Back to leaderboard

qwen3.5-0.8b

LM-STUDIO GGUF

qwen35 · 0.8B · Q4_K_M

Marginal

Mar 6, 2026 · Intel Core™ i5-5300U

qwen3-next:80b-a3b-instruct-q4_K_M

OLLAMA GGUF

qwen3next · 79.7B · Q4_K_M

Good

Aug 18, 2026 · Intel Xeon® E5-2637 v3

Global Score
48 vs 78
Hardware Fit
61 vs 51
Quality Score
42 vs 89

Hardware

qwen3.5-0.8b qwen3-next:80b-a3b…
MachineLENOVO 20BUS00700Dell Inc. Precision Tower 7910
CPUIntel Core™ i5-5300UIntel Xeon® E5-2637 v3
Cores416
RAM16 GB96 GB
GPUIntel(R) HD Graphics 5500NVIDIA GeForce RTX 3090, NVIDIA GeForce RTX 3060
OSMicrosoft Windows 10 Professionnel 10.0.19045Microsoft Windows 10 Pro 10.0.19045
Archx64x64
Power Modebalancedbalanced

Performance

qwen3.5-0.8b qwen3-next:80b-a3b…
Tokens/sec6.28.7
First chunk4461 ms1251 ms
TTFT4.5 s1.3 s
Load timeN/A61.6 s
Memory usage0.7 GB48.3 GB
Memory %4%50%

HW Fit Score Breakdown

qwen3.5-0.8b

Speed
22/50
TTFT
12/20
Memory
27/30

qwen3-next:80b-a3b-inst…

Speed
9/50
TTFT
17/20
Memory
25/30

Quality

qwen3.5-0.8b

Reasoning
10/20
Coding
2/20
Instruction
10/20
Structured
12/15
Math
2/15
Multilingual
6/10
Reasoning: Adequate Coding: Poor Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Adequate

qwen3-next:80b-a3b-inst…

Reasoning
18/20
Coding
19/20
Instruction
14/20
Structured
15/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong
View qwen3.5-0.8b details | View qwen3-next:80b-a3b… 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