Back to leaderboard

qwen/qwen3-8b

LM-STUDIO MLX

qwen3 · 8B · 4bit

Excellent

Mar 5, 2026 · Apple M4 Pro

falcon-h1-1.5b-instruct

LM-STUDIO GGUF

falcon-h1 · 1.5B · Q4_K_M

Good

Mar 8, 2026 · Intel Core™ i5-5300U

Global Score
89 vs 63
Hardware Fit
95 vs 54
Quality Score
87 vs 67

Hardware

qwen/qwen3-8b falcon-h1-1.5b-ins…
MachineMac miniLENOVO 20BUS00700
CPUApple M4 ProIntel Core™ i5-5300U
Cores144
RAM64 GB16 GB
GPUApple M4 ProIntel(R) HD Graphics 5500
OSmacOS 15.7.4Microsoft Windows 10 Professionnel 10.0.19045
Archarm64x64
Power Modebalancedbalanced

Performance

qwen/qwen3-8b falcon-h1-1.5b-ins…
Tokens/sec33.46.6
First chunk257 ms8225 ms
TTFT257 ms8.2 s
Load timeN/AN/A
Memory usage4.3 GB0.9 GB
Memory %7%6%

HW Fit Score Breakdown

qwen/qwen3-8b

Speed
45/50
TTFT
20/20
Memory
30/30

falcon-h1-1.5b-instruct

Speed
23/50
TTFT
6/20
Memory
25/30

Quality

qwen/qwen3-8b

Reasoning
19/20
Coding
14/20
Instruction
16/20
Structured
15/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

falcon-h1-1.5b-instruct

Reasoning
13/20
Coding
14/20
Instruction
14/20
Structured
11/15
Math
7/15
Multilingual
8/10
Reasoning: Adequate Coding: Adequate Instruction Following: Adequate Structured Output: Adequate Math: Weak Multilingual: Strong
View qwen/qwen3-8b details | View falcon-h1-1.5b-ins… 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