Best Local LLMs for 32GB RAM

Ranked open-weight models that run well on a 32GB 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 ~32GB

12 picks

Estimates assume a representative Apple-Silicon machine with 32GB unified memory. Tok/s are ModelFit estimates, not measured benchmarks. Run the wizard for figures tuned to your exact chip.

01

Qwen3.5 9B Instruct

Qwen / 9B / Q4_K_M / ~7 GB

Best for: Quality, Coding, Reasoning·Perf: ~119.2 tok/s (est.) · first token ~0.5s

Perfect fit

Best for quality, coding, reasoning. Strong fit for 32 GB RAM with balanced speed and quality.

ollama
$ollama run qwen3.5:9b
02

LFM2 24B-A2B Instruct

LFM2 / 24B / Q4_K_M / ~14 GB

Best for: Local AI agents, privacy-first tool calling, MCP workflows·Perf: ~49.3 tok/s (est.) · first token ~0.7s

Runs well

Best for local ai agents, privacy-first tool calling, mcp workflows. Strong fit for 32 GB RAM with balanced speed and quality.

ollama
$ollama run lfm2:24b-a2b
03

Gemma 4 12B

Gemma / 12B / Q4_K_M / ~8 GB

Best for: Chat, Coding, Multimodal·Perf: ~92 tok/s (est.) · first token ~0.6s

Perfect fit

Best for chat, coding, multimodal. Strong fit for 32 GB RAM with balanced speed and quality.

ollama
$ollama run gemma4:12b
04

Qwen3 14B

Qwen / 14B / Q4_K_M / ~11 GB

Best for: Coding, Quality·Perf: ~80.1 tok/s (est.) · first token ~0.6s

Runs well

Best for coding, quality. Strong fit for 32 GB RAM with balanced speed and quality.

ollama
$ollama run qwen3:14b-q4_K_M
05

Mistral Nemo 12B

Mistral / 12B / Q4_K_M / ~9.5 GB

Best for: Chat, Translation·Perf: ~92 tok/s (est.) · first token ~0.6s

Runs well

Best for chat, translation. Strong fit for 32 GB RAM with balanced speed and quality.

ollama
$ollama run mistral-nemo:12b
06

Gemma 3 12B Instruct

Gemma / 12B / Q4_K_M / ~9.5 GB

Best for: Chat, Quality·Perf: ~92 tok/s (est.) · first token ~0.6s

Runs well

Best for chat, quality. Strong fit for 32 GB RAM with balanced speed and quality.

ollama
$ollama run gemma3:12b
07

Gemma 2 9B Instruct

Gemma / 9B / Q4_K_M / ~7 GB

Best for: Chat, Coding·Perf: ~119.2 tok/s (est.) · first token ~0.5s

Perfect fit

Best for chat, coding. Strong fit for 32 GB RAM with balanced speed and quality.

ollama
$ollama run gemma2:9b-instruct-q4_K_M
08

Qwen2.5 Coder 14B

Qwen / 14B / Q4_K_M / ~11 GB

Best for: Coding·Perf: ~80.1 tok/s (est.) · first token ~0.6s

Runs well

Best for coding. Strong fit for 32 GB RAM with balanced speed and quality.

ollama
$ollama run qwen2.5-coder:14b
09

Qwen2.5 14B Instruct

Qwen / 14B / Q4_K_M / ~11 GB

Best for: Coding, Chat·Perf: ~80.1 tok/s (est.) · first token ~0.6s

Runs well

Best for coding, chat. Strong fit for 32 GB RAM with balanced speed and quality.

ollama
$ollama run qwen2.5:14b-instruct-q4_K_M
10

DeepSeek-R1 Distill Qwen 14B

DeepSeek / 14B / Q4_K_M / ~11 GB

Best for: Reasoning, Quality·Perf: ~80.1 tok/s (est.) · first token ~0.6s

Runs well

Best for reasoning, quality. Strong fit for 32 GB RAM with balanced speed and quality.

ollama
$ollama run deepseek-r1:14b
11

Phi-4 14B

Phi / 14B / Q4_K_M / ~11.5 GB

Best for: Coding, Quality·Perf: ~80.1 tok/s (est.) · first token ~0.6s

Runs well

Best for coding, quality. Strong fit for 32 GB RAM with balanced speed and quality.

ollama
$ollama run phi4:14b-q4_K_M
12

Qwen3.5 35B-A3B Instruct

Qwen / 35B / Q4_K_M / ~20 GB

Best for: Reasoning, Coding, Agent scenarios·Perf: ~30.8 tok/s (est.) · first token ~1.6s

Runs well

This model may feel memory-heavy on 32 GB RAM, but it is still listed for balanced speed and quality.

ollama
$ollama run qwen3.5:35b-a3b

Browse by RAM tier

8 GB16 GB24 GB32 GB48 GB64 GB96 GB128 GB

Want an exact recommendation?

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

Open ModelFit Wizard Browse all devices