Only the same benchmark, version, workload, scenario and unit share a row. Missing results are not zero. System results include the full submitted hardware and software configuration.
Arena text preference / chinesehuman preference · 2026-10-28 · rating
Qwen3 30B A3B
1,346.77 rating
Confidence interval: 1,331.89 – 1,361.65
1578 votes
Category
chinese
Evaluated configuration
Qwen3-30B-A3B
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-10-28 · rating
Qwen3 30B A3B
1,336.53 rating
Confidence interval: 1,327.73 – 1,345.34
4504 votes
Category
coding
Evaluated configuration
Qwen3-30B-A3B
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-10-28 · rating
Qwen3 30B A3B
1,271.30 rating
Confidence interval: 1,260.96 – 1,281.64
3340 votes
Category
creative_writing
Evaluated configuration
Qwen3-30B-A3B
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-10-28 · rating
Qwen3 30B A3B
1,334.65 rating
Confidence interval: 1,328.55 – 1,340.74
12315 votes
Category
english
Evaluated configuration
Qwen3-30B-A3B
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating
Qwen3 30B A3B
1,259.93 rating
Confidence interval: 1,253.31 – 1,266.54
18087 votes
Category
exclude_ties
Evaluated configuration
Qwen3-30B-A3B
Evaluation type
human preference
Arena text preference / experthuman preference · 2026-10-28 · rating
Qwen3 30B A3B
1,314.29 rating
Confidence interval: 1,298.16 – 1,330.43
1342 votes
Category
expert
Evaluated configuration
Qwen3-30B-A3B
Evaluation type
human preference
Arena text preference / frenchhuman preference · 2026-10-28 · rating
Qwen3 30B A3B
1,352.16 rating
Confidence interval: 1,321.90 – 1,382.42
352 votes
Category
french
Evaluated configuration
Qwen3-30B-A3B
Evaluation type
human preference
Arena text preference / germanhuman preference · 2026-10-28 · rating
Qwen3 30B A3B
1,307.06 rating
Confidence interval: 1,285.75 – 1,328.38
767 votes
Category
german
Evaluated configuration
Qwen3-30B-A3B
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-10-28 · rating
Qwen3 30B A3B
1,313.96 rating
Confidence interval: 1,307.63 – 1,320.30
10644 votes
Category
hard_prompts
Evaluated configuration
Qwen3-30B-A3B
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating
Qwen3 30B A3B
1,328.88 rating
Confidence interval: 1,320.45 – 1,337.31
5161 votes
Category
hard_prompts_english
Evaluated configuration
Qwen3-30B-A3B
Evaluation type
human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-28 · rating
No catalogued Local AI system meets this memory estimate with the reserved headroom.
Shared-memory systems use a planning budget of 75% of installed memory, leaving 25% for the OS and other allocations. This is an assumption, not a measured GPU allocation. Firmware and driver limits may be lower and may require configuration. Memory matches do not verify a runtime, quantized model artifact or inference speed.
Includes FP16 KV cache, prompt plus generated tokens, quantization metadata and a runtime allowance. GPU matches reserve 10% of VRAM. Memory fit is not a speed or software-compatibility guarantee; quantized weights and runtime support must be available.
API cost
USD / month
Standard text-token estimate. Excludes taxes, caching, batch discounts, reasoning and multimodal surcharges. Provider limits and regional availability may differ.
Qwen3 30B A3B
Qwen3 30B A3B / Pricing tiers 1
Provider / scope
Rate
Currency
Amount / unit
DeepInfraQwen/Qwen3-30B-A3BStandard
Input
USD
0.12 / 1M tokens
Output
USD
0.5 / 1M tokens
Capabilities
Context window
131,072 tokens
Maximum output
16,384 tokens
Reasoning
Yes
Tool calling
Yes
Open weights
Yes
Declared context window
128K*
Model type
LLM (MoE)*
Declared modalities
Text → Text*
Model license
Apache 2.0 (open)*
Total parameters
30.53 B
Checkpoint tensor payload
56.87 GiB
Input modalities
text
Output modalities
text
Processing & platform
Architecture
qwen3_moe
System configuration
Detailed specifications
Specifications · 15 fields
api providers
Alibaba, OpenRouter, Ollama*Scope and conditions
native_context
metadata
name
Convly AI Models Database*
description
Hand-verified specifications, licences, API pricing (USD) and local-hardware VRAM requirements for frontier and open-weight AI models.*
generated
2026-09-22T15:41:48+00:00*
model_count
43*
fields
slug*
name*
developer*
model_type*
modality*
parameters*
context_window*
max_output*
open_weights*
license*
release_date*
input_price*
output_price*
price_unit*
price_tiers*
vram_q4*
vram_q4_gb*
min_gpu*
intelligence*
api_providers*
official_url*
retired*
convly_url*
developer
Alibaba*
price_unit
Not reported*
price_tiers
Not reported*
context window
128K*Scope and conditions
native_context
metadata
name
Convly AI Models Database*
description
Hand-verified specifications, licences, API pricing (USD) and local-hardware VRAM requirements for frontier and open-weight AI models.*
generated
2026-09-22T15:41:48+00:00*
model_count
43*
fields
slug*
name*
developer*
model_type*
modality*
parameters*
context_window*
max_output*
open_weights*
license*
release_date*
input_price*
output_price*
price_unit*
price_tiers*
vram_q4*
vram_q4_gb*
min_gpu*
intelligence*
api_providers*
official_url*
retired*
convly_url*
developer
Alibaba*
price_unit
Not reported*
price_tiers
Not reported*
developer
Alibaba*Scope and conditions
native_context
metadata
name
Convly AI Models Database*
description
Hand-verified specifications, licences, API pricing (USD) and local-hardware VRAM requirements for frontier and open-weight AI models.*
generated
2026-09-22T15:41:48+00:00*
model_count
43*
fields
slug*
name*
developer*
model_type*
modality*
parameters*
context_window*
max_output*
open_weights*
license*
release_date*
input_price*
output_price*
price_unit*
price_tiers*
vram_q4*
vram_q4_gb*
min_gpu*
intelligence*
api_providers*
official_url*
retired*
convly_url*
developer
Alibaba*
price_unit
Not reported*
price_tiers
Not reported*
input price
0.12*Scope and conditions
native_context
metadata
name
Convly AI Models Database*
description
Hand-verified specifications, licences, API pricing (USD) and local-hardware VRAM requirements for frontier and open-weight AI models.*
generated
2026-09-22T15:41:48+00:00*
model_count
43*
fields
slug*
name*
developer*
model_type*
modality*
parameters*
context_window*
max_output*
open_weights*
license*
release_date*
input_price*
output_price*
price_unit*
price_tiers*
vram_q4*
vram_q4_gb*
min_gpu*
intelligence*
api_providers*
official_url*
retired*
convly_url*
developer
Alibaba*
price_unit
Not reported*
price_tiers
Not reported*
license
Apache 2.0 (open)*Scope and conditions
native_context
metadata
name
Convly AI Models Database*
description
Hand-verified specifications, licences, API pricing (USD) and local-hardware VRAM requirements for frontier and open-weight AI models.*
generated
2026-09-22T15:41:48+00:00*
model_count
43*
fields
slug*
name*
developer*
model_type*
modality*
parameters*
context_window*
max_output*
open_weights*
license*
release_date*
input_price*
output_price*
price_unit*
price_tiers*
vram_q4*
vram_q4_gb*
min_gpu*
intelligence*
api_providers*
official_url*
retired*
convly_url*
developer
Alibaba*
price_unit
Not reported*
price_tiers
Not reported*
min gpu
RTX 4090 24GB (Q4) — fast, 3B active*Scope and conditions
native_context
metadata
name
Convly AI Models Database*
description
Hand-verified specifications, licences, API pricing (USD) and local-hardware VRAM requirements for frontier and open-weight AI models.*
generated
2026-09-22T15:41:48+00:00*
model_count
43*
fields
slug*
name*
developer*
model_type*
modality*
parameters*
context_window*
max_output*
open_weights*
license*
release_date*
input_price*
output_price*
price_unit*
price_tiers*
vram_q4*
vram_q4_gb*
min_gpu*
intelligence*
api_providers*
official_url*
retired*
convly_url*
developer
Alibaba*
price_unit
Not reported*
price_tiers
Not reported*
modality
Text → Text*Scope and conditions
native_context
metadata
name
Convly AI Models Database*
description
Hand-verified specifications, licences, API pricing (USD) and local-hardware VRAM requirements for frontier and open-weight AI models.*
generated
2026-09-22T15:41:48+00:00*
model_count
43*
fields
slug*
name*
developer*
model_type*
modality*
parameters*
context_window*
max_output*
open_weights*
license*
release_date*
input_price*
output_price*
price_unit*
price_tiers*
vram_q4*
vram_q4_gb*
min_gpu*
intelligence*
api_providers*
official_url*
retired*
convly_url*
developer
Alibaba*
price_unit
Not reported*
price_tiers
Not reported*
model type
LLM (MoE)*Scope and conditions
native_context
metadata
name
Convly AI Models Database*
description
Hand-verified specifications, licences, API pricing (USD) and local-hardware VRAM requirements for frontier and open-weight AI models.*
generated
2026-09-22T15:41:48+00:00*
model_count
43*
fields
slug*
name*
developer*
model_type*
modality*
parameters*
context_window*
max_output*
open_weights*
license*
release_date*
input_price*
output_price*
price_unit*
price_tiers*
vram_q4*
vram_q4_gb*
min_gpu*
intelligence*
api_providers*
official_url*
retired*
convly_url*
developer
Alibaba*
price_unit
Not reported*
price_tiers
Not reported*
name
Qwen3 30B-A3B*Scope and conditions
native_context
metadata
name
Convly AI Models Database*
description
Hand-verified specifications, licences, API pricing (USD) and local-hardware VRAM requirements for frontier and open-weight AI models.*
generated
2026-09-22T15:41:48+00:00*
model_count
43*
fields
slug*
name*
developer*
model_type*
modality*
parameters*
context_window*
max_output*
open_weights*
license*
release_date*
input_price*
output_price*
price_unit*
price_tiers*
vram_q4*
vram_q4_gb*
min_gpu*
intelligence*
api_providers*
official_url*
retired*
convly_url*
developer
Alibaba*
price_unit
Not reported*
price_tiers
Not reported*
open weights
yes*Scope and conditions
native_context
metadata
name
Convly AI Models Database*
description
Hand-verified specifications, licences, API pricing (USD) and local-hardware VRAM requirements for frontier and open-weight AI models.*
generated
2026-09-22T15:41:48+00:00*
model_count
43*
fields
slug*
name*
developer*
model_type*
modality*
parameters*
context_window*
max_output*
open_weights*
license*
release_date*
input_price*
output_price*
price_unit*
price_tiers*
vram_q4*
vram_q4_gb*
min_gpu*
intelligence*
api_providers*
official_url*
retired*
convly_url*
developer
Alibaba*
price_unit
Not reported*
price_tiers
Not reported*
output price
0.5*Scope and conditions
native_context
metadata
name
Convly AI Models Database*
description
Hand-verified specifications, licences, API pricing (USD) and local-hardware VRAM requirements for frontier and open-weight AI models.*
generated
2026-09-22T15:41:48+00:00*
model_count
43*
fields
slug*
name*
developer*
model_type*
modality*
parameters*
context_window*
max_output*
open_weights*
license*
release_date*
input_price*
output_price*
price_unit*
price_tiers*
vram_q4*
vram_q4_gb*
min_gpu*
intelligence*
api_providers*
official_url*
retired*
convly_url*
developer
Alibaba*
price_unit
Not reported*
price_tiers
Not reported*
parameters
30B total / 3B active (MoE)*Scope and conditions
native_context
metadata
name
Convly AI Models Database*
description
Hand-verified specifications, licences, API pricing (USD) and local-hardware VRAM requirements for frontier and open-weight AI models.*
generated
2026-09-22T15:41:48+00:00*
model_count
43*
fields
slug*
name*
developer*
model_type*
modality*
parameters*
context_window*
max_output*
open_weights*
license*
release_date*
input_price*
output_price*
price_unit*
price_tiers*
vram_q4*
vram_q4_gb*
min_gpu*
intelligence*
api_providers*
official_url*
retired*
convly_url*
developer
Alibaba*
price_unit
Not reported*
price_tiers
Not reported*
release date
2025*Scope and conditions
native_context
metadata
name
Convly AI Models Database*
description
Hand-verified specifications, licences, API pricing (USD) and local-hardware VRAM requirements for frontier and open-weight AI models.*
generated
2026-09-22T15:41:48+00:00*
model_count
43*
fields
slug*
name*
developer*
model_type*
modality*
parameters*
context_window*
max_output*
open_weights*
license*
release_date*
input_price*
output_price*
price_unit*
price_tiers*
vram_q4*
vram_q4_gb*
min_gpu*
intelligence*
api_providers*
official_url*
retired*
convly_url*
developer
Alibaba*
price_unit
Not reported*
price_tiers
Not reported*
vram q4
~18 GB*Scope and conditions
native_context
metadata
name
Convly AI Models Database*
description
Hand-verified specifications, licences, API pricing (USD) and local-hardware VRAM requirements for frontier and open-weight AI models.*
generated
2026-09-22T15:41:48+00:00*
model_count
43*
fields
slug*
name*
developer*
model_type*
modality*
parameters*
context_window*
max_output*
open_weights*
license*
release_date*
input_price*
output_price*
price_unit*
price_tiers*
vram_q4*
vram_q4_gb*
min_gpu*
intelligence*
api_providers*
official_url*
retired*
convly_url*
developer
Alibaba*
price_unit
Not reported*
price_tiers
Not reported*
vram q4 gb
18* GBScope and conditions
native_context
metadata
name
Convly AI Models Database*
description
Hand-verified specifications, licences, API pricing (USD) and local-hardware VRAM requirements for frontier and open-weight AI models.*