unsloth / text-generation updated 7 months ago

GLM-4.7-Flash-GGUF

Name: GLM-4.7-Flash-GGUF
Author: unsloth

You can now use Z.ai's recommended parameters and get great results: - For general use-case: --temp 1.0 --top-p 0.95 - For tool-calling: --temp 0.7 --top-p 1.0 - If using llama.cpp, set --min-p 0.01 as llama.cpp's default is 0.05

Params

—

Context

—

Downloads 30d

216 K

Likes

703

Commercial use: allowed mit Not gated GGUF 2 languages View on Hugging Face ↗

Download history

daily snapshots · 37 days

▲ 22 K in the last 30 days (9.4%)

250 K185 K

Aug 16Aug 28Sep 9Sep 21

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
GLM-4.7-Flash-Q2_K.gguf	Q2_K	11.3 GB	13.0 GB	✅ Runs comfortably
GLM-4.7-Flash-Q2_K_L.gguf	Q2_K_L	11.4 GB	13.1 GB	✅ Runs comfortably
GLM-4.7-Flash-Q3_K_S.gguf	Q3_K_S	13.3 GB	15.1 GB	✅ Runs comfortably
GLM-4.7-Flash-Q3_K_M.gguf	Q3_K_M	14.6 GB	16.6 GB	✅ Runs comfortably
GLM-4.7-Flash-IQ4_XS.gguf	IQ4_XS	16.3 GB	18.4 GB	✅ Runs comfortably
GLM-4.7-Flash-IQ4_NL.gguf	IQ4_NL	17.2 GB	19.4 GB	✅ Runs comfortably
GLM-4.7-Flash-Q4_0.gguf	Q4_0	17.2 GB	19.4 GB	✅ Runs comfortably
GLM-4.7-Flash-BF16-00001-of-00002.gguf	GGUF	49.9 GB	55.4 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

~ · ollama · Q4_0

$ ollama run glm-4-7-flash-gguf

# pin the quantization explicitly
$ ollama run glm-4-7-flash-gguf-q4_0

est. VRAM 19.4 GBon RTX 4090 · 24 GBJSON API →

Specifications

Licence: mit
First seen on the Hub: 2026-01-20
Base model: GLM-4.7-Flash
Training datasets: undisclosed
Added to our catalog: 2026-08-16

Family

Base model and the most-downloaded derivatives in the catalog.

Base GLM-4.7-Flash zai-org 1.9 M

Compare with any text-generation model