Back to leaderboard

liquid/lfm2-24b-a2b

LM-STUDIO MLX

lfm2_moe · 24B · 4bit

Good

Mar 19, 2026 · Apple M4

qwen3.5-0.8b

LM-STUDIO GGUF

qwen35 · 0.8B · Q4_K_M

Marginal

Mar 6, 2026 · Intel Core™ i5-5300U

Global Score
74 vs 48
Hardware Fit
84 vs 61
Quality Score
69 vs 42

Hardware

liquid/lfm2-24b-a2b qwen3.5-0.8b
MachineMac miniLENOVO 20BUS00700
CPUApple M4Intel Core™ i5-5300U
Cores104
RAM24 GB16 GB
GPUApple M4Intel(R) HD Graphics 5500
OSmacOS 26.3Microsoft Windows 10 Professionnel 10.0.19045
Archarm64x64
Power Modebalancedbalanced

Performance

liquid/lfm2-24b-a2b qwen3.5-0.8b
Tokens/sec58.96.2
First chunk28 ms4461 ms
TTFT481 ms4.5 s
Load timeN/AN/A
Memory usage17.5 GB0.7 GB
Memory %73%4%

HW Fit Score Breakdown

liquid/lfm2-24b-a2b

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

qwen3.5-0.8b

Speed
22/50
TTFT
12/20
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

qwen3.5-0.8b

Reasoning
10/20
Coding
2/20
Instruction
10/20
Structured
12/15
Math
2/15
Multilingual
6/10
Reasoning: Adequate Coding: Poor Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Adequate

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