Back to leaderboard

qwen3.5:0.8b

OLLAMA GGUF

qwen35 · 873.44M · Q8_0

Not Rec.

Apr 29, 2026 · Intel Core™ i5-8350U

qwen3:30b-a3b-instruct-2507-q4_K_M

OLLAMA GGUF

qwen3moe · 30.5B · Q4_K_M

Not Rec.

Jul 31, 2026 · Intel Xeon® E5-4620 0

Global Score
18 vs 71
Hardware Fit
53 vs 42
Quality Score
3 vs 84

Hardware

qwen3.5:0.8b qwen3:30b-a3b-inst…
MachineLENOVO 20L7CTO1WWDell Inc. PowerEdge R820
CPUIntel Core™ i5-8350UIntel Xeon® E5-4620 0
Cores864
RAM23 GB256 GB
GPUKaby Lake-R GT2 [UHD Graphics 620]Microsoft Remote Display Adapter, Microsoft Basic Display Adapter
OSFedora Linux 43Microsoft Windows Server 2022 Datacenter 10.0.20348
Archx64x64
Power Modelow-powerbalanced

Performance

qwen3.5:0.8b qwen3:30b-a3b-inst…
Tokens/sec9.44.0
First chunk799 ms2070 ms
TTFT30.0 s2.1 s
Load time3.3 s44.5 s
Memory usage1.9 GB17.7 GB
Memory %8%7%

HW Fit Score Breakdown

qwen3.5:0.8b

Speed
23/50
TTFT
0/20
Memory
30/30

qwen3:30b-a3b-instruct-…

Speed
3/50
TTFT
9/20
Memory
30/30

Quality

qwen3.5:0.8b

Reasoning
0/20
Coding
0/20
Instruction
2/20
Structured
0/15
Math
0/15
Multilingual
1/10
Reasoning: Poor Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor Multilingual: Poor

qwen3:30b-a3b-instruct-…

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