Qwen3 14B qwen3-14b

qwen · qwen

unranked — no quality signals yet

params
14.8B
arch
dense
context
128k
license
apache-2.0 open weights
released
Apr 2025
downloads/30d
1.8M

# architecture

attn shared GQA 40q/8kv feed-forward (dense) every parameter, every token out ×40 layers ctx 131,072 14.8B — no routing
layers
40
d_model
5120
heads
40q / 8kv
head dim
128
vocab
151936
family
qwen3

signal path of one layer, generated from the registry's structured fields — dimension lines quote the model's real numbers; an MoE trace forks at the router, a dense trace runs straight through. Geometry fields come from the repo's config.json.

# trend

collecting history — trends appear after a few daily runs.

# where to run

providerquantctx$/M in$/M out$/M cacheprice srctpsuptime
Featherless via hfrouter
SiliconFlow siliconflow
Nscale 40k $0.07$0.20 via hfrouter 95
Nebius 32k $0.08$0.24 via litellm
NextBitint4 40k $0.10$0.22 via openrouter 99.7%
DeepInfrafp8 40k $0.12$0.24 deepinfra 99.8%
Alibabaunknown 128k $0.23$0.91 via openrouter 99.7%

sorted by blended price ((3·input + output) / 4 per 1M) · ✓ = the provider's own catalog confirms the offer · "via …" prices are what the aggregator routing the offer charges, not the provider's own list price

source aliases
openrouter
qwen/qwen3-14b