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

huihui-qwen3.6-35b-a3b-claude-4.7-opus-abliterated-mtp

LM-STUDIO GGUF

qwen35moe · 35B · Q4_K

Excellent

Jun 13, 2026 · AMD Ryzen 5 5600X 6-Core Processor

Global Score
81 vs 88
Hardware Fit
89 vs 85
Quality Score
77 vs 89

Hardware

glm-4.7-flash:q4_K_M huihui-qwen3.6-35b…
MachineASUSGigabyte Technology Co., Ltd. B550M AORUS PRO
CPUIntel Core™ i5-14600KFAMD Ryzen 5 5600X 6-Core Processor
Cores2012
RAM32 GB47 GB
GPUNVIDIA GeForce RTX 4070 Ti SUPERAD106 [GeForce RTX 4060 Ti]
OSMicrosoft Windows 11 Famille 10.0.26200cachyos rolling
Archx64x64
Power Modebalancedlow-power

Performance

glm-4.7-flash:q4_K_M huihui-qwen3.6-35b…
Tokens/sec35.137.7
First chunk440 ms18 ms
TTFT440 ms2.9 s
Load time11.6 sN/A
Memory usage18.4 GB26.1 GB
Memory %58%56%

HW Fit Score Breakdown

glm-4.7-flash:q4_K_M

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

huihui-qwen3.6-35b-a3b-…

Speed
50/50
TTFT
13/20
Memory
22/30

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

huihui-qwen3.6-35b-a3b-…

Reasoning
19/20
Coding
15/20
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