IngiaFungua pochi

M5 Ultra yenye GB 96 inaweza kuendesha nini?

Modeli huria 44 kati ya 73 zinaenda vizuri juu yake. Kwa chaguo-msingi GPU inaweza kutumia takriban GB 72 kati ya GB 96 zake, na husoma kumbukumbu kwa 1,200 GB/s, jambo linaloamua kasi yake ya kuandika. Inapatikana katika: Mac Studio (M5 Max or M5 Ultra).

Yenye akili zaidi inayoenda vizuriQwen3.8 27B8-bit · 28.7 GB · 19–33 tok/sKubwa zaidi inayoenda vizurigpt-oss-120b4.25-bit asili · 65.3 GB · 200–356 tok/sKwa kuandika codeQwen3 Coder Next6-bit · 65 GB · 225–400 tok/s

Zinaenda vizuri 51

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

ModeliToleoKumbukumbuTokeni/s
Qwen3.8 27B27B · Akili 33.78-bit28.7 GB19–33
Nemotron 3.5 Bolt 74B A9B74B · 9B zinazotumika · Akili 21.46-bit60.1 GB74–132
Qwen3.6 35B A3B35B · 3B zinazotumika · Akili 18.28-bit37.2 GB169–300
Muse Glimmer 30B29.6B · Akili 17.58-bit31.5 GB17–30
Gemma 4 31B30.7B · Akili 14.78-bit32.6 GB17–29
Nemotron 3.5 Lightning 30B A3B30B · 3B zinazotumika · Akili 12.98-bit31.9 GB169–300
Granite 4.2 30B30B · Akili 12.78-bit31.9 GB17–30
MiniCPM5 2B2.52B · Akili 12.58-bit2.7 GB200–356
gpt-oss-120b117B · 5.1B zinazotumika · Akili 11.64.25-bit asili65.3 GB200–356
Qwen3.5 9B9B · Akili 11.28-bit9.6 GB56–100
Granite 4.2 8B8B · Akili 11.18-bit8.5 GB64–113
Qwen3 Coder Next80B · 3B zinazotumika · Akili 9.26-bit65 GB225–400
Granite 4.2 3B3B · Akili 9.18-bit3.2 GB169–300
gpt-oss-20b21B · 3.6B zinazotumika · Akili 94.25-bit asili13.8 GB284–505
Nemotron 3 Nano 30B A3B30B · 3.5B zinazotumika · Akili 8.98-bit31.9 GB146–259
Gemma 4 E4B8B · Akili 8.98-bit8.5 GB113–200
Llama 4 Scout 17B-16E Instruct109B · 17B zinazotumika · Akili 6.54-bit61.3 GB56–100
Ministral 3 8B8.9B · Akili 5.58-bit9.5 GB57–101
Nemotron 3 Nano 4B3.97B · Akili 4.88-bit4.2 GB129–229
GLM-4.5 Air106B · 12B zinazotumika4-bit59.6 GB79–141
Llama 3.3 70B Instruct70B4-bit39.4 GB14–24
Qwen3 Coder 30B A3B Instruct30.5B · 3.3B zinazotumika8-bit32.4 GB154–274
GLM-4.7 Flash30B · 3B zinazotumika8-bit31.9 GB169–300
Qwen3.6 27B27B8-bit28.7 GB19–33
Gemma 4 26B A4B25.2B · 3.8B zinazotumika8-bit26.8 GB135–240
Devstral Small 2 (24B)24B8-bit25.5 GB21–38
Magistral Small 1.2 (2509)24B8-bit25.5 GB21–38
Mistral Small 3.2 (24B)24B8-bit25.5 GB21–38
LFM2.5 24B A2B24B · 2B zinazotumika8-bit25.5 GB257–457
Phi-4 Reasoning Vision 15B15B8-bit15.9 GB34–60
Phi-4 (14B)14B8-bit14.9 GB36–64
Gemma 4 12B Unified12B8-bit12.7 GB43–76
Qwen3 8B8.2B8-bit8.7 GB62–110
Llama 3.1 8B Instruct8B8-bit8.5 GB64–113
Gemma 4 E2B5.1B8-bit5.4 GB225–400
Qwen3.5 4B4B8-bit4.3 GB126–223
Phi-4 mini instruct3.8B8-bit4 GB135–240
Llama 3.2 3B Instruct3.21B8-bit3.4 GB159–282
SmolLM3 3B3B8-bit3.2 GB169–300
LFM2.5 2.6B2.69B8-bit2.9 GB186–331
Qwen3.5 2B2B8-bit2.1 GB257–457
Llama 3.2 1B Instruct1.23B8-bit1.3 GB415–738
Qwen3.5 0.8B0.8B8-bit0.9 GB600–1067
Qwen3 0.6B0.6B8-bit0.6 GB900–1600
Qwen3.8 Flash Next180B · 6B zinazotumika · Akili 39.82-bit ubora wa chini56.3 GB284–505
Qwen3.5 122B A10B122B · 10B zinazotumika · Akili 15.63-bit ubora wa chini53.4 GB123–218
Mistral Medium 3.5 (128B)128B · Akili 14.23-bit ubora wa chini56 GB10–17
Mistral Small 4 (119B)119B · 6.5B zinazotumika · Akili 11.33-bit ubora wa chini52.1 GB193–343
Devstral 2 (123B)123B3-bit ubora wa chini53.8 GB10–18
Ornith 1.5 122B122B · 10B zinazotumika3-bit ubora wa chini53.4 GB123–218
Nemotron 3 Super 120B A12B120B · 12B zinazotumika3-bit ubora wa chini52.5 GB102–181

Zinatosha kwa shida 1

Inahitaji karibu kumbukumbu yote: ongeza kikomo cha kumbukumbu ya GPU na weka context fupi.

ModeliToleoKumbukumbuTokeni/s
MiniMax M2.7230B · 10B zinazotumika2-bit ubora wa chini71.9 GB174–310

Kubwa mno 21

Inahitaji kumbukumbu zaidi ya GB 96, hata kwa biti 2.

Mac nyingine

Kila Mac yenye GB 96, ya chipu yoyote.

M5 Ultra yenye kumbukumbu zaidi au kidogo:

Chipu jirani:

Ana kwa ana:

Dhidi ya PC na kadi za michoro:

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

Maswali

LLM ipi ni bora kwa M5 Ultra yenye GB 96?
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 19–33 kwa sekunde. Kubwa zaidi inayoenda vizuri ni gpt-oss-120b.
Je, M5 Ultra yenye GB 96 inaweza kuendesha Llama 3.3 70B?
Ndiyo: 4-bit, kwa takriban tokeni 14–24 kwa sekunde.
gpt-oss-20b ina kasi gani kwenye M5 Ultra?
Takriban tokeni 284–505 kwa sekunde (4.25-bit asili), kutokana na bandwidth ya kumbukumbu ya chipu ya 1,200 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 Ultra yenye GB 96 inaendesha LLM zipi? Modeli na kasi