Back to leaderboard

qwen3.5-0.8b

LM-STUDIO GGUF

qwen35 · 0.8B · Q4_K_M

Marginal

Mar 6, 2026 · Intel Core™ i5-5300U

gemma-3-4b-it-q4-k-m

OLLAMA GGUF

llama · 4B · Q4_K_M

Excellent

Jul 9, 2026 · Intel Core™ i5-10400

Global Score
48 vs 80
Hardware Fit
61 vs 100
Quality Score
42 vs 71

Hardware

qwen3.5-0.8b gemma-3-4b-it-q4-k-m
MachineLENOVO 20BUS00700Mac Pro
CPUIntel Core™ i5-5300UIntel Core™ i5-10400
Cores412
RAM16 GB32 GB
GPUIntel(R) HD Graphics 5500AMD Radeon RX 6700 XT
OSMicrosoft Windows 10 Professionnel 10.0.19045macOS 26.5.1
Archx64x64
Power Modebalancedbalanced

Performance

qwen3.5-0.8b gemma-3-4b-it-q4-k-m
Tokens/sec6.275.0
First chunk4461 ms136 ms
TTFT4.5 s136 ms
Load timeN/A0.0 s
Memory usage0.7 GB0.8 GB
Memory %4%3%

HW Fit Score Breakdown

qwen3.5-0.8b

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

gemma-3-4b-it-q4-k-m

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

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

gemma-3-4b-it-q4-k-m

Reasoning
11/20
Coding
17/20
Instruction
14/20
Structured
14/15
Math
5/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong
View qwen3.5-0.8b details | View gemma-3-4b-it-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