Alibaba

Qwen3 0.6B

reasoning

0,8B

Parameters

0,5 Go

Q4_K_M file

≥ 2,0 Go

Recommended VRAM

40 960

Max context

Standard llama-bench run (prompt 512 / generation 128 tokens), model fully in VRAM. Click a card for details. Electricity cost at the default price (0,25 €/kWh).

Card · Q4_K_MVRAMGenerationPromptVRAM usedPower€ elec. / M tokPrice
RTX 5070 Ti16 Go728 tok/s43 3151,9 Go45 W0,00 €/M tok—

Not measured on these cards yet — click for an estimate:

Technical sheet

Published
2025-04-27
Architecture
28 layers · 8 KV heads · dimension 128
Attention
Standard: every layer keeps the whole context in memory.
Context cache (f16)
≈ 109 MB per 1,000 tokens · 3,5 Go for 32,768 tokens
GGUF file
bartowski/Qwen_Qwen3-0.6B-GGUF · Qwen_Qwen3-0.6B-Q4_K_M.gguf Download (0,5 Go)
Official repo
Qwen/Qwen3-0.6B

Public Hugging Face data (official config.json, GGUF repo). The context cache only counts full-attention layers.