Back to leaderboard

glm-4.7-flash-reap-39-i1

LM-STUDIO GGUF

deepseek2 · Q5_K_M

Excellent

Aug 20, 2026 · AMD Ryzen 7 9700X 8-Core Processor

hf.co/LiquidAI/LFM2.5-2.6B-GGUF:F16

OLLAMA GGUF

lfm2 · 2.7B · unknown

Good

Aug 26, 2026 · Apple M1 Pro

Global Score
80 vs 61
Hardware Fit
97 vs 97
Quality Score
73 vs 46

Hardware

glm-4.7-flash-reap… hf.co/LiquidAI/LFM…
MachineMicro-Star International Co., Ltd. MS-7E51MacBook Pro
CPUAMD Ryzen 7 9700X 8-Core ProcessorApple M1 Pro
Cores1610
RAM31 GB16 GB
GPUNVIDIA GeForce RTX 5080, AMD Radeon(TM) GraphicsApple M1 Pro
OSMicrosoft Windows 11 Pro 10.0.26200macOS 26.6.2
Archx64arm64
Power Modebalancedbalanced

Performance

glm-4.7-flash-reap… hf.co/LiquidAI/LFM…
Tokens/sec154.831.3
First chunk13 ms131 ms
TTFT70 ms131 ms
Load timeN/A4.2 s
Memory usage12.6 GB6.6 GB
Memory %41%41%

HW Fit Score Breakdown

glm-4.7-flash-reap-39-i1

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

hf.co/LiquidAI/LFM2.5-2…

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

Quality

glm-4.7-flash-reap-39-i1

Reasoning
13/20
Coding
18/20
Instruction
15/20
Structured
15/15
Math
7/15
Multilingual
5/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Weak Multilingual: Adequate

hf.co/LiquidAI/LFM2.5-2…

Reasoning
14/20
Coding
13/20
Instruction
3/20
Structured
0/15
Math
14/15
Multilingual
2/10
Reasoning: Adequate Coding: Adequate Instruction Following: Poor Structured Output: Poor Math: Strong Multilingual: Poor
View glm-4.7-flash-reap… details | View hf.co/LiquidAI/LFM… details

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