Back to leaderboard

liquid/lfm2-24b-a2b

LM-STUDIO MLX

lfm2_moe · 24B · 4bit

Good

Apr 1, 2026 · Apple M4

deepseek-r1:70b

OLLAMA GGUF

llama · 70.6B · Q4_K_M

Not Rec.

Jun 27, 2026 · Cortex-X925

Global Score
74 vs 47
Hardware Fit
84 vs 51
Quality Score
69 vs 45

Hardware

liquid/lfm2-24b-a2b deepseek-r1:70b
MachineMac miniNVIDIA NVIDIA_DGX_Spark
CPUApple M4Cortex-X925
Cores1020
RAM24 GB122 GB
GPUApple M4Device 2e12
OSmacOS 26.3Ubuntu 24.04.4 LTS
Archarm64arm64
Power Modebalancedperformance

Performance

liquid/lfm2-24b-a2b deepseek-r1:70b
Tokens/sec51.84.7
First chunk10 ms557 ms
TTFT503 ms557 ms
Load timeN/A52.6 s
Memory usage17.5 GB49.5 GB
Memory %73%41%

HW Fit Score Breakdown

liquid/lfm2-24b-a2b

Speed
50/50
TTFT
20/20
Memory
14/30

deepseek-r1:70b

Speed
4/50
TTFT
20/20
Memory
27/30

Quality

liquid/lfm2-24b-a2b

Reasoning
11/20
Coding
12/20
Instruction
16/20
Structured
13/15
Math
8/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong

deepseek-r1:70b

Reasoning
3/20
Coding
1/20
Instruction
14/20
Structured
9/15
Math
8/15
Multilingual
10/10
Reasoning: Poor Coding: Poor Instruction Following: Adequate Structured Output: Adequate Math: Adequate Multilingual: Strong

Run yours and compare

$ npm install -g metrillm@latest
$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest