FITMYLLM · AUGUST 17, 2026 · OPEN METHODOLOGY · COMMUNITY BENCHMARKS
LIVE · UPDATED DAILY
Quantization Options Select your GPU for speed estimates Context length: 4K 8K 16K 32K
Quant Bits VRAM @ 16K Quality IQ2_XXS 2.38 54.6 GB
43.0 + 11.6 KV
low IQ2_M 2.93 64.4 GB
52.8 + 11.6 KV
low Q2_K 3.16 68.5 GB
56.9 + 11.6 KV
low IQ3_XXS 3.25 70.1 GB
58.5 + 11.6 KV
low IQ3_XS 3.5 74.6 GB
63.0 + 11.6 KV
low Q3_K_S 3.64 77.1 GB
65.5 + 11.6 KV
low IQ3_M 3.76 79.2 GB
67.6 + 11.6 KV
low Q3_K_M 4 83.5 GB
71.9 + 11.6 KV
low Q3_K_L 4.3 88.9 GB
77.2 + 11.6 KV
moderate IQ4_XS 4.46 91.7 GB
80.1 + 11.6 KV
moderate Q4_K_S 4.67 95.5 GB
83.8 + 11.6 KV
moderate Q4_K_M 4.89 99.4 GB
87.8 + 11.6 KV
good Q5_K_S 5.57 111.5 GB
99.9 + 11.6 KV
good Q5_K_M 5.7 113.9 GB
102.2 + 11.6 KV
good Q6_K 6.56 129.2 GB
117.6 + 11.6 KV
excellent Q8_0 8.5 163.8 GB
152.2 + 11.6 KV
lossless FP16 16 297.7 GB
286.1 + 11.6 KV
lossless
Select your GPU above to see speed estimates and compatibility for each quantization.
Too big for a single GPU — plan a multi-GPU deployment
Even the lightest quant needs ~55 GB. Size GPUs, replicas, TCO and scaling for a production setup. Open in Enterprise →
▸ READY TO RUN THIS? RENT BY THE HOUR
RENT A GPU AND RUN DOTS.LLM1.INST 142.8B 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_XXS — 43.0 GB VRAM IQ2_M — 52.8 GB VRAM Q2_K — 56.9 GB VRAM IQ3_XXS — 58.5 GB VRAM IQ3_XS — 63.0 GB VRAM Q3_K_S — 65.5 GB VRAM IQ3_M — 67.6 GB VRAM Q3_K_M — 71.9 GB VRAM Q3_K_L — 77.2 GB VRAM IQ4_XS — 80.1 GB VRAM Q4_K_S — 83.8 GB VRAM Q4_K_M — 87.8 GB VRAM Q5_K_S — 99.9 GB VRAM Q5_K_M — 102.2 GB VRAM Q6_K — 117.6 GB VRAM Q8_0 — 152.2 GB VRAM FP16 — 286.1 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 other:143b-q4_K_MCOPY
Tag may need adjustment — check ollama.com/library/other 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 dots.llm1.inst 142.8B
Build Hardware for dots.llm1.inst 142.8B ▸ COLOPHON FITMYLLM · INDEPENDENT · DATA-DRIVEN
FITMYLLM · EST. 2025 · © 2026
RECOMMENDATIONS FROM PUBLISHED MATH, CORRECTED BY THE COMMUNITY — 30.
▸ SPEC SHEET
dots.llm1.inst 142.8B — 142.8B Dense. ▸ SPECIFICATIONS
PARAMETERS 142.8B
ARCHITECTURE Dense Transformer
CONTEXT LENGTH 32K tokens
CAPABILITIES chat
RELEASE DATE 2025-05-14
PROVIDER Rednote
FAMILY other ▸ VRAM REQUIREMENTS
QUANT BPW VRAM QUALITY IQ2_XXS 2.38 43.0 GB 65% IQ2_M 2.93 52.8 GB 75% Q2_K 3.16 56.9 GB 78% IQ3_XXS 3.25 58.5 GB 82% IQ3_XS 3.5 63.0 GB 84% Q3_K_S 3.64 65.5 GB 85% IQ3_M 3.76 67.6 GB 86% Q3_K_M 4 71.9 GB 88% Q3_K_L 4.3 77.2 GB 90% IQ4_XS 4.46 80.1 GB 92% Q4_K_S 4.67 83.8 GB 93% Q4_K_M 4.89 87.8 GB 94% Q5_K_S 5.57 99.9 GB 96% Q5_K_M 5.7 102.2 GB 96% Q6_K 6.56 117.6 GB 97% Q8_0 8.5 152.2 GB 100% FP16 16 286.1 GB 100%
§ 02 RUN COMMAND
Run dots.llm1.inst 142.8B locally with Ollama — needs 87.8 GB VRAM at Q4_K_M:
$ ollama run other:142b
§ 03 COMPATIBLE GPUs
30 @ Q4_K_M Feedback