Bolt 74B A9B74B · 9B zinazotumika · Akili 21.44-bit41.6 GB71–125
Qwen3.6 35B A3B35B · 3B zinazotumika · Akili 18.28-bit37.2 GB113–200
Muse Glimmer 30B29.6B · Akili 17.58-bit31.5 GB11–20
Gemma 4 31B30.7B · Akili 14.78-bit32.6 GB11–20
Nemotron 3.5 Lightning 30B A3B30B · 3B zinazotumika · Akili 12.98-bit31.9 GB113–200
Granite 4.2 30B30B · Akili 12.78-bit31.9 GB11–20
MiniCPM5 2B2.52B · Akili 12.58-bit2.7 GB133–237
Qwen3.5 9B9B · Akili 11.28-bit9.6 GB38–67
Granite 4.2 8B8B · Akili 11.18-bit8.5 GB42–75
Granite 4.2 3B3B · Akili 9.18-bit3.2 GB113–200
gpt-oss-20b21B · 3.6B zinazotumika · Akili 94.25-bit asili13.8 GB189–337
Nemotron 3 Nano 30B A3B30B · 3.5B zinazotumika · Akili 8.98-bit31.9 GB97–173
Gemma 4 E4B8B · Akili 8.98-bit8.5 GB75–133
Ministral 3 8B8.9B · Akili 5.58-bit9.5 GB38–67
Nemotron 3 Nano 4B3.97B · Akili 4.88-bit4.2 GB86–152
Qwen3 Coder 30B A3B Instruct30.5B · 3.3B zinazotumika8-bit32.4 GB103–183
GLM-4.7 Flash30B · 3B zinazotumika8-bit31.9 GB113–200
Qwen3.6 27B27B8-bit28.7 GB13–22
Gemma 4 26B A4B25.2B · 3.8B zinazotumika8-bit26.8 GB90–160
Devstral Small 2 (24B)24B8-bit25.5 GB14–25
Magistral Small 1.2 (2509)24B8-bit25.5 GB14–25
Mistral Small 3.2 (24B)24B8-bit25.5 GB14–25
LFM2.5 24B A2B24B · 2B zinazotumika8-bit25.5 GB171–305
Phi-4 Reasoning Vision 15B15B8-bit15.9 GB23–40
Phi-4 (14B)14B8-bit14.9 GB24–43
Gemma 4 12B Unified12B8-bit12.7 GB28–50
Qwen3 8B8.2B8-bit8.7 GB41–74
Llama 3.1 8B Instruct8B8-bit8.5 GB42–75
Gemma 4 E2B5.1B8-bit5.4 GB150–267
Qwen3.5 4B4B8-bit4.3 GB84–149
Phi-4 mini instruct3.8B8-bit4 GB90–160
Llama 3.2 3B Instruct3.21B8-bit3.4 GB106–188
SmolLM3 3B3B8-bit3.2 GB113–200
LFM2.5 2.6B2.69B8-bit2.9 GB124–221
Qwen3.5 2B2B8-bit2.1 GB171–305
Llama 3.2 1B Instruct1.23B8-bit1.3 GB277–492
Qwen3.5 0.8B0.8B8-bit0.9 GB400–711
Qwen3 0.6B0.6B8-bit0.6 GB600–1067
Qwen3.5 122B A10B122B · 10B zinazotumika · Akili 15.62-bit ubora wa chini38.1 GB116–206
gpt-oss-120b117B · 5.1B zinazotumika · Akili 11.62-bit ubora wa chini36.6 GB225–400
Mistral Small 4 (119B)119B · 6.5B zinazotumika · Akili 11.32-bit ubora wa chini37.2 GB180–320
Qwen3 Coder Next80B · 3B zinazotumika · Akili 9.23-bit ubora wa chini35 GB277–492
Llama 4 Scout 17B-16E Instruct109B · 17B zinazotumika · Akili 6.52-bit ubora wa chini34.1 GB68–121
Ornith 1.5 122B122B · 10B zinazotumika2-bit ubora wa chini38.1 GB116–206
Nemotron 3 Super 120B A12B120B · 12B zinazotumika2-bit ubora wa chini37.5 GB95–168
GLM-4.5 Air106B · 12B zinazotumika2-bit ubora wa chini33.1 GB95–168

Zinaenda, lakini polepole 3

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

ModeliToleoKumbukumbuTokeni/s
Llama 3.3 70B Instruct70B4-bit39.4 GB9–16
Mistral Medium 3.5 (128B)128B · Akili 14.22-bit ubora wa chini40 GB9–16
Devstral 2 (123B)123B2-bit ubora wa chini38.4 GB9–17

Kubwa mno 23

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

Mac nyingine

Kila Mac yenye GB 64, ya chipu yoyote.

M1 Ultra yenye kumbukumbu zaidi au kidogo:

Chipu jirani:

Ana kwa ana:

Ilinganishe na Mac au GPU yoyote · M1 Ultra kwa AI ya ndani ya kifaa · Mac bora kwa LLM za ndani · Kila Mac

Maswali

LLM ipi ni bora kwa M1 Ultra yenye GB 64?
Miongoni mwa modeli zenye Intelligence Index iliyochapishwa, Qwen3.8 27B ina alama ya juu zaidi kati ya zile zinazoenda vizuri hapa: 8-bit, takriban tokeni 13–22 kwa sekunde. Kubwa zaidi inayoenda vizuri ni Nemotron 3.5 Bolt 74B A9B.
Je, M1 Ultra yenye GB 64 inaweza kuendesha Llama 3.3 70B?
Ndiyo, lakini polepole: 4-bit, kwa takriban tokeni 9–16 kwa sekunde.
gpt-oss-20b ina kasi gani kwenye M1 Ultra?
Takriban tokeni 189–337 kwa sekunde (4.25-bit asili), kutokana na bandwidth ya kumbukumbu ya chipu ya 800 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.

M1 Ultra yenye GB 64 inaendesha LLM zipi? Modeli na kasi