AI Models for Motorola Razr (2024) — What runs on 12GB
Specs checked against manufacturer and public documentation on .
What runs on the Motorola Razr (2024)
All 51 models at their recommended quant, on the 12GB configuration. Tap a model for the full report.
| Model | Params | Quant | Needs | Speed | Verdict | |
|---|---|---|---|---|---|---|
| S | Ternary Bonsai 1.7B | 1.7B | PQ2_0 | 1.2 GB | ~15.4 tokens/s | ✓ Runs great |
| S | Qwen3 0.6B | 0.6B | Q8_0 | 1.3 GB | ~12.8 tokens/s | ✓ Runs great |
| S | LFM2.5 8B-A1B | 8B | Q4_K_M | 6.6 GB | ~11.8 tokens/s | ✓ Runs great |
| S | Llama 3.2 1B | 1.2B | Q4_K_M | 1.5 GB | ~9.6 tokens/s | ✓ Runs great |
| S | Gemma 3 1B | 1B | Q4_K_M | 1.5 GB | ~9.6 tokens/s | ✓ Runs great |
| A | DeepSeek R1 Distill 1.5B | 1.8B | Q4_K_M | 1.9 GB | ~7 tokens/s | ! Runs, barely |
| A | SmolLM2 1.7B | 1.7B | Q4_K_M | 1.9 GB | ~7 tokens/s | ! Runs, barely |
| A | Ternary Bonsai 4B | 4B | PQ2_0 | 2 GB | ~7 tokens/s | ! Runs, barely |
| A | Qwen 3.5 2B | 2B | Q4_K_M | 2.1 GB | ~5.9 tokens/s | ! Runs, barely |
| A | Qwen3 1.7B | 1.7B | Q8_0 | 2.6 GB | ~4.3 tokens/s | ! Runs, barely |
| A | SmolLM3 3B | 3.1B | Q4_K_M | 2.8 GB | ~4.1 tokens/s | ! Runs, barely |
| A | Llama 3.2 3B | 3.2B | Q4_K_M | 2.9 GB | ~3.8 tokens/s | ! Runs, barely |
| A | Ministral 3 3B | 3B | Q4_K_M | 3 GB | ~3.7 tokens/s | ! Runs, barely |
| B | Ternary Bonsai 8B | 8B | PQ2_0 | 3.5 GB | ~3.5 tokens/s | ! Runs, barely |
| B | Qwen3 4B | 4B | Q4_K_M | 3.5 GB | ~3.1 tokens/s | ! Runs, barely |
| B | Gemma 3 4B | 4.3B | Q4_K_M | 3.5 GB | ~3.1 tokens/s | ! Runs, barely |
| B | Phi-4 Mini 3.8B | 3.8B | Q4_K_M | 3.5 GB | ~3.1 tokens/s | ! Runs, barely |
| B | Qwen 3.5 4B | 4B | Q4_K_M | 3.7 GB | ~2.9 tokens/s | ! Runs, barely |
| B | Gemma 4 E2B | 2B | Q4_K_M | 4 GB | ~2.5 tokens/s | ! Runs, barely |
| B | Nemotron 3 Nano 4B | 4B | Q4_K_M | 3.8 GB | ~2.7 tokens/s | ! Runs, barely |
| B | Mistral 7B v0.3 | 7.2B | Q4_K_M | 5.7 GB | ~1.7 tokens/s | ! Runs, barely |
| B | Bonsai 27B (1-bit) | 27B | Q1_0 | 6.5 GB | ~2 tokens/s | ! Runs, barely |
| B | Qwen3 8B | 8.2B | Q4_K_M | 6.4 GB | ~1.5 tokens/s | ! Runs, barely |
| B | Llama 3.1 8B | 8B | Q4_K_M | 6.3 GB | ~1.6 tokens/s | ! Runs, barely |
| B | Ministral 8B | 8B | Q4_K_M | 6.3 GB | ~1.6 tokens/s | ! Runs, barely |
| B | DeepSeek R1 Distill 7B | 7.6B | Q4_K_M | 6.1 GB | ~1.6 tokens/s | ! Runs, barely |
| B | Gemma 4 E4B | 4B | Q4_K_M | 6.1 GB | ~1.5 tokens/s | ! Runs, barely |
| B | Ministral 3 8B | 8B | Q4_K_M | 6.6 GB | ~1.5 tokens/s | ! Runs, barely |
| B | Ornith 1.0 9B | 9B | Q4_K_M | 7.1 GB | ~1.4 tokens/s | ! Runs, barely |
| B | Qwen 3.5 9B | 9B | Q4_K_M | 7.2 GB | ~1.4 tokens/s | ! Runs, barely |
| C | Gemma 4 12B | 12B | Q4_0 | 8.8 GB | ~1.1 tokens/s | ! Runs, barely |
| F | Gemma 3 12B | 12.2B | Q4_K_M | 9.1 GB | — | ✕ Won't fit |
| F | Ternary Bonsai 27B | 27B | PQ2_0 | 10.1 GB | — | ✕ Won't fit |
| F | Ministral 3 14B | 14B | Q4_K_M | 10.2 GB | — | ✕ Won't fit |
| F | Qwen3 14B | 14.8B | Q4_K_M | 11.1 GB | — | ✕ Won't fit |
| F | Phi-4 14B | 14.7B | Q4_K_M | 11.2 GB | — | ✕ Won't fit |
| F | GPT-OSS 20B | 21B | MXFP4 | 14.8 GB | — | ✕ Won't fit |
| F | Gemma 4 26B-A4B | 26B | Q4_0 | 17.5 GB | — | ✕ Won't fit |
| F | Qwen3 30B A3B | 30.5B | Q4_K_M | 22.3 GB | — | ✕ Won't fit |
| F | Qwen 3.5 27B | 27B | Q4_K_M | 20 GB | — | ✕ Won't fit |
| F | Qwen 3.5 35B-A3B | 35B | Q4_K_M | 26.2 GB | — | ✕ Won't fit |
| F | Qwen 3.6 27B | 27B | Q4_K_M | 20.1 GB | — | ✕ Won't fit |
| F | Qwen 3.6 35B-A3B | 35B | Q4_K_M | 26.3 GB | — | ✕ Won't fit |
| F | Nemotron 3 Nano 30B-A3B | 30B | Q4_K_M | 28.5 GB | — | ✕ Won't fit |
| F | Ornith 1.0 35B-A3B | 35B | Q5_K_M | 29 GB | — | ✕ Won't fit |
| F | Llama 3.3 70B | 70B | Q4_K_M | 50.1 GB | — | ✕ Won't fit |
| F | Qwen3 32B | 32.8B | Q4_K_M | 23.7 GB | — | ✕ Won't fit |
| F | Ornith 1.0 397B | 397B | Q4_K_S | 269.6 GB | — | ✕ Won't fit |
| F | Gemma 4 31B | 31B | Q4_K_M | 22 GB | — | ✕ Won't fit |
| F | Hunyuan 3 (Hy3) | 298.8B | Q4_K_M | 212.8 GB | — | ✕ Won't fit |
| F | Inkling | 952.4B | Q8_0 | 966.9 GB | — | ✕ Won't fit |
~ = bandwidth-based estimate · ✓ = measured on real hardware
Best model by use case
Top everyday assistant & writing pick here — ~15.4 tokens/s at PQ2_0, using 1.2 of ~9GB.
Top code completion & explain-this pick here — ~3.1 tokens/s at Q4_K_M, using 3.5 of ~9GB.
Top math & step-by-step thinking pick here — ~7 tokens/s at Q4_K_M, using 1.9 of ~9GB.
FAQ
What is the biggest AI model the Motorola Razr (2024) can run?
Bonsai 27B (1-bit) (27B parameters) at Q1_0 — it needs 6.5GB of the ~9GB usable on the 12GB Motorola Razr (2024), at ~2 tokens/s.
How much of the Motorola Razr (2024)'s 12GB RAM can AI models actually use?
About 9GB. Android keeps roughly 2–4GB for the system and resident apps, so of the 12GB about 9GB is actually available to a model.
Can the Motorola Razr (2024) run Llama 3.1 8B?
Yes — at Q4_K_M it needs 6.3GB of the ~9GB usable and runs at ~1.6 tokens/s.
How fast is local AI on the Motorola Razr (2024)?
The Dimensity 7300X has 17.1GB/s of memory bandwidth, which is what decode speed scales with. Small models like Ternary Bonsai 1.7B reach ~15.4 tokens/s; larger 7–14B models land in the single digits. Anything above ~8 tokens/s feels smooth for chat.
Which quantization should I use on the Motorola Razr (2024)?
Q4_K_M is the size/quality sweet spot for most models. For example, Ternary Bonsai 1.7B at PQ2_0 takes 1.2GB of memory here. Only drop to Q3 or IQ4 if a model just misses fitting; Q8 rarely pays off on 12GB of RAM.
Is 12GB of RAM enough for local AI?
31 of the 51 models we track fit on the Motorola Razr (2024) — 5 run great and 26 run with compromises. 20 models (mostly 12B+) don't fit at their recommended quant.