Back to leaderboard

glm-4.7-flash:bf16

OLLAMA GGUF

deepseek2 · 29.9B · F16

Good

Jun 26, 2026 · Cortex-X925

qwen3.8-27b-mlx

LM-STUDIO MLX

qwen3_5 · 27B · 8bit

Marginal

Aug 17, 2026 · Apple M5 Max

Global Score
76 vs 59
Hardware Fit
73 vs 63
Quality Score
77 vs 58

Hardware

glm-4.7-flash:bf16 qwen3.8-27b-mlx
MachineNVIDIA NVIDIA_DGX_SparkMacBook Pro
CPUCortex-X925Apple M5 Max
Cores2018
RAM122 GB64 GB
GPUDevice 2e12Apple M5 Max
OSUbuntu 24.04.4 LTSmacOS 27.0
Archarm64arm64
Power Modeperformancebalanced

Performance

glm-4.7-flash:bf16 qwen3.8-27b-mlx
Tokens/sec25.818.3
First chunk605 ms4 ms
TTFT605 ms530 ms
Load time44.2 sN/A
Memory usage57.0 GB38.5 GB
Memory %47%60%

HW Fit Score Breakdown

glm-4.7-flash:bf16

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

qwen3.8-27b-mlx

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

Quality

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

qwen3.8-27b-mlx

Reasoning
19/20
Coding
14/20
Instruction
6/20
Structured
1/15
Math
13/15
Multilingual
5/10
Reasoning: Strong Coding: Adequate Instruction Following: Weak Structured Output: Poor Math: Strong Multilingual: Weak
View glm-4.7-flash:bf16 details | View qwen3.8-27b-mlx 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