Back to leaderboard

hf.co/unsloth/Qwen3.8-27B-GGUF:UD-IQ1_S

OLLAMA GGUF

qwen35 · 27.3B · unknown

Marginal

Aug 25, 2026 · Apple M1 Pro

glm-4.7-flash:latest

OLLAMA GGUF

glm4moelite · 29.9B · Q4_K_M

Not Rec.

Mar 22, 2026 · AMD RYZEN AI MAX+ 395

Global Score
46 vs 86
Hardware Fit
50 vs 74
Quality Score
44 vs 91

Hardware

hf.co/unsloth/Qwen… glm-4.7-flash:latest
MachineMacBook ProAZW GTR Pro
CPUApple M1 ProAMD RYZEN AI MAX+ 395
Cores1032
RAM16 GB125 GB
GPUApple M1 ProRadeon 8060S
OSmacOS 26.6.2Ubuntu 24.04.4 LTS
Archarm64x64
Power Modebalancedperformance

Performance

hf.co/unsloth/Qwen… glm-4.7-flash:latest
Tokens/sec6.047.8
First chunk2377 ms194 ms
TTFT2.2 s30.0 s
Load time6.8 s7.4 s
Memory usage10.6 GB37.7 GB
Memory %66%30%

HW Fit Score Breakdown

hf.co/unsloth/Qwen3.8-2…

Speed
15/50
TTFT
18/20
Memory
17/30

glm-4.7-flash:latest

Speed
44/50
TTFT
0/20
Memory
30/30

Quality

hf.co/unsloth/Qwen3.8-2…

Reasoning
8/20
Coding
5/20
Instruction
10/20
Structured
11/15
Math
3/15
Multilingual
7/10
Reasoning: Weak Coding: Weak Instruction Following: Adequate Structured Output: Adequate Math: Poor Multilingual: Adequate

glm-4.7-flash:latest

Reasoning
19/20
Coding
17/20
Instruction
15/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

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