FITMYLLM · AUGUST 17, 2026 · OPEN METHODOLOGY · COMMUNITY BENCHMARKS
LIVE · UPDATED DAILY
80B
Parameters (13B active)
Quantization Options Select your GPU for speed estimates Context length: 4K 8K 16K 32K 64K 128K 250K
Quant Bits VRAM @ 16K Quality IQ2_M 2.93 31.3 GB
29.8 + 1.5 KV
low Q2_K 3.16 33.6 GB
32.1 + 1.5 KV
low IQ3_XXS 3.25 34.5 GB
33.0 + 1.5 KV
low IQ3_XS 3.5 37.0 GB
35.5 + 1.5 KV
low Q3_K_S 3.64 38.4 GB
36.9 + 1.5 KV
low IQ3_M 3.76 39.6 GB
38.1 + 1.5 KV
low Q3_K_M 4 42.0 GB
40.5 + 1.5 KV
low Q3_K_L 4.3 45.0 GB
43.5 + 1.5 KV
moderate IQ4_XS 4.46 46.6 GB
45.1 + 1.5 KV
moderate Q4_K_S 4.67 48.7 GB
47.2 + 1.5 KV
moderate Q4_K_M 4.89 50.9 GB
49.4 + 1.5 KV
good Q5_K_S 5.57 57.7 GB
56.2 + 1.5 KV
good Q5_K_M 5.7 59.0 GB
57.5 + 1.5 KV
good Q6_K 6.56 67.6 GB
66.1 + 1.5 KV
excellent Q8_0 8.5 87.0 GB
85.5 + 1.5 KV
lossless FP16 16 162.0 GB
160.5 + 1.5 KV
lossless
Select your GPU above to see speed estimates and compatibility for each quantization.
Deploying for a team or in production? Size GPUs, cost & scaling in Enterprise → ▸ READY TO RUN THIS? RENT BY THE HOUR
RENT A GPU AND RUN HUNYUAN A13B NOW
Spin up an A100 / H100 / 4090 in ~60s. Pay by the second. Cancel anytime.
Community Ratings Chat Coding Reasoning Creative Vision Roleplay Agentic
Loading ratings...
Run this model IQ2_M — 29.8 GB VRAM Q2_K — 32.1 GB VRAM IQ3_XXS — 33.0 GB VRAM IQ3_XS — 35.5 GB VRAM Q3_K_S — 36.9 GB VRAM IQ3_M — 38.1 GB VRAM Q3_K_M — 40.5 GB VRAM Q3_K_L — 43.5 GB VRAM IQ4_XS — 45.1 GB VRAM Q4_K_S — 47.2 GB VRAM Q4_K_M — 49.4 GB VRAM Q5_K_S — 56.2 GB VRAM Q5_K_M — 57.5 GB VRAM Q6_K — 66.1 GB VRAM Q8_0 — 85.5 GB VRAM FP16 — 160.5 GB VRAM
Ollama llama.cpp vLLM LM Studio KoboldCpp Jan Docker
▸ Easiest way to get started · Beginners
DOCS ↗ curl -fsSL https://ollama.com/install.sh | shCOPY
$ ollama run hunyuan:80b-q4_K_MCOPY
Tag may need adjustment — check ollama.com/library/hunyuan for available tags.
▸ SETUP GUIDE >_
Auto-setup with fitmyllm CLI Detects your GPU, recommends the best model, downloads it, and starts chatting — zero config. Benchmarks your speed and contributes anonymous data to improve predictions.
Auto-detect GPU Live tok/s in chat Speed benchmarks 9 inference engines
GPUs that can run this model At Q4_K_M quantization. Sorted by minimum VRAM.
Find the best GPU for Hunyuan A13B
Build Hardware for Hunyuan A13B Tencent Hunyuan A13B — large MoE model with strong Chinese-English capabilities.
Read full model card ▸ COLOPHON FITMYLLM · INDEPENDENT · DATA-DRIVEN
FITMYLLM · EST. 2025 · © 2026
RECOMMENDATIONS FROM PUBLISHED MATH, CORRECTED BY THE COMMUNITY — 30.
▸ SPEC SHEET
Hunyuan A13B — 80B MoE. ▸ SPECIFICATIONS
PARAMETERS 80B (13B active)
ARCHITECTURE Mixture of Experts
CONTEXT LENGTH 250K tokens
CAPABILITIES chat, coding, reasoning, multilingual, math
RELEASE DATE 2025-06-27
PROVIDER Tencent
FAMILY hunyuan ▸ VRAM REQUIREMENTS
QUANT BPW VRAM QUALITY IQ2_M 2.93 29.8 GB 75% Q2_K 3.16 32.1 GB 78% IQ3_XXS 3.25 33.0 GB 82% IQ3_XS 3.5 35.5 GB 84% Q3_K_S 3.64 36.9 GB 85% IQ3_M 3.76 38.1 GB 86% Q3_K_M 4 40.5 GB 88% Q3_K_L 4.3 43.5 GB 90% IQ4_XS 4.46 45.1 GB 92% Q4_K_S 4.67 47.2 GB 93% Q4_K_M 4.89 49.4 GB 94% Q5_K_S 5.57 56.2 GB 96% Q5_K_M 5.7 57.5 GB 96% Q6_K 6.56 66.1 GB 97% Q8_0 8.5 85.5 GB 100% FP16 16 160.5 GB 100%
§ 01 BENCHMARK SCORES
MMLU-PRO 67.2
MATH 94.3
BBH 89.1
GPQA 71.2
MBPP 83.9
§ 03 COMPATIBLE GPUs
30 @ Q4_K_M Feedback