Model Spend Arena2ND ED.
14B · dense · 40,960 ctx · 2026-08-14

Qwen3 14B

Runs on ≤16 GB · Hugging Face ↗

llama.cppvLLMOllamaLM Studio

Coding index 13.8 (Artificial Analysis)

The dense 14B of the Qwen3 line — a solid mid-small generalist with a reasoning mode.

First-party test · not the AA coding index

HumanEval pass@1 63% (19/30), via local GPU (Ollama, Q4_K_M). Measured by us on this hardware, as a rough sanity check — HumanEval is a different, easier, partly-contaminated benchmark than Artificial Analysis’ composite, so it is not comparable to the coding-index column.

First-party test · not the AA coding index

BigCodeBench-Hard pass@1 31% (38/121), via local GPU (Ollama, num_ctx 16384, budget 12K) — comparable full-148. The brutal counterpart to HumanEval — where HumanEval saturates near the top, BCB-Hard spreads the field, so this is the number that actually separates coding ability.

First-party measurement

~25 tok/s on RTX 4060 Ti, measured by us.

Sizes on disk

Real GGUF file sizes = weight VRAM. Add the KV cache for your context (≈5 GB at 32K, fp16).

QuantizationSize
Q3_K_M7.3 GB
IQ4_XS8.1 GB
Q4_08.5 GB
Q4_K_S8.6 GB
Q4_K_M9.0 GB
Q49.2 GB
Q4_19.4 GB
Q5_K_M10.5 GB
Q8_015.7 GB
Q2_K17.8 GB
Q818.8 GB
Q6_K25.4 GB
BF1629.5 GB

Config tips

~9 GB at Q4, fits 16 GB with generous context. Turn thinking off for latency- sensitive agent loops.