GLM 4.7 Flash Claude Opus 4.5 High Reasoning Distill 4bit is an open-source language model by mlx-community. Features: 29.9b LLM, VRAM: 17GB, Context: 198K, License: apache-2.0, MoE, Quantized, LLM Explorer Score: 0.28.
4-bit 4bit Base model:quantized:teichai/g... Base model:teichai/glm-4.7-fla... Conversational Dataset:teichai/claude-4.5-opu... Glm4 moe lite Mlx Moe Quantized Region:us Safetensors Sharded Tensorflow Unsloth
Model Card on HF 🤗: https://huggingface.co/mlx-community/GLM-4.7-Flash-Claude-Opus-4.5-High-Reasoning-Distill-4bit
GLM 4.7 Flash Claude Opus 4.5 High Reasoning Distill 4bit Benchmarks
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
What is the LLM Explorer Rank (Score)
GLM 4.7 Flash Claude Opus 4.5 High Reasoning Distill 4bit Parameters and Internals
| LLM Name | GLM 4.7 Flash Claude Opus 4.5 High Reasoning Distill 4bit |
| Repository 🤗 | https://huggingface.co/mlx-community/GLM-4.7-Flash-Claude-Opus-4.5-High-Reasoning-Distill-4bit |
| Base Model(s) | |
| Model Size | 29.9b |
| Required VRAM | 17 GB |
| Updated | 2026-04-13 |
| Maintainer | mlx-community |
| Model Type | glm4_moe_lite |
| Model Files | |
| Quantization Type | 4bit |
| Model Architecture | Glm4MoeLiteForCausalLM |
| License | apache-2.0 |
| Context Length | 202752 |
| Model Max Length | 202752 |
| Transformers Version | 5.0.0.dev0 |
| Tokenizer Class | TokenizersBackend |
| Padding Token | [MASK] |
| Vocabulary Size | 154880 |
| Torch Data Type | bfloat16 |
Best Alternatives to GLM 4.7 Flash Claude Opus 4.5 High Reasoning Distill 4bit
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| GLM 4.7 Flash 6bit | 198K / 24.2 GB | 10811 | 5 |
| ....5 High Reasoning Distill 6bit | 198K / 24.2 GB | 1643 | 2 |
| GLM 4.7 Flash 4bit Mxfp4 | 198K / 15.9 GB | 477 | 4 |
| GLM 4.7 Flash 8bit Gs32 | 198K / 33.6 GB | 187 | 5 |
| Glm 4.7 Flash Opus Reasoning | 198K / 59.9 GB | 580 | 0 |
| GLM 4.7 Flash Heretic | 198K / 59.9 GB | 2055 | 12 |
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/GLM-4.7-Flash-Claude-Opus-4.5-High-Reasoning-Distill-4bit .
Rank the GLM 4.7 Flash Claude Opus 4.5 High Reasoning Distill 4bit Capabilities
🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟
What open-source LLMs or SLMs are you in search of? 53053 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a