Back to leaderboard

qwen2.5-7b-instruct

LM-STUDIO MLX

qwen2 · 7B · 4bit

Excellent

Mar 3, 2026 · Apple M4

tinyllama-1.1b-chat-v1.0

LM-STUDIO GGUF

llama · 1.1B · Q3_K_M

Not Rec.

Mar 5, 2026 · Intel Core™ i5-5300U

Global Score
84 vs 33
Hardware Fit
97 vs 76
Quality Score
78 vs 14

Hardware

qwen2.5-7b-instruct tinyllama-1.1b-cha…
MachineMacBook AirLENOVO 20BUS00700
CPUApple M4Intel Core™ i5-5300U
Cores104
RAM32 GB16 GB
GPUApple M4Intel(R) HD Graphics 5500
OSmacOS 26.3Microsoft Windows 10 Professionnel 10.0.19045
Archarm64x64
Power Modebalancedbalanced

Performance

qwen2.5-7b-instruct tinyllama-1.1b-cha…
Tokens/sec24.49.9
First chunk464 ms3166 ms
TTFT464 ms3.2 s
Load timeN/AN/A
Memory usage4.0 GB0.5 GB
Memory %13%3%

HW Fit Score Breakdown

qwen2.5-7b-instruct

Speed
47/50
TTFT
20/20
Memory
30/30

tinyllama-1.1b-chat-v1.0

Speed
32/50
TTFT
16/20
Memory
28/30

Quality

qwen2.5-7b-instruct

Reasoning
14/20
Coding
17/20
Instruction
15/20
Structured
15/15
Math
8/15
Multilingual
9/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong

tinyllama-1.1b-chat-v1.0

Reasoning
2/20
Coding
1/20
Instruction
6/20
Structured
2/15
Math
1/15
Multilingual
2/10
Reasoning: Poor Coding: Poor Instruction Following: Weak Structured Output: Poor Math: Poor Multilingual: Poor
View qwen2.5-7b-instruct details | View tinyllama-1.1b-cha… 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