Back to leaderboard

glm-4.7-flash:latest

OLLAMA GGUF

glm4moelite · 29.9B · Q4_K_M

Excellent

Mar 22, 2026 · AMD RYZEN AI MAX+ 395

qwen2.5-coder:7b

OLLAMA GGUF

qwen2 · 7.6B · Q4_K_M

Good

Mar 5, 2026 · Intel Gen Intel® Core™ i7-13700K

Global Score
82 vs 68
Hardware Fit
94 vs 59
Quality Score
77 vs 72

Hardware

glm-4.7-flash:latest qwen2.5-coder:7b
MachineAZW GTR ProASUS
CPUAMD RYZEN AI MAX+ 395Intel Gen Intel® Core™ i7-13700K
Cores3224
RAM125 GB64 GB
GPURadeon 8060SNVIDIA GeForce RTX 3070
OSUbuntu 24.04.4 LTSMicrosoft Windows 11 Pro 10.0.26200
Archx64x64
Power Modeperformanceunknown

Performance

glm-4.7-flash:latest qwen2.5-coder:7b
Tokens/sec47.634.4
First chunk200 ms1991 ms
TTFT200 ms2.0 s
Load time7.3 s40.6 s
Memory usage37.7 GB5.0 GB
Memory %30%8%

HW Fit Score Breakdown

glm-4.7-flash:latest

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

qwen2.5-coder:7b

Speed
38/50
TTFT
12/20
Memory
9/30

Quality

glm-4.7-flash:latest

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

qwen2.5-coder:7b

Reasoning
11/20
Coding
18/20
Instruction
12/20
Structured
13/15
Math
9/15
Multilingual
9/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Adequate 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