qwen3:4b
OLLAMA GGUFqwen3 · 4.0B · Q4_K_M
Nov 4, 2026 · Intel Core™ i7-9700
qwen3.6:35b-a3b-coding-nvfp4
OLLAMA GGUFnvfp4
May 25, 2026 · Apple M4 Pro
Global Score
29 vs 76
Hardware Fit
84 vs 77
Quality Score
6 vs 76
Hardware
qwen3:4b qwen3.6:35b-a3b-co…
MachineVMware, Inc. VMware Virtual PlatformMacBook Pro
CPUIntel Core™ i7-9700Apple M4 Pro
Cores414
RAM16 GB48 GB
GPUIntegrated / UnknownApple M4 Pro
OSUbuntu 24.04.5 LTSmacOS 26.4.1
Archx64arm64
Power Modeunknownbalanced
Performance
qwen3:4b qwen3.6:35b-a3b-co…
Tokens/sec10.472.7
First chunk857 ms147 ms
TTFT857 ms30.0 s
Load time41.0 s5.7 s
Memory usage3.0 GB19.6 GB
Memory %19%41%
HW Fit Score Breakdown
qwen3:4b
Speed
34/50
TTFT
20/20
Memory
30/30
qwen3.6:35b-a3b-coding-…
Speed
50/50
TTFT
0/20
Memory
27/30
Quality
qwen3:4b
Reasoning
0/20
Coding
2/20
Instruction
2/20
Structured
0/15
Math
1/15
Multilingual
1/10
Reasoning: Poor Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor Multilingual: Poor
qwen3.6:35b-a3b-coding-…
Reasoning
19/20
Coding
9/20
Instruction
13/20
Structured
12/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong
Run yours and compare
$
npm install -g metrillm@latest$
metrillmRequires Node 20+ and Ollama or LM Studio running
Or run without installing: npx metrillm@latest