Back to leaderboard

qwen/qwen3-8b

LM-STUDIO MLX

qwen3 · 8B · 4bit

Excellent

Mar 5, 2026 · Apple M4 Pro

glm-4.7-flash:bf16

OLLAMA GGUF

deepseek2 · 29.9B · F16

Good

Jun 26, 2026 · Cortex-X925

Global Score
89 vs 76
Hardware Fit
95 vs 73
Quality Score
87 vs 77

Hardware

qwen/qwen3-8b glm-4.7-flash:bf16
MachineMac miniNVIDIA NVIDIA_DGX_Spark
CPUApple M4 ProCortex-X925
Cores1420
RAM64 GB122 GB
GPUApple M4 ProDevice 2e12
OSmacOS 15.7.4Ubuntu 24.04.4 LTS
Archarm64arm64
Power Modebalancedperformance

Performance

qwen/qwen3-8b glm-4.7-flash:bf16
Tokens/sec33.425.8
First chunk257 ms605 ms
TTFT257 ms605 ms
Load timeN/A44.2 s
Memory usage4.3 GB57.0 GB
Memory %7%47%

HW Fit Score Breakdown

qwen/qwen3-8b

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

glm-4.7-flash:bf16

Speed
27/50
TTFT
20/20
Memory
26/30

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

glm-4.7-flash:bf16

Reasoning
13/20
Coding
17/20
Instruction
12/20
Structured
15/15
Math
10/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Adequate Multilingual: Strong
View qwen/qwen3-8b details | View glm-4.7-flash:bf16 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