CRia LM 75M Instruct — Hardware Requirements & GPU Compatibility
Chat
CRia LM 75M Instruct is a 76M-parameter open language model from sz14. It supports a context window of up to 4,096 tokens. At BF16 it needs about 0.47 GB of VRAM — see which GPUs and Macs can run it below.
Runs great on a 24 GB GPU
Runs from 8 GB (BF16 · 4K)Best on 24 GB (BF16 · ~1394 tok/s · 4K)Macs from 8 GB (BF16 · ~153 tok/s)
Apache 2.0
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run CRia LM 75M Instruct
One recommended way. Every other method, OS and quant is in the step-by-step guide.Each way opens a step-by-step guide for your OS and quant.
Recommended
vllm serve sz14/cRia-LM-75M-Instruct --max-model-len 4096vLLM repo with its own quantisation
Download: Weights on Hugging Face
Ways to runOther ways
each opens step-by-stepRun in cloud
Runs on RTX 3080 Ti (12 GB) (11 GB headroom) · BF16
- Generation speed
- ~1262 tok/s
- generation speed
- Cost per 1M output tokens
- $0.027
- per 1M output tokens
How Much VRAM Does CRia LM 75M Instruct Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 0.5 GB | — | 16-bit · bfloat — Brain floating point 16 — preferred for training | Fits: 4K context · ~1394 tok/s |
Selected BF16
Brain floating point 160.5GBat 4K context
- Weights
- 0.2 GB
- KV cache
- 0.0 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 23.5 GB free · ~1394 tok/s
≥50 tok/s needs ≥36 GB/s · RTX 5090 ~2478, RTX 3090 Ti ~1394
Which Hardware Can Run CRia LM 75M Instruct?
BF16 · 0.5 GBCRia LM 75M Instruct (BF16) requires 0.5 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 1+ GB is recommended. 52 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti. 163 devices with unified memory can run CRia LM 75M Instruct, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB).
≤ 11 GB
≤ 11 GB tier →fits · 7.5 GB free · up to 4K ctx
16 GPUs · 1 Mac class · 2 device families
RTX 3080~1052Simulate output on RTX 3080RTX 2080 Ti~852Simulate output on RTX 2080 TiRTX 3070 Ti~841Simulate output on RTX 3070 TiM3*8 GB~153Simulate output on iMac 24" M3 (8 GB)Orin Nano~141Simulate output on NVIDIA Jetson Orin Nano 8GB (Super)iPhone~102Simulate output on iPhone 1720 GB
fits · 19.5 GB free · up to 4K ctx
1 GPU
RX 7900 XT~1021Simulate output on RX 7900 XT32–40 GB
fits · 31.5 GB free · up to 4K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~2478Simulate output on RTX 5090M5 Max36 GB~685Simulate output on Mac Studio M5 Max (36 GB)M532 GB~229Simulate output on MacBook Air 13" M5 (32 GB)Orin~283Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~187Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at BF16
Specifications
- Publisher
- sz14
- Parameters
- 76M
- Architecture
- RRTForCausalLM
- Context Length
- 4,096 tokens
- Vocabulary Size
- 49,152
- Release Date
- 2026-09-11
- License
- Apache 2.0
Frequently Asked Questions
How much VRAM does CRia LM 75M Instruct need?
CRia LM 75M Instruct requires 0.5 GB of VRAM at BF16.
VRAM = Weights + KV Cache + Overhead
Weights = 76M × 16 bits ÷ 8 = 0.2 GB
KV Cache + Overhead ≈ 0.3 GB (at 2K context + ~0.3 GB framework)
Fit ratings and hardware model lists check this model with room for a 16K-token context, which needs a little more memory.
KV Cache + Overhead ≈ 0.3 GB (at full 4K context)
VRAM usage by quantization
Can I run CRia LM 75M Instruct on a Mac?
Yes — MacBook Air 13" M3 (8 GB) and 145 other Macs can run CRia LM 75M Instruct. Apple Silicon uses unified memory, so the model shares RAM with the system. At BF16 you need at least 0.5 GB of usable unified memory (RAM minus macOS overhead).
Can I run CRia LM 75M Instruct locally?
Yes — CRia LM 75M Instruct can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is CRia LM 75M Instruct?
At BF16, CRia LM 75M Instruct can reach ~10213 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~1394 tok/s. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = (bandwidth GB/s ÷ model GB) × efficiency
Example: NVIDIA B200 → 8000 ÷ 0.47 × 0.65 = ~11064 tok/s
Estimated speed at BF16 (0.5 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of CRia LM 75M Instruct?
At BF16, the download is about 0.15 GB.
Which GPUs can run CRia LM 75M Instruct?
52 consumer GPUs can run CRia LM 75M Instruct at BF16. Top options include AMD Radeon RX 6700 XT, AMD Radeon RX 6800, AMD Radeon RX 6800 XT. 52 GPUs have plenty of headroom for comfortable inference.
Which devices can run CRia LM 75M Instruct?
163 devices with unified memory can run CRia LM 75M Instruct at BF16 (0.5 GB), including AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10, Beelink GTR9 Pro (Ryzen AI Max+ 395, 128 GB), Framework Desktop (Ryzen AI Max+ 395, 128 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.