JiRackUltra_14b
CMSManhattanmittext

JiRackUltra_14b

Updated Sep 19, 2026
Parameters
14.8B
Context
131,072
License
mit
Updated
Sep 19, 2026

Will it run on your hardware?

Pick your GPU memory - see which quantizations fit, and the cheapest card for the rest

Runs on your 24 GB - best at Q8_0
3 of 4 quantizations fit JiRackUltra_14b with real runtime overhead.
Q4_K_M
9 GB
Q5_K_M
11 GB
Q8_0
16 GB
FP16
30 GB
fits tight too big

Need an exact figure for your context length? Use the VRAM calculator.

Run it locally

Copy-paste - running in under a minute

vLLMOpenAI-compatible API
vllm serve CMSManhattan/JiRackUltra_14b

New to this? Start with Ollama · serve to many users with vLLM.

Deep dive

Notes, sources, and the full write-up

JiRackUltra_14b is a 14.8B-parameter mit model from CMSManhattan. At Q4_K_M it needs roughly 9 GB of VRAM, placing it in the 8–12 GB GPU hardware tier.

Popularity

JiRackUltra_14b has 852,833 downloads in the last month on HuggingFace and 2 likes.

Frequently asked

Quick answers to common questions

How much VRAM does JiRackUltra_14b need?

JiRackUltra_14b with 14.8B parameters needs approximately 9 GB at Q4_K_M quantization. Use our VRAM calculator for an exact estimate.

Is JiRackUltra_14b better than other CMSManhattan models?

JiRackUltra_14b has 14.8B parameters with 131,072 context - a strong choice for general use.

What license is JiRackUltra_14b under?

JiRackUltra_14b is released under the mit license, making it suitable for most commercial and personal projects.

What hardware runs JiRackUltra_14b well?

With 14.8B parameters, JiRackUltra_14b requires adequate VRAM. High-end GPUs like the RTX 4090 (24GB), RTX 5090 (32GB), or Mac Studio with unified memory are good options. Check our hardware directory for specific recommendations.

What is the best quantization for JiRackUltra_14b?

Q4_K_M is the recommended sweet spot - ~98% of FP16 quality at ~27% of the size. Q5_K_M (~11 GB) is an option if you have spare VRAM. Use our VRAM calculator to compare.

How long can JiRackUltra_14b's context window handle?

JiRackUltra_14b supports a 131,072-token context window - enough for very long documents, codebases, or multi-turn conversations. Real-world usable context may vary by implementation.

What models compete with JiRackUltra_14b?

JiRackUltra_14b competes with other models in its class. Browse our model directory for comparisons, benchmarks, and community reviews to find the best fit.

Nearby options

Similar models and compatible hardware by spec

Comments coming soon

Configure NEXT_PUBLIC_GISCUS_REPO_ID and NEXT_PUBLIC_GISCUS_CATEGORY_ID at giscus.app to enable.