01
Qwen3.5 9B Instruct
Qwen / 9B / Q4_K_M / ~7 GB
Best for: Quality, Coding, Reasoning·Perf: ~55.1 tok/s · first token ~0.6s
This model may feel memory-heavy on 12 GB RAM, but it is still listed for balanced speed and quality.
$ollama run qwen3.5:9b
Best Local LLMs for 12GB RAM
Ranked open-weight models that run well on a 12GB machine, with estimated speed and the exact ollama command for each.
Try: RTX 4090, MacBook Pro M4, 16GB, iPhone 17 Pro
Best local models for ~12GB
12 picksEstimates assume a representative Apple-Silicon machine with 12GB unified memory. Tok/s are ModelFit estimates, not measured benchmarks. Run the wizard for figures tuned to your exact chip.
Runs well
02
Qwen3 8B
Qwen / 8B / Q4_K_M / ~6.5 GB
Best for: Chat, Coding·Perf: ~65.3 tok/s · first token ~0.6s
This model may feel memory-heavy on 12 GB RAM, but it is still listed for balanced speed and quality.
$ollama run qwen3:8b-q4_K_M
03
LFM2.5 8B-A1B
LFM2 / 8.3B / Q4_K_M / ~5.5 GB
Best for: On-device agents, tool calling, multilingual chat·Perf: ~136.3 tok/s · first token ~0.5s
Best for on-device agents, tool calling, multilingual chat. Strong fit for 12 GB RAM with balanced speed and quality.
$ollama run lfm2.5:8b-a1b-q4_K_M
04
Llama 3.1 8B Instruct
Llama / 8B / Q4_K_M / ~6.5 GB
Best for: Chat, Coding·Perf: ~65.3 tok/s · first token ~0.6s
This model may feel memory-heavy on 12 GB RAM, but it is still listed for balanced speed and quality.
$ollama run llama3.1:8b-instruct-q4_K_M
05
Qwen2.5 Coder 7B
Qwen / 7B / Q4_K_M / ~5.5 GB
Best for: Coding·Perf: ~73.6 tok/s · first token ~0.6s
Best for coding. Strong fit for 12 GB RAM with balanced speed and quality.
$ollama run qwen2.5-coder:7b
06
DeepSeek-R1 Distill Qwen 7B
DeepSeek / 7B / Q4_K_M / ~5.5 GB
Best for: Reasoning, Coding·Perf: ~73.6 tok/s · first token ~0.6s
Best for reasoning, coding. Strong fit for 12 GB RAM with balanced speed and quality.
$ollama run deepseek-r1:7b
07
Qwen2.5 7B Instruct
Qwen / 7B / Q4_K_M / ~5.5 GB
Best for: Chat, Coding·Perf: ~73.6 tok/s · first token ~0.6s
Best for chat, coding. Strong fit for 12 GB RAM with balanced speed and quality.
$ollama run qwen2.5:7b-instruct-q4_K_M
08
Mistral 7B Instruct
Mistral / 7B / Q4_K_M / ~5.5 GB
Best for: Chat, Coding·Perf: ~73.6 tok/s · first token ~0.6s
Best for chat, coding. Strong fit for 12 GB RAM with balanced speed and quality.
$ollama run mistral:7b-instruct-q4_K_M
09
Granite 4.1 8B Instruct
Granite / 8B / Q4_K_M / ~5.5 GB
Best for: Enterprise assistant, tool calling, instruction following·Perf: ~65.3 tok/s · first token ~0.6s
Best for enterprise assistant, tool calling, instruction following. Strong fit for 12 GB RAM with balanced speed and quality.
$ollama run granite4.1:8b
10
Qwen3.5 4B Instruct
Qwen / 4B / Q4_K_M / ~3.5 GB
Best for: Coding, Agents, Multimodal·Perf: ~121.8 tok/s · first token ~0.5s
Best for coding, agents, multimodal. Strong fit for 12 GB RAM with balanced speed and quality.
$ollama run qwen3.5:4b
11
Gemma 2 9B Instruct
Gemma / 9B / Q4_K_M / ~7 GB
Best for: Chat, Coding·Perf: ~55.1 tok/s · first token ~0.6s
This model may feel memory-heavy on 12 GB RAM, but it is still listed for balanced speed and quality.
$ollama run gemma2:9b-instruct-q4_K_M
12
Gemma 4 E4B
Gemma / 4.5B / Q4_K_M / ~4 GB
Best for: On-device, Mobile, Chat·Perf: ~109.5 tok/s · first token ~0.5s
Best for on-device, mobile, chat. Strong fit for 12 GB RAM with balanced speed and quality.
$ollama run gemma4:e4b
Want an exact recommendation?
The wizard tunes picks and speed estimates to your exact device, chip, and RAM.