LLM ipi ni bora kwa Mac yenye GB 96?

Miongoni mwa modeli zenye Intelligence Index iliyochapishwa, Qwen3.8 27B ina alama ya juu zaidi kati ya zile zinazoenda vizuri ndani ya GB 96 (8-bit). Kubwa zaidi inayoenda vizuri ni gpt-oss-120b. Kwa code: Qwen3 Coder Next.

Je, GB 96 zinatosha kwa AI ya ndani kwenye Mac?

Modeli huria 44 kati ya 73 zilizo hapa zinaenda vizuri ndani yake kwa biti 4 au zaidi. Kwa chaguo-msingi macOS huiruhusu GPU kutumia takriban GB 72 kati yake; modeli na context yake lazima zitoshe humo.

Je, Mac ya GB 96 inaweza kuendesha gpt-oss-20b?

Ndiyo, 4.25-bit asili, kwa takriban tokeni 71–126 kwa sekunde kwenye M3 Max na 284–505 kwenye M5 Ultra.

LLM bora za ndani kwa Mac ya GB 96 (M2 hadi M5)

Mac zenye GB 96

Chipu 4 kuanzia M2 hadi M5 huja na GB 96. Fungua yoyote kuona orodha na kasi zake.

Zinaenda vizuri 51

Inatosha na kubakiza nafasi ya context, kwa tokeni 10 au zaidi kwa sekunde kwenye M5 Ultra.

Modeli	Toleo	Kumbukumbu	M3 Max	M5 Ultra
Qwen3.8 27B27B · Akili 33.7	8-bit	28.7 GB	5–8	19–33
Nemotron 3.5 Bolt 74B A9B74B · 9B zinazotumika · Akili 21.4	6-bit	60.1 GB	18–33	74–132
Qwen3.6 35B A3B35B · 3B zinazotumika · Akili 18.2	8-bit	37.2 GB	42–75	169–300
Muse Glimmer 30B29.6B · Akili 17.5	8-bit	31.5 GB	4–8	17–30
Gemma 4 31B30.7B · Akili 14.7	8-bit	32.6 GB	4–7	17–29
Nemotron 3.5 Lightning 30B A3B30B · 3B zinazotumika · Akili 12.9	8-bit	31.9 GB	42–75	169–300
Granite 4.2 30B30B · Akili 12.7	8-bit	31.9 GB	4–8	17–30
MiniCPM5 2B2.52B · Akili 12.5	8-bit	2.7 GB	50–89	200–356
gpt-oss-120b117B · 5.1B zinazotumika · Akili 11.6	4.25-bit asili	65.3 GB	50–89	200–356
Qwen3.5 9B9B · Akili 11.2	8-bit	9.6 GB	14–25	56–100
Granite 4.2 8B8B · Akili 11.1	8-bit	8.5 GB	16–28	64–113
Qwen3 Coder Next80B · 3B zinazotumika · Akili 9.2	6-bit	65 GB	56–100	225–400
Granite 4.2 3B3B · Akili 9.1	8-bit	3.2 GB	42–75	169–300
gpt-oss-20b21B · 3.6B zinazotumika · Akili 9	4.25-bit asili	13.8 GB	71–126	284–505
Nemotron 3 Nano 30B A3B30B · 3.5B zinazotumika · Akili 8.9	8-bit	31.9 GB	36–65	146–259
Gemma 4 E4B8B · Akili 8.9	8-bit	8.5 GB	28–50	113–200
Llama 4 Scout 17B-16E Instruct109B · 17B zinazotumika · Akili 6.5	4-bit	61.3 GB	14–25	56–100
Ministral 3 8B8.9B · Akili 5.5	8-bit	9.5 GB	14–25	57–101
Nemotron 3 Nano 4B3.97B · Akili 4.8	8-bit	4.2 GB	32–57	129–229
GLM-4.5 Air106B · 12B zinazotumika	4-bit	59.6 GB	20–35	79–141
Llama 3.3 70B Instruct70B	4-bit	39.4 GB	2–4	14–24
Qwen3 Coder 30B A3B Instruct30.5B · 3.3B zinazotumika	8-bit	32.4 GB	39–69	154–274
GLM-4.7 Flash30B · 3B zinazotumika	8-bit	31.9 GB	42–75	169–300
Qwen3.6 27B27B	8-bit	28.7 GB	5–8	19–33
Gemma 4 26B A4B25.2B · 3.8B zinazotumika	8-bit	26.8 GB	34–60	135–240
Devstral Small 2 (24B)24B	8-bit	25.5 GB	10–18	21–38
Magistral Small 1.2 (2509)24B	8-bit	25.5 GB	10–18	21–38
Mistral Small 3.2 (24B)24B	8-bit	25.5 GB	10–18	21–38
LFM2.5 24B A2B24B · 2B zinazotumika	8-bit	25.5 GB	64–114	257–457
Phi-4 Reasoning Vision 15B15B	8-bit	15.9 GB	11–20	34–60
Phi-4 (14B)14B	8-bit	14.9 GB	12–21	36–64
Gemma 4 12B Unified12B	8-bit	12.7 GB	11–19	43–76
Qwen3 8B8.2B	8-bit	8.7 GB	16–28	62–110
Llama 3.1 8B Instruct8B	8-bit	8.5 GB	16–28	64–113
Gemma 4 E2B5.1B	8-bit	5.4 GB	56–100	225–400
Qwen3.5 4B4B	8-bit	4.3 GB	31–56	126–223
Phi-4 mini instruct3.8B	8-bit	4 GB	34–60	135–240
Llama 3.2 3B Instruct3.21B	8-bit	3.4 GB	40–71	159–282
SmolLM3 3B3B	8-bit	3.2 GB	42–75	169–300
LFM2.5 2.6B2.69B	8-bit	2.9 GB	47–83	186–331
Qwen3.5 2B2B	8-bit	2.1 GB	64–114	257–457
Llama 3.2 1B Instruct1.23B	8-bit	1.3 GB	104–185	415–738
Qwen3.5 0.8B0.8B	8-bit	0.9 GB	150–267	600–1067
Qwen3 0.6B0.6B	8-bit	0.6 GB	225–400	900–1600
Qwen3.8 Flash Next180B · 6B zinazotumika · Akili 39.8	2-bit ubora wa chini	56.3 GB	71–126	284–505
Qwen3.5 122B A10B122B · 10B zinazotumika · Akili 15.6	3-bit ubora wa chini	53.4 GB	31–55	123–218
Mistral Medium 3.5 (128B)128B · Akili 14.2	3-bit ubora wa chini	56 GB	2–4	10–17
Mistral Small 4 (119B)119B · 6.5B zinazotumika · Akili 11.3	3-bit ubora wa chini	52.1 GB	48–86	193–343
Devstral 2 (123B)123B	3-bit ubora wa chini	53.8 GB	3–4	10–18
Ornith 1.5 122B122B · 10B zinazotumika	3-bit ubora wa chini	53.4 GB	31–55	123–218
Nemotron 3 Super 120B A12B120B · 12B zinazotumika	3-bit ubora wa chini	52.5 GB	25–45	102–181

Zinatosha kwa shida 1

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

Modeli	Toleo	Kumbukumbu	M3 Max	M5 Ultra
MiniMax M2.7230B · 10B zinazotumika	2-bit ubora wa chini	71.9 GB	44–77	174–310

Maswali

LLM ipi ni bora kwa Mac yenye GB 96?: Miongoni mwa modeli zenye Intelligence Index iliyochapishwa, Qwen3.8 27B ina alama ya juu zaidi kati ya zile zinazoenda vizuri ndani ya GB 96 (8-bit). Kubwa zaidi inayoenda vizuri ni gpt-oss-120b. Kwa code: Qwen3 Coder Next.
Je, GB 96 zinatosha kwa AI ya ndani kwenye Mac?: Modeli huria 44 kati ya 73 zilizo hapa zinaenda vizuri ndani yake kwa biti 4 au zaidi. Kwa chaguo-msingi macOS huiruhusu GPU kutumia takriban GB 72 kati yake; modeli na context yake lazima zitoshe humo.
Je, Mac ya GB 96 inaweza kuendesha gpt-oss-20b?: Ndiyo, 4.25-bit asili, kwa takriban tokeni 71–126 kwa sekunde kwenye M3 Max na 284–505 kwenye M5 Ultra.

Ukubwa mwingine: 8 GB · 16 GB · 18 GB · 24 GB · 32 GB · 36 GB · 48 GB · 64 GB · 96 GB · 128 GB · 192 GB · 256 GB · 512 GB

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.

LLM bora kwa Mac ya GB 96.