Back to leaderboard

glm-4.7-flash:q4_K_M

OLLAMA GGUF

glm4moelite · 29.9B · Q4_K_M

Excellent

Mar 7, 2026 · Intel Core™ i5-14600KF

richardyoung/qwythos-9b-abliterated:Q8_0

OLLAMA GGUF

qwen35 · 9.0B · Q8_0

Good

Jun 28, 2026 · Apple M4 Pro

Global Score
81 vs 65
Hardware Fit
89 vs 96
Quality Score
77 vs 52

Hardware

glm-4.7-flash:q4_K_M richardyoung/qwyth…
MachineASUSMac mini
CPUIntel Core™ i5-14600KFApple M4 Pro
Cores2012
RAM32 GB24 GB
GPUNVIDIA GeForce RTX 4070 Ti SUPERApple M4 Pro
OSMicrosoft Windows 11 Famille 10.0.26200macOS 15.6.1
Archx64arm64
Power Modebalancedbalanced

Performance

glm-4.7-flash:q4_K_M richardyoung/qwyth…
Tokens/sec35.125.3
First chunk440 ms397 ms
TTFT440 ms397 ms
Load time11.6 s6.3 s
Memory usage18.4 GB8.3 GB
Memory %58%34%

HW Fit Score Breakdown

glm-4.7-flash:q4_K_M

Speed
49/50
TTFT
20/20
Memory
20/30

richardyoung/qwythos-9b…

Speed
47/50
TTFT
20/20
Memory
29/30

Quality

glm-4.7-flash:q4_K_M

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

richardyoung/qwythos-9b…

Reasoning
18/20
Coding
13/20
Instruction
6/20
Structured
0/15
Math
14/15
Multilingual
1/10
Reasoning: Strong Coding: Adequate Instruction Following: Weak Structured Output: Poor Math: Strong Multilingual: Poor

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