IngiaFungua pochi

M2 Ultra yenye GB 128 inaweza kuendesha nini?

Modeli huria 47 kati ya 73 zinaenda vizuri juu yake. Kwa chaguo-msingi GPU inaweza kutumia takriban GB 96 kati ya GB 128 zake, na husoma kumbukumbu kwa 800 GB/s, jambo linaloamua kasi yake ya kuandika. Inapatikana katika: Mac Studio (2023), Mac Pro (2023), Mac Pro (Rack, 2023).

Yenye akili zaidi inayoenda vizuriQwen3.8 27B8-bit · 28.7 GB · 13–22 tok/sKubwa zaidi inayoenda vizuriQwen3.5 122B A10B4-bit · 68.6 GB · 64–114 tok/sKwa kuandika codeQwen3 Coder Next8-bit · 85 GB · 113–200 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 GB13–22
Nemotron 3.5 Bolt 74B A9B74B · 9B zinazotumika · Akili 21.48-bit78.6 GB38–67
Qwen3.6 35B A3B35B · 3B zinazotumika · Akili 18.28-bit37.2 GB113–200
Muse Glimmer 30B29.6B · Akili 17.58-bit31.5 GB11–20
Qwen3.5 122B A10B122B · 10B zinazotumika · Akili 15.64-bit68.6 GB64–114
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
gpt-oss-120b117B · 5.1B zinazotumika · Akili 11.64.25-bit asili65.3 GB133–237
Mistral Small 4 (119B)119B · 6.5B zinazotumika · Akili 11.34-bit66.9 GB97–173
Qwen3.5 9B9B · Akili 11.28-bit9.6 GB38–67
Granite 4.2 8B8B · Akili 11.18-bit8.5 GB42–75
Qwen3 Coder Next80B · 3B zinazotumika · Akili 9.28-bit85 GB113–200
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
Llama 4 Scout 17B-16E Instruct109B · 17B zinazotumika · Akili 6.56-bit88.6 GB26–46
Ministral 3 8B8.9B · Akili 5.58-bit9.5 GB38–67
Nemotron 3 Nano 4B3.97B · Akili 4.88-bit4.2 GB86–152
Ornith 1.5 122B122B · 10B zinazotumika4-bit68.6 GB64–114
Nemotron 3 Super 120B A12B120B · 12B zinazotumika4-bit67.5 GB53–94
GLM-4.5 Air106B · 12B zinazotumika6-bit86.1 GB37–65
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
Qwen3.8 Flash Next180B · 6B zinazotumika · Akili 39.83-bit ubora wa chini78.8 GB138–246
Inkling Small276B · 12B zinazotumika · Akili 25.72-bit ubora wa chini86.3 GB95–168
DeepSeek V4 Flash 0731284B · 13B zinazotumika2-bit ubora wa chini88.8 GB88–156
MiniMax M2.7230B · 10B zinazotumika2-bit ubora wa chini71.9 GB116–206

Zinaenda, lakini polepole 3

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

ModeliToleoKumbukumbuTokeni/s
Mistral Medium 3.5 (128B)128B · Akili 14.24-bit72 GB5–9
Devstral 2 (123B)123B4-bit69.2 GB5–9
Llama 3.3 70B Instruct70B8-bit74.4 GB5–9

Zinatosha kwa shida 3

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

ModeliToleoKumbukumbuTokeni/s
GLM-5.3 Flash320B · 18B zinazotumika · Akili 41.82-bit ubora wa chini100 GB64–114
MiMo V2.6 Flash309B · 15B zinazotumika · Akili 37.92-bit ubora wa chini96.6 GB77–136
Hy3295B · 21B zinazotumika · Akili 25.32-bit ubora wa chini92.2 GB55–97

Kubwa mno 16

Inahitaji kumbukumbu zaidi ya GB 128, hata kwa biti 2.

Mac nyingine

Kila Mac yenye GB 128, ya chipu yoyote.

M2 Ultra yenye kumbukumbu zaidi au kidogo:

Chipu jirani:

Ana kwa ana:

Ilinganishe na Mac au GPU yoyote · M2 Ultra kwa AI ya ndani ya kifaa · Mac bora kwa LLM za ndani · Kila Mac

Maswali

LLM ipi ni bora kwa M2 Ultra yenye GB 128?
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 Qwen3.5 122B A10B.
Je, M2 Ultra yenye GB 128 inaweza kuendesha Llama 3.3 70B?
Ndiyo, lakini polepole: 8-bit, kwa takriban tokeni 5–9 kwa sekunde.
gpt-oss-20b ina kasi gani kwenye M2 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.

M2 Ultra yenye GB 128 inaendesha LLM zipi? Modeli na kasi