mistral-nemo:12b

llama · 12.2B · Q4_0

MacBook Air (Apple M4)

32 GB · macOS 26.3

Tested on March 1, 2026

Top 29% Compare

Global Score

73 /100

Good

Hardware Fit

86/100

Quality

65/100

Get this model

🦙

Ollama

ollama pull mistral-nemo:12b

View on Ollama Library

ollama.com/library/mistral-nemo

🤗

Find on HuggingFace

GGUF versions & quantizations

Hardware

Machine: MacBook Air
CPU: Apple M4
Cores: 10 total (4 perf + 6 eff)
Frequency: 2.4 GHz
RAM: 32 GB LPDDR5
GPU: Apple M4
OS: macOS 26.3
Arch: arm64
Power Mode: balanced

Performance

Tokens/sec Tokens generated per second — higher is better: 14.6
Standard deviation Variation of speed across benchmark runs — lower means more consistent: ±0.1
Time to first token How fast the model starts responding — lower is better: 371 ms
Load time Time to load the model into memory before inference: 1.0 s
Memory usage RAM consumed during inference — percentage of total system memory: 13.3 GB (42%)
Total tokens Total number of tokens generated across all benchmark prompts: 957

Score breakdown

Speed

26/40

Time to first token

30/30

Memory

30/30

Quality

Reasoning

12/20

Coding

13/20

Instruction following

11/20

Structured output

15/15

Math

4/15

Multilingual

10/10

Category levels

Reasoning: Adequate Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Strong

Metadata

Spec version: 0.2.0
Runtime: Ollama 0.17.4
Model format: GGUF
Hardware profile: BALANCED
Result hash: b2671a7ec015c6876ccbe5ea6b23709bb39e5900509e189ded44c0fbe2c33847

Interpretation

Hardware fit: 86/100. Overall suitability: GOOD (Global 73/100). Category profile: Reasoning: Adequate, Coding: Adequate, Instruction Following: Adequate, Structured Output: Strong, Math: Poor, Multilingual: Strong.

Run yours now

npx metrillm@latest bench

Requires Node 20+ and Ollama running