Qwen3-8B

Model performance

Radar task score: four tests, equal weight. An experimental summary of these tasks, not a universal intelligence rating.

Tested configuration Radar task score

Unrated

1/4 core tests · not enough evidence

2 benchmark results for this configuration

Scientific reasoning

GPQA Diamond · 25%

Expert-written science questions; strict multiple-choice scoring. Chance accuracy is 25%.

Qwen3-8B 47.5^*% Approx. 95% interval: 42.3–52.6% · 2026-08-27

Novel problem solving

Mystery Game Puzzles · 25%

Best-next-move puzzles in an undisclosed game variant. A narrow reasoning test, not general intelligence.

Qwen3-8B Not available

Advanced mathematics

FrontierMath Tiers 1-3 · 25%

Private v2 mathematics problems with Python tools. Earlier versions and Tier 4 are excluded.

Qwen3-8B Not available

Factual answers

SimpleQA Verified · 25%

Correct factual answers under a guessing prompt, graded by a model. Not a hallucination or abstention score.

Qwen3-8B Not available

Competition mathematics

OTIS Mock AIME 2024-2025 · Separate result

Competition problems with model-extracted answers checked against an exact key. Earlier grading procedures are excluded.

Qwen3-8B 22.2^*% Approx. 95% interval: 13.3–31.1% · 2026-08-27

Bars show reported task scores. Whiskers are approximate 95% intervals where standard errors are available. Different reasoning budgets are not equal-cost tests. Missing results are never zero.

Run it locally

Inference · memory estimate

Qwen3-8B

8.19 B total parameters · qwen3 · BF16

Published checkpoint tensor payload: 15.3 GiB. This includes stored copies and buffers; it is separate from the runtime estimates below.

Weight precision Total context Check a GPU Check a Local AI system

Estimated accelerator memory5.8 GiB

Weights: 4.2 GiB
KV cache: 0.6 GiB
Runtime allowance: 1.0 GiB

One user, full model in accelerator memory.

GPUs with memory headroom

Local AI systems with memory headroom

AMD Ryzen AI Halo (Ryzen AI Max+ 395, 128 GB) Planning budget: 96.0 GiB
ASUS Ascent GX10 (128 GB) Planning budget: 96.0 GiB
Beelink GTR9 Pro (Ryzen AI Max+ 395, 128 GB) Planning budget: 96.0 GiB
Framework Desktop (Ryzen AI Max+ 395, 128 GB) Planning budget: 96.0 GiB
NVIDIA DGX Spark (128 GB) Planning budget: 96.0 GiB

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

Input tokens / monthOutput tokens / month

Standard text-token estimate. Excludes taxes, caching, batch discounts, reasoning and multimodal surcharges. Provider limits and regional availability may differ.

Qwen3-8B

Provider offer

Capabilities

Context window: 40,960 tokens
Maximum output: 32,768 tokens
Reasoning: Yes
Tool calling: Yes
Open weights: Yes
Declared context window: 128K^*
Model type: LLM (dense)^*
Declared modalities: Text → Text^*
Model license: apache-2.0
Total parameters: 8.19 B
Checkpoint tensor payload: 15.26 GiB

Input modalities

text

Output modalities

text

Processing & platform

Architecture: qwen3

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

0.04^*

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 3060 8GB / any 8GB GPU^*

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 (dense)^*

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 8B^*

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

0.14^*

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

8B^*

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

~5 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

5^* 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^*