Skip to content
Local AI Wizard
Your machine
Theme

GLM-4.7 Flash

Z.ai · zai-org/GLM-4.7-Flash

Q4 file 18.3 GB (Q4_K_M) · runs well from 32 GB · Weights license: MIT

LMArena · text1,365 ± 6Rank 203 · release 2026-10-22 · its own scale
Memory needed~23 GBQ4 weights + working room, before the machine's reserve
Parameters30 Bmanufacturer specification · ~3B active
Context202,752 tokensPublished for this model

Quality

LMArena · text · rating
1,365 ± 6Confidence interval 1,359–1,370 · 12,013 votes · rank 203 of the releaseLMArena 2026-10-22 · CC BY 4.0

No result in LiveBench 2026-06-25 Not in LiveBench 2026-06-25

Reported by the publisher

7 results · Z.ai's model card · read 2026-10-25
AIME 25
91.6
GPQA
75.2
LCB v6
64.0
HLE
14.4
SWE-bench Verified
59.2
τ²-Bench
79.5
BrowseComp
42.8

Values as printed on the card, with the publisher's own settings (card section: Introduction › Performances on Benchmarks); column “GLM-4.7-Flash”. Not comparable across publishers and not used in any ranking. Model card

Run it

Run it

File Q4_K_M · 18.3 GB · unsloth/GLM-4.7-Flash-GGUF · What is Q4?

Measured 48.7 tok/s · Q8_0 · 1 machine · llama.cpp benches/dgx-spark · all rows

ollama run hf.co/unsloth/GLM-4.7-Flash-GGUF:Q4_K_M
  1. Install Ollama
  2. Run the command above
  3. Ask: Explain what a context window is, in two sentences.

Runs on

Fast memory holds it 42

The planning estimate fits the memory the model can use quickly: graphics card VRAM, or unified memory within the macOS GPU share.

Show all 42

Within memory, outside the fast part 51

Within the machine's memory, outside its fast part: on a graphics card the layers that do not fit run on the CPU from PC RAM (the listed RAM, or 32 GB assumed); on a Mac, above the macOS default GPU share. Not a speed figure.

Show all 51

One memory tier short 9

The same machines with the next memory size up would hold it in fast memory.

Show all 9

GLM-4.7 Flash is a text model from Z.ai with 30B parameters, ~3B of them active per token (mixture of experts). It was released on January 19, 2026 and reads up to 202,752 tokens of context. Its Q4 weights plus working room come to about 23 GB before the machine's reserve; the smallest reference machines whose fast memory holds that are Mac mini M4 · 32 GB unified (~31 GB with its reserve) and RTX 5090 · 32 GB VRAM (~25 GB with its reserve). We collected 31 downloadable GGUF and MLX files from 3 publisher sources; the most downloaded GGUF source is unsloth's. It has no result in LiveBench 2026-06-25. Its LMArena text rating is 1,365 ± 6 (release 2026-10-22), a separate human-preference scale.

Hardware profiles grouped by the Q4 planning estimate on each machine (dedicated GPUs reserve 2 GB; unified and system memory 25%, 2 to 8 GB): the fast memory holds it, it is within memory but outside the fast part (layers offloaded to PC RAM, or above the macOS GPU share), or the machine is one memory tier short. Each card opens its hardware profile. Not a measured fit or speed.

On the reference machines

GLM-4.7 Flash on the reference machines
Where Q4 sits
Mac mini M2 · 8 GB unifiedLarger than its memoryNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column~25 GBLarger than its memoryNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column
Mac mini M4 · 16 GB unifiedLarger than its memoryNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column~27 GBLarger than its memoryNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column
Mac mini M4 · 24 GB unifiedLarger than its memoryQ3_K_MGGUF · 14.6 GB · needs ~24 GB8,192 tokens~29 GBLarger than its memoryQ3_K_MGGUF · 14.6 GB · needs ~24 GB8,192 tokens
Mac mini M4 · 32 GB unifiedFast memory holds itQ4_K_MGGUF · 18.3 GB · needs ~31 GB32,768 tokens~31 GBFast memory holds itQ4_K_MGGUF · 18.3 GB · needs ~31 GB32,768 tokens
Mac mini M5 Pro · 64 GB unifiedFast memory holds itQ8_0GGUF · 31.8 GB · needs ~47 GB131,072 tokens~31 GBFast memory holds itQ8_0GGUF · 31.8 GB · needs ~47 GB131,072 tokens
Mac Studio M5 Max · 128 GB unifiedFast memory holds itQ8_0GGUF · 31.8 GB · needs ~47 GB131,072 tokens~31 GBFast memory holds itQ8_0GGUF · 31.8 GB · needs ~47 GB131,072 tokens
Mac Studio · M5 Ultra · 36-core CPU / 80-core GPU · 512 GB unifiedFast memory holds itQ8_0GGUF · 31.8 GB · needs ~47 GB131,072 tokens~31 GBFast memory holds itQ8_0GGUF · 31.8 GB · needs ~47 GB131,072 tokens
RTX 4060 · 8 GB VRAMIn memory, outside the fast partNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column~25 GBIn memory, outside the fast partNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column
RTX 3060 · 12 GB VRAMIn memory, outside the fast partNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column~25 GBIn memory, outside the fast partNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column
RTX 5080 · 16 GB VRAMIn memory, outside the fast partNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column~25 GBIn memory, outside the fast partNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column
RTX 4090 · 24 GB VRAMIn memory, outside the fast partIQ4_XSGGUF · 16.3 GB · needs ~22 GB32,768 tokens~25 GBIn memory, outside the fast partIQ4_XSGGUF · 16.3 GB · needs ~22 GB32,768 tokens
RTX 5090 · 32 GB VRAMFast memory holds itQ5_K_MGGUF · 21.4 GB · needs ~29 GB65,536 tokens~25 GBFast memory holds itQ5_K_MGGUF · 21.4 GB · needs ~29 GB65,536 tokens
DGX H100 · 8 × 80 GBFast memory holds itQ8_0GGUF · 31.8 GB · needs ~55 GB131,072 tokens~39 GBFast memory holds itQ8_0GGUF · 31.8 GB · needs ~55 GB131,072 tokens

The file column uses the site's quant ladder (Q8_0 to Q3_K_M, MLX 8 to 4-bit on a Mac): the largest collected file whose size × 1.2 plus the context cache and the machine's reserve fits the fast memory. Planning estimates, not measured runs.

Plan another quantization or context

Consider it for

Compare GLM-4.7 Flash using its publisher card. No overall score appears in the LiveBench 2026-06-25 snapshot.

Check first

The Q4 weights plus working room come to about 23 GB from 30B stated parameters, before the machine's reserve (Runs on adds it per machine). It is not a measured minimum; context, batch size, runtime and quantization change actual memory use.

Versions to download

Files you can download for this checkpoint. The section opens on the most downloaded collected GGUF source, unsloth, at Q4_K_M. On a Mac it opens on the most downloaded MLX source. Sizes are the Hub's published bytes. What is Q4?

unsloth

unsloth/GLM-4.7-Flash-GGUF · GLM-4.7-Flash-Q4_K_M.gguf · 18.3 GB

Run this file

ollama run hf.co/unsloth/GLM-4.7-Flash-GGUF:Q4_K_M
llama-server -hf unsloth/GLM-4.7-Flash-GGUF:Q4_K_M
lms get https://huggingface.co/unsloth/GLM-4.7-Flash-GGUF
  • mlx-lm: mlx-lm runs MLX repositories; pick the MLX version on a Mac

Quality scores on this page belong to the original checkpoint; these files are not scored or ranked. File sizes read 2026-10-23 · download counts read 2026-10-17 · commands: Hugging Face Hub docs: Use Ollama with any GGUF model · llama.cpp server README (-hf <user>/<model>[:quant]) · LM Studio docs: lms get with a Hugging Face URL · mlx-lm README (mlx_lm.generate --model)

Fine-tunes, adapters and other versions81 fine-tunes
Quantized versions
107
Fine-tunes
81
Adapters · merges
22 · 0

Browse them on the Hugging Face model tree · read 2026-10-23

Uncensored and abliterated versions9

Some community uploads remove the model's safety refusals. Quality may drop, the original publisher does not support them, claims about them are the uploader's, and the original license still applies. This site never recommends or ranks them.

9 derivative repositories have “uncensored” or “abliterated” in their name (read 2026-10-23).

Measured speed

Tokens per second by machine

Output tok/s · 1 machine · every row in the table · What is a token?

DGX Spark, 48.68 ± 0.12 · Q8_048.7
Measured speed
DGX SparkDGX Spark · 1× NVIDIA GB1048.68 ± 0.12Q8_00 / 32 · Single llama-bench process; server concurrency not measuredllama.cpp CUDAllama.cpp commit 11fb327bfFlash Attention enabledggml-org/GLM-4.7-Flash-GGUF · llama-bench model “deepseek2 30B.A3B Q8_0”

Source: llama.cpp benches/dgx-spark · maintainer result (checked 2026-10-25) · llama.cpp CUDA · llama.cpp commit 11fb327bf · not estimated

How to run

The memory needed above is the Q4 load before a machine's reserve. Formula: parameters × 0.625 bytes, plus 20% working allowance; each machine then adds its system reserve: 25% of unified or system memory, 2 to 8 GB, or 2 GB per GPU on dedicated cards. This is neither measured VRAM nor checkpoint download size.

Q4 planning estimate only. Check checkpoint format, runtime support, KV cache, context, batch size and offload before choosing hardware.

Evidence level: Generic estimate only; no execution reproduced by this site.

Publisher sampling defaults
temperature 1generation_config.json · read 2026-10-23source
Chat template markers
tool calls · thinkingmarkers found in the template, not a test of the feature · read 2026-10-23source
Before downloading
  1. Check the exact checkpoint and license linked here.
  2. Confirm a compatible runtime and precision or quantization for your platform.
  3. Allow for context, batch size and any extra media components beyond the weights.

Technical details

What the source and the catalog store for this checkpoint. Missing fields are left out, never zero.

Checkpoint / version
zai-org/GLM-4.7-Flash
Task and modality
language and reasoning · text
Count and basis
30B · manufacturer specification · ~3B activezai-org/GLM-4.7-Flash model card (Hugging Face) · read 2026-10-17source
Context
202,752 tokens published for this modelzai-org/GLM-4.7-Flash config.json (Hugging Face) · read 2026-10-09source
Architecture
MoEzai-org/GLM-4.7-Flash model card (Hugging Face) · read 2026-10-17source
Released
New Released - Z.AI DEVELOPER DOCUMENT · read 2026-10-09source
Runtime and precision
No local execution verified.
Languages
en, zhModel card metadata · read 2026-10-25source
Commercial use
Allowed MIT license text (SPDX) · read 2026-10-18license text
Every stored field11 fields
Revision checked
7dd20894a642a0aa287e9827cb1a1f7f91386b67
Architecture
Glm4MoeLiteForCausalLM
Library
transformers
Hub task tag
text-generation
Formats
safetensors
Access
Open download
Publisher kind
Official
Repository created
2026-01-19creation is not the model's release
Repository updated
2026-01-29a commit is not a release date
Hub downloads (30 days) · likes
953,714 · 1,888this repository only · read 2026-10-25
Catalog state
Hub config or weights found; no inventory benchmark link

Sources

Identity and published specifications come from the checkpoint page. Benchmark scores belong to the named release and do not measure speed on your computer.

Catalog reviewed: 2026-10-17. Benchmark release: 2026-06-25; snapshot collected: 2026-10-18.