Back to leaderboard

qwen2.5-7b-instruct

LM-STUDIO MLX

qwen2 · 7B · 4bit

Excellent

Mar 3, 2026 · Apple M4

qwen3.5-35b-a3b-t24-c8k:latest

OLLAMA GGUF

qwen35moe · 36.0B · Q4_K_M

Not Rec.

Jul 30, 2026 · Intel Core™ i9-14900K

Global Score
84 vs 34
Hardware Fit
97 vs 45
Quality Score
78 vs 29

Hardware

qwen2.5-7b-instruct qwen3.5-35b-a3b-t2…
MachineMacBook AirMicro-Star International Co., Ltd. MS-7D98
CPUApple M4Intel Core™ i9-14900K
Cores1032
RAM32 GB128 GB
GPUApple M4Intel(R) UHD Graphics 770, NVIDIA Quadro K4000
OSmacOS 26.3Microsoft Windows 11 Pro 10.0.26200
Archarm64x64
Power Modebalancedbalanced

Performance

qwen2.5-7b-instruct qwen3.5-35b-a3b-t2…
Tokens/sec24.416.5
First chunk464 ms772 ms
TTFT464 ms30.0 s
Load timeN/A11.6 s
Memory usage4.0 GB22.0 GB
Memory %13%17%

HW Fit Score Breakdown

qwen2.5-7b-instruct

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

qwen3.5-35b-a3b-t24-c8k…

Speed
15/50
TTFT
0/20
Memory
30/30

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

qwen3.5-35b-a3b-t24-c8k…

Reasoning
9/20
Coding
0/20
Instruction
4/20
Structured
1/15
Math
6/15
Multilingual
9/10
Reasoning: Weak Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Weak Multilingual: Strong
View qwen2.5-7b-instruct details | View qwen3.5-35b-a3b-t2… 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