cyankiwi / text-generation Open weights updated 1 week ago

MiniCPM-SALA-AWQ-8bit

Name: MiniCPM-SALA-AWQ-8bit
Author: cyankiwi

Version llm-compressor Calibration nvidia/Llama-Nemotron-Post-Training-Dataset Model Size 10.63 GB

Params

3.1 B

Context

524,288

Downloads 30d

621 K

Likes

Commercial use: allowed apache-2.0 Not gated SAFETENSORS 2 languages View on Hugging Face ↗

Download history

daily snapshots · 91 days

▲ 17 K in the last 30 days (2.9%)

622 K166 K

Aug 12Sep 11Oct 11Nov 10

Can you run it?

Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.

File	Quant	Size	Est. VRAM	Verdict on RTX 4090 · 24 GB
model.safetensors	i32	10.6 GB	12.7 GB	✅ Runs comfortably
model.safetensors (bf16, full)	bf16 + 512K ctx	10.6 GB	41.9 GB	❌ Won’t fit

Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.

Run it

copy-paste, exact tags checked against the Hub

~ · curl · api/v1

$ curl -s https://aimodelscomparison.com/api/v1/models/minicpm-sala-awq-8bit
{
  "hf_id": "cyankiwi/MiniCPM-SALA-AWQ-8bit",
  "params_b": 3.10,
  "context_length": 524288,
  "license": { "id": "apache-2.0", "commercial": "yes" },
  "downloads_30d": 620818,
  "vram_estimates": [
    { "quant": "i32", "gb": 12.7 }
  ],
  "updated_at": "2026-11-01T01:00:08Z"
}

est. VRAM —on RTX 4090 · 24 GBJSON API →

Specifications

Architecture: MiniCPMSALAForCausalLM
Parameters: 3.1 B
Tensor type: I32
Context length: 524,288
Vocabulary: 73,448
Layers / heads: 32 / 32
Licence: apache-2.0
First seen on the Hub: 2026-02-15
Training datasets: undisclosed
Added to our catalog: 2026-08-12

Compare with any text-generation model

Popular comparisons

Qwen3-8B 6.8 M Qwen2.5-7B-Instruct 6.0 M Qwen2.5-1.5B-Instruct 5.0 M Qwen3-4B 4.0 M Qwen3-1.7B 3.7 M Qwen2.5-3B-Instruct 2.6 M