lmstudio-community / text-generation updated 6 months ago

GLM-4.7-Flash-MLX-8bit

Name: GLM-4.7-Flash-MLX-8bit
Author: lmstudio-community

👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord.

Params

29.9 B

Context

202,752

Downloads 30d

220 K

Likes

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

Download history

daily snapshots · 10 days

242 K220 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	u32	31.8 GB	40.0 GB	❌ Won’t fit
model.safetensors (bf16, full)	bf16 + 198K ctx	31.8 GB	146.7 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/glm-4-7-flash-mlx-8bit
{
  "hf_id": "lmstudio-community/GLM-4.7-Flash-MLX-8bit",
  "params_b": 29.94,
  "context_length": 202752,
  "license": { "id": "mit", "commercial": "yes" },
  "downloads_30d": 219995,
  "vram_estimates": [
    { "quant": "u32", "gb": 40.0 }
  ],
  "updated_at": "2026-07-28T18:07:25Z"
}

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

Specifications

Architecture: Glm4MoeLiteForCausalLM
Parameters: 29.9 B
Tensor type: U32
Context length: 202,752
Vocabulary: 154,880
Layers / heads: 47 / 20
Licence: mit
First seen on the Hub: 2026-01-19
Base model: GLM-4.7-Flash
Training datasets: undisclosed
Added to our catalog: 2026-07-28

Family

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

Base GLM-4.7-Flash zai-org 2.1 M

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