Back to leaderboard

qwen3.5:9b

OLLAMA GGUF

qwen35 · 9.7B · Q4_K_M

Excellent

Mar 6, 2026 · AMD RYZEN AI MAX+ 395 w/ Radeon 8060S

falcon-h1-0.5b-instruct

LM-STUDIO GGUF

falcon-h1 · 0.5B · Q4_K_M

Marginal

Mar 8, 2026 · Intel Core™ i5-5300U

Global Score
82 vs 57
Hardware Fit
81 vs 91
Quality Score
82 vs 42

Hardware

qwen3.5:9b falcon-h1-0.5b-ins…
MachineAZW GTR ProLENOVO 20BUS00700
CPUAMD RYZEN AI MAX+ 395 w/ Radeon 8060SIntel Core™ i5-5300U
Cores324
RAM125 GB16 GB
GPUIntegrated / Apple SiliconIntel(R) HD Graphics 5500
OSUbuntu 24.04.4 LTSMicrosoft Windows 10 Professionnel 10.0.19045
Archx64x64
Power Modeperformancebalanced

Performance

qwen3.5:9b falcon-h1-0.5b-ins…
Tokens/sec30.816.3
First chunk195 ms2987 ms
TTFT195 ms3.0 s
Load time6.8 sN/A
Memory usage18.8 GB0.3 GB
Memory %15%2%

HW Fit Score Breakdown

qwen3.5:9b

Speed
31/50
TTFT
20/20
Memory
30/30

falcon-h1-0.5b-instruct

Speed
48/50
TTFT
16/20
Memory
27/30

Quality

qwen3.5:9b

Reasoning
14/20
Coding
17/20
Instruction
15/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong

falcon-h1-0.5b-instruct

Reasoning
8/20
Coding
7/20
Instruction
12/20
Structured
10/15
Math
4/15
Multilingual
1/10
Reasoning: Weak Coding: Weak Instruction Following: Adequate Structured Output: Adequate Math: Weak Multilingual: Poor
View qwen3.5:9b details | View falcon-h1-0.5b-ins… 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