Back to leaderboard

qwen3.5:2b

OLLAMA GGUF

qwen35 · 2.3B · Q8_0

Not Rec.

Apr 29, 2026 · Intel Core™ i5-8350U

glm-4.7-flash:q4_K_M

OLLAMA GGUF

glm4moelite · 29.9B · Q4_K_M

Excellent

Mar 7, 2026 · Intel Core™ i5-14600KF

Global Score
13 vs 81
Hardware Fit
41 vs 89
Quality Score
1 vs 77

Hardware

qwen3.5:2b glm-4.7-flash:q4_K_M
MachineLENOVO 20L7CTO1WWASUS
CPUIntel Core™ i5-8350UIntel Core™ i5-14600KF
Cores820
RAM23 GB32 GB
GPUKaby Lake-R GT2 [UHD Graphics 620]NVIDIA GeForce RTX 4070 Ti SUPER
OSFedora Linux 43Microsoft Windows 11 Famille 10.0.26200
Archx64x64
Power Modelow-powerbalanced

Performance

qwen3.5:2b glm-4.7-flash:q4_K_M
Tokens/sec4.535.1
First chunk1413 ms440 ms
TTFT31.1 s440 ms
Load time7.1 s11.6 s
Memory usage3.8 GB18.4 GB
Memory %16%58%

HW Fit Score Breakdown

qwen3.5:2b

Speed
11/50
TTFT
0/20
Memory
30/30

glm-4.7-flash:q4_K_M

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

Quality

qwen3.5:2b

Reasoning
0/20
Coding
0/20
Instruction
1/20
Structured
0/15
Math
0/15
Multilingual
0/10
Reasoning: Poor Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor Multilingual: Poor

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
View qwen3.5:2b details | View glm-4.7-flash:q4_K_M 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