stelterlab / text-generation updated 1 year ago

Mistral-Small-24B-Instruct-2501-AWQ

Name: Mistral-Small-24B-Instruct-2501-AWQ
Author: stelterlab

AWQ quantization: done by stelterlab in INT4 GEMM with AutoAWQ by casper-hansen (https://github.com/casper-hansen/AutoAWQ/)

Params

23.6 B

Context

32,768

Downloads 30d

255 K

Likes

Commercial use: allowed apache-2.0 Not gated SAFETENSORS 10 languages View on Hugging Face ↗

Download history

daily snapshots · 10 days

255 K236 K

Jul 28Jul 31Aug 3Aug 6

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	14.2 GB	19.7 GB	⚠️ Tight — reduce context
model.safetensors (bf16, full)	bf16 + 32K ctx	14.2 GB	30.3 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/mistral-small-24b-instruct-2501-awq
{
  "hf_id": "stelterlab/Mistral-Small-24B-Instruct-2501-AWQ",
  "params_b": 23.57,
  "context_length": 32768,
  "license": { "id": "apache-2.0", "commercial": "yes" },
  "downloads_30d": 254550,
  "vram_estimates": [
    { "quant": "i32", "gb": 19.7 }
  ],
  "updated_at": "2026-07-28T18:07:30Z"
}

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

Specifications

Architecture: MistralForCausalLM
Parameters: 23.6 B
Tensor type: I32
Context length: 32,768
Vocabulary: 131,072
Layers / heads: 40 / 32
Licence: apache-2.0
First seen on the Hub: 2025-01-30
Training datasets: undisclosed
Added to our catalog: 2026-07-28

Compare with

Qwen3-8B 16.3 M Qwen2.5-7B-Instruct 12.1 M Qwen3.6-35B-A3B-NVFP4 11.3 M gpt-oss-20b 8.6 M Qwen3-32B 8.3 M dolphin-2.9.1-yi-1.5-34b 4.6 M

Appears in

Best open coding models Commercial-use text models Models that fit in 12 GB