Qwen3.8 2.4T A95B qwen3.8-2.4t-a95b

qwen · qwen

unranked — no quality signals yet

params
2446.2B
arch
moe
context
1024k
license
other open weights
released
Aug 2026
downloads/30d
25.9k

# architecture

attn shared GQA 64q/4kv router top-10 of 512 expert ×512 expert out ×92 layers ctx 1,048,576 2446.2B pool
layers
92
d_model
8192
heads
64q / 4kv
head dim
256
experts
top-10 of 512
vocab
248320
family
qwen3_5_moe_text

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

OGM score · last 81 days
OGM score over 81 days
overall rank (up is better)
Overall rank over 81 days

methodology changed during this history window; score movement across that boundary is not model movement. See methodology v6.

# where to run

providerquantctx$/M in$/M out$/M cacheprice srctpsuptime✓
Chutes — ——— chutes — — ✓
Aihubmix 1000k $2.00$6.00— via litellm — —
Alibabaunknown 1000k $2.00$6.00$0.25 via openrouter — 99.8%
DeepInfra 256k $2.00$6.00— via hfrouter 73 —
Novitaunknown 1000k $2.00$6.00— novita — 99.9% ✓
SiliconFlowfp8 1024k $2.00$6.00$0.25 openrouter — 100.0% ✓
StreamLake 983k $2.00$6.00— via litellm — —
Togetherunknown 1010k $2.00$6.00$0.25 via openrouter — 100.0%
Veniceunknown 256k $2.50$7.50— venice — 98.9% ✓

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/qwen3.8-2.4t-a95b