IngiaFungua pochi

M3 Ultra yenye GB 256 inaweza kuendesha nini?

Modeli huria 53 kati ya 73 zinaenda vizuri juu yake. Kwa chaguo-msingi GPU inaweza kutumia takriban GB 192 kati ya GB 256 zake, na husoma kumbukumbu kwa 819 GB/s, jambo linaloamua kasi yake ya kuandika. Inapatikana katika: Mac Studio (2025).

Yenye akili zaidi inayoenda vizuriQwen3.8 Flash Next6-bit · 146 GB · 75–134 tok/sKubwa zaidi inayoenda vizuriMiMo V2.6 Flash4.48-bit asili · 173 GB · 44–78 tok/sKwa kuandika codeQwen3 Coder Next8-bit · 85 GB · 115–205 tok/s

Zinaenda vizuri 60

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

ModeliToleoKumbukumbuTokeni/s
Qwen3.8 Flash Next180B · 6B zinazotumika · Akili 39.86-bit146 GB75–134
MiMo V2.6 Flash309B · 15B zinazotumika · Akili 37.94.48-bit asili173 GB44–78
Qwen3.8 27B27B · Akili 33.78-bit28.7 GB13–23
Inkling Small276B · 12B zinazotumika · Akili 25.74-bit155 GB54–96
Hy3295B · 21B zinazotumika · Akili 25.34-bit166 GB31–56
Nemotron 3.5 Bolt 74B A9B74B · 9B zinazotumika · Akili 21.48-bit78.6 GB38–68
Qwen3.6 35B A3B35B · 3B zinazotumika · Akili 18.28-bit37.2 GB115–205
Muse Glimmer 30B29.6B · Akili 17.58-bit31.5 GB12–21
Qwen3.5 122B A10B122B · 10B zinazotumika · Akili 15.68-bit130 GB35–62
Gemma 4 31B30.7B · Akili 14.78-bit32.6 GB11–20
Nemotron 3.5 Lightning 30B A3B30B · 3B zinazotumika · Akili 12.98-bit31.9 GB115–205
Granite 4.2 30B30B · Akili 12.78-bit31.9 GB12–21
MiniCPM5 2B2.52B · Akili 12.58-bit2.7 GB137–243
gpt-oss-120b117B · 5.1B zinazotumika · Akili 11.64.25-bit asili65.3 GB137–243
Mistral Small 4 (119B)119B · 6.5B zinazotumika · Akili 11.38-bit126 GB53–95
Qwen3.5 9B9B · Akili 11.28-bit9.6 GB38–68
Granite 4.2 8B8B · Akili 11.18-bit8.5 GB43–77
Qwen3 Coder Next80B · 3B zinazotumika · Akili 9.28-bit85 GB115–205
Granite 4.2 3B3B · Akili 9.18-bit3.2 GB115–205
gpt-oss-20b21B · 3.6B zinazotumika · Akili 94.25-bit asili13.8 GB194–345
Nemotron 3 Nano 30B A3B30B · 3.5B zinazotumika · Akili 8.98-bit31.9 GB100–177
Gemma 4 E4B8B · Akili 8.98-bit8.5 GB77–137
Llama 4 Scout 17B-16E Instruct109B · 17B zinazotumika · Akili 6.58-bit116 GB20–36
Ministral 3 8B8.9B · Akili 5.58-bit9.5 GB39–69
Nemotron 3 Nano 4B3.97B · Akili 4.88-bit4.2 GB88–156
DeepSeek V4 Flash 0731284B · 13B zinazotumika4-bit160 GB50–90
MiniMax M2.7230B · 10B zinazotumika4-bit129 GB66–117
Ornith 1.5 122B122B · 10B zinazotumika8-bit130 GB35–62
Nemotron 3 Super 120B A12B120B · 12B zinazotumika8-bit128 GB29–51
GLM-4.5 Air106B · 12B zinazotumika8-bit113 GB29–51
Qwen3 Coder 30B A3B Instruct30.5B · 3.3B zinazotumika8-bit32.4 GB105–187
GLM-4.7 Flash30B · 3B zinazotumika8-bit31.9 GB115–205
Qwen3.6 27B27B8-bit28.7 GB13–23
Gemma 4 26B A4B25.2B · 3.8B zinazotumika8-bit26.8 GB92–164
Devstral Small 2 (24B)24B8-bit25.5 GB14–26
Magistral Small 1.2 (2509)24B8-bit25.5 GB14–26
Mistral Small 3.2 (24B)24B8-bit25.5 GB14–26
LFM2.5 24B A2B24B · 2B zinazotumika8-bit25.5 GB176–312
Phi-4 Reasoning Vision 15B15B8-bit15.9 GB23–41
Phi-4 (14B)14B8-bit14.9 GB25–44
Gemma 4 12B Unified12B8-bit12.7 GB29–52
Qwen3 8B8.2B8-bit8.7 GB42–75
Llama 3.1 8B Instruct8B8-bit8.5 GB43–77
Gemma 4 E2B5.1B8-bit5.4 GB154–273
Qwen3.5 4B4B8-bit4.3 GB86–152
Phi-4 mini instruct3.8B8-bit4 GB92–164
Llama 3.2 3B Instruct3.21B8-bit3.4 GB108–193
SmolLM3 3B3B8-bit3.2 GB115–205
LFM2.5 2.6B2.69B8-bit2.9 GB127–226
Qwen3.5 2B2B8-bit2.1 GB176–312
Llama 3.2 1B Instruct1.23B8-bit1.3 GB284–504
Qwen3.5 0.8B0.8B8-bit0.9 GB410–728
Qwen3 0.6B0.6B8-bit0.6 GB614–1092
DeepSeek V4.1 Flash 1017552B · 16B zinazotumika · Akili 45.12-bit ubora wa chini173 GB74–131
GLM-5.3 Flash320B · 18B zinazotumika · Akili 41.83-bit ubora wa chini140 GB47–83
Beam 1.0501B · 23B zinazotumika · Akili 30.32-bit ubora wa chini157 GB51–91
MiniMax M3428B · 23B zinazotumika · Akili 29.22-bit ubora wa chini134 GB51–91
Nemotron 3 Ultra 550B A55B550B · 55B zinazotumika · Akili 22.92-bit ubora wa chini172 GB21–38
Qwen3.5 397B A17B397B · 17B zinazotumika · Akili 18.43-bit ubora wa chini174 GB50–89
Llama 4 Maverick 17B-128E Instruct400B · 17B zinazotumika · Akili 9.33-bit ubora wa chini175 GB50–89

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 14.28-bit136 GB3–5
Devstral 2 (123B)123B8-bit131 GB3–5
Llama 3.3 70B Instruct70B8-bit74.4 GB5–9

Zinatosha kwa shida 1

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

ModeliToleoKumbukumbuTokeni/s
Mistral Large 3 (675B)675B · 41B zinazotumika2-bit ubora wa chini211 GB29–51

Kubwa mno 9

Inahitaji kumbukumbu zaidi ya GB 256, hata kwa biti 2.

Mac nyingine

Kila Mac yenye GB 256, ya chipu yoyote.

M3 Ultra yenye kumbukumbu zaidi au kidogo:

Chipu jirani:

Ana kwa ana:

Dhidi ya PC na kadi za michoro:

Ilinganishe na Mac au GPU yoyote · M3 Ultra kwa AI ya ndani ya kifaa · Mac bora kwa LLM za ndani · Kila Mac

Maswali

LLM ipi ni bora kwa M3 Ultra yenye GB 256?
Miongoni mwa modeli zenye Intelligence Index iliyochapishwa, Qwen3.8 Flash Next ina alama ya juu zaidi kati ya zile zinazoenda vizuri hapa: 6-bit, takriban tokeni 75–134 kwa sekunde. Kubwa zaidi inayoenda vizuri ni MiMo V2.6 Flash.
Je, M3 Ultra yenye GB 256 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 M3 Ultra?
Takriban tokeni 194–345 kwa sekunde (4.25-bit asili), kutokana na bandwidth ya kumbukumbu ya chipu ya 819 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.

M3 Ultra yenye GB 256 inaendesha LLM zipi? Modeli na kasi