Best Local LLMs for 16GB RAM

Ranked open-weight models that run well on a 16GB machine, with estimated speed and the exact ollama command for each.

Try: Qwen3 8B, RTX 4090, MacBook Pro M4, 16GB, iPhone 17 Pro

Ranked picks

Best local models for ~16GB

12 picks

Estimates assume a representative Apple-Silicon machine with 16GB unified memory. Tok/s are ModelFit estimates, not measured benchmarks; typical error is the median gap to measured runs on hardware the model was not fitted on (how the estimates work). Run the wizard for figures tuned to your exact chip.

  1. 01

    Qwen3.5 9B Instruct

    Qwen / 9B / Q4_K_M / ~7 GB

    Best for quality, coding, reasoning. Strong fit for 16 GB RAM with balanced speed and quality.

    ollama
    $ollama run qwen3.5:9b
    Fit
    Runs wellB · 37
    Best for
    Quality, Coding, Reasoning
    Perf
    est. 26 tok/s, typical error 10% · first token ~1.7s
  2. 02

    Mellum2.1 12B-A2.5B Thinking

    Mellum / 12.1B / Q4_K_M / ~8.1 GB

    Best for agentic coding, small machines. Strong fit for 16 GB RAM with balanced speed and quality.

    ollama
    $ollama run mellum2.1-12b-q4
    Fit
    Runs wellB · 28
    Best for
    Agentic coding, Small machines
    Perf
    est. 51 tok/s, typical error 10% · first token ~0.5s
  3. 03

    NVIDIA Nemotron 3.5 Bolt E4B

    Nemotron / 4B / Q4_K_M / ~7.9 GB

    Best for voice assistants, tool calling, chat. Strong fit for 16 GB RAM with balanced speed and quality.

    ollama
    $ollama run nemotron-3.5-bolt:e4b
    Fit
    Runs wellB · 29
    Best for
    Voice assistants, Tool calling, Chat
    Perf
    est. 34 tok/s, typical error 10% · first token ~1.5s
  4. 04

    Gemma 4 12B

    Gemma / 12B / Q4_K_M / ~8 GB

    Best for chat, coding, multimodal. Strong fit for 16 GB RAM with balanced speed and quality.

    ollama
    $ollama run gemma4:12b
    Fit
    Runs wellB · 29
    Best for
    Chat, Coding, Multimodal
    Perf
    est. 17 tok/s, typical error 10% · first token ~2.5s
  5. 05

    MiMo-V2.6-Distill-Qwen-9B

    MiMo / 9B / Q4_K_M / ~5.8 GB

    Best for agentic coding, small machines. Strong fit for 16 GB RAM with balanced speed and quality.

    ollama
    $ollama run mimo-v2.6-distill-qwen-9b
    Fit
    Runs wellB · 48
    Best for
    Agentic coding, Small machines
    Perf
    est. 25 tok/s, typical error 10% · first token ~1.7s
  6. 06

    Ornith 1.0 9B

    Ornith / 9B / Q4_K_M / ~5.6 GB

    Best for agentic coding on small machines. Strong fit for 16 GB RAM with balanced speed and quality.

    ollama
    $ollama run ornith:9b
    Fit
    Runs wellB · 50
    Best for
    Agentic coding on small machines
    Perf
    est. 26 tok/s, typical error 10% · first token ~1.7s
  7. 07

    LFM2.5 8B-A1B

    LFM2 / 8.3B / Q4_K_M / ~5.5 GB

    Best for on-device agents, tool calling, multilingual chat. Strong fit for 16 GB RAM with balanced speed and quality.

    ollama
    $ollama run lfm2.5:8b-a1b-q4_K_M
    Fit
    Runs wellB · 51
    Best for
    On-device agents, tool calling, multilingual chat
    Perf
    est. 75 tok/s, typical error 10% · first token ~0.3s
  8. 08

    Qwen3.5 4B Instruct

    Qwen / 4B / Q4_K_M / ~3.5 GB

    Best for coding, agents, multimodal. Strong fit for 16 GB RAM with balanced speed and quality.

    ollama
    $ollama run qwen3.5:4b
    Fit
    Lots of roomA · 69
    Best for
    Coding, Agents, Multimodal
    Perf
    est. 46 tok/s, typical error 10% · first token ~0.8s
  9. 09

    Granite Switch 4.1 8B

    Granite / 8.8B / Q4_K_M / ~6.4 GB

    Best for chat, decisions, safety checks. Strong fit for 16 GB RAM with balanced speed and quality.

    ollama
    $ollama run granite-switch-4.1-8b-q4
    Fit
    Runs wellB · 43
    Best for
    Chat, Decisions, Safety checks
    Perf
    est. 19 tok/s, typical error 10% · first token ~2.0s
  10. 10

    Gemma 4 E4B (Q8)

    Gemma / 4.5B / Q8_0 / ~7.5 GB

    Best for on-device, mobile, chat. Strong fit for 16 GB RAM with balanced speed and quality.

    ollama
    $ollama run gemma4:e4b-it-q8_0
    Fit
    Runs wellB · 33
    Best for
    On-device, Mobile, Chat
    Perf
    est. 26 tok/s, typical error 10% · first token ~1.6s
  11. 11

    Ministral 3 8B

    Mistral / 8.4B / Q4_K_M / ~6 GB

    Best for chat, coding, vision. Strong fit for 16 GB RAM with balanced speed and quality.

    ollama
    $ollama run ministral-3:8b
    Fit
    Runs wellB · 46
    Best for
    Chat, Coding, Vision
    Perf
    est. 21 tok/s, typical error 10% · first token ~1.9s
  12. 12

    Gemma 4 E4B

    Gemma / 4.5B / Q4_K_M / ~4 GB

    Best for on-device, mobile, chat. Strong fit for 16 GB RAM with balanced speed and quality.

    ollama
    $ollama run gemma4:e4b
    Fit
    Lots of roomA · 64
    Best for
    On-device, Mobile, Chat
    Perf
    est. 37 tok/s, typical error 10% · first token ~1.5s

Browse by RAM tier

Want an exact recommendation?

The wizard tunes picks and speed estimates to your exact device, chip, and RAM.

Open ModelFit Wizard Browse all devices
Best Local LLMs for 16GB RAM (2026) | ModelFit