Kimi-48B:48B
OLLAMA GGUFkimi-linear · 49.1B · unknown
Aug 19, 2026 · Intel Core™ Ultra X7 358H
qwen3.5-35b-a3b-uncensored-hauhaucs-aggressive
LM-STUDIO GGUFqwen35moe · 35B · Q4_K_M
Apr 21, 2026 · Apple M2 Max
Global Score
86 vs 71
Hardware Fit
78 vs 92
Quality Score
89 vs 62
Hardware
Kimi-48B:48B qwen3.5-35b-a3b-un…
MachineGMKtec NucBox EVO-T2SMac Studio
CPUIntel Core™ Ultra X7 358HApple M2 Max
Cores1612
RAM64 GB96 GB
GPUIntel(R) Arc(TM) B390 GPUApple M2 Max
OSMicrosoft Windows 11 Pro 10.0.26200macOS 26.1
Archx64arm64
Power Modebalancedbalanced
Performance
Kimi-48B:48B qwen3.5-35b-a3b-un…
Tokens/sec22.859.8
First chunk721 ms5 ms
TTFT721 ms2.4 s
Load time23.0 s8.5 s
Memory usage25.5 GB0.4 GB
Memory %40%0%
HW Fit Score Breakdown
Kimi-48B:48B
Speed
31/50
TTFT
20/20
Memory
27/30
qwen3.5-35b-a3b-uncenso…
Speed
50/50
TTFT
12/20
Memory
30/30
Quality
Kimi-48B:48B
Reasoning
18/20
Coding
19/20
Instruction
15/20
Structured
15/15
Math
13/15
Multilingual
9/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
qwen3.5-35b-a3b-uncenso…
Reasoning
18/20
Coding
8/20
Instruction
13/20
Structured
6/15
Math
12/15
Multilingual
5/10
Reasoning: Strong Coding: Weak Instruction Following: Adequate Structured Output: Weak Math: Strong Multilingual: Adequate
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