How much memory does GLM-4.7-Flash need at Q4?

The Q4 figure used here is 18.8 GB. GGUF file size plus an FP16 KV-cache estimate at 8,192 tokens. The cache counts only the layers and heads named in the method on the About page.

What is the cheapest catalog device that runs GLM-4.7-Flash at Q4?

Radeon RX 7900 XT, list price $899.

How fast is GLM-4.7-Flash on the Framework Desktop 128GB, as a bandwidth estimate?

About 42.7 tok/s at FP16. That is device bandwidth divided by active weight bytes, not a measured run.

Yes. GLM-4.7-Flash fits on the Framework Desktop 128GB at FP16, with 21.1 GB of headroom. Usable memory is 96.0 GB.

Can the Framework Desktop 128GB run GLM-4.7-Flash?

Data updated 16 October 2026. Last reviewed the same day, when this catalog snapshot was written.

Usable memory on this 128 GB unified-memory config is 96.0 GB (75% of the sticker figure). A result under 2 GB of headroom is labeled tight.

Quant ladder

Estimated memory for GLM-4.7-Flash on Framework Desktop 128GB
Quant	Estimate	Headroom	Est. tok/s	Verdict
Q4	18.8 GB	77.2 GB	145 tok/s	Yes
Q8	32.3 GB	63.7 GB	83.7 tok/s	Yes
FP16	74.9 GB	21.1 GB	42.7 tok/s	Yes

GGUF file size plus an FP16 KV-cache estimate at 8,192 tokens. The cache counts only the layers and heads named in the method on the About page.
Formula estimate: parameter count × bytes per weight × 1.20. No GGUF file size is stored for this quant.
Tokens/sec is a bandwidth roofline: GB/s divided by active weight GB. It is not a measured generation speed.

KV cache at 8K and 32K

FP16 KV-cache estimate: 0.4 GB at 8,192 tokens and 1.8 GB at 32,768 tokens. MLA models use the compressed latent plus the RoPE key from config.json, not a per-head KV.

Offload

This machine has one memory pool. Weights are not offloaded to a second bank of system RAM.

Ollama

This command pulls the Q4_K_M file from unsloth/GLM-4.7-Flash-GGUF, the Hub repo whose file size is used above. It is not an official Ollama library tag.

ollama run hf.co/unsloth/GLM-4.7-Flash-GGUF:Q4_K_M

Other picks

Cheapest catalog device at Q4: Radeon RX 7900 XT
Closest catalog model that still fits at Q4: Mixtral 8x22B.

All hardware for GLM-4.7-Flash · All models for the Framework Desktop 128GB

Questions

How much memory does GLM-4.7-Flash need at Q4?: The Q4 figure used here is 18.8 GB. GGUF file size plus an FP16 KV-cache estimate at 8,192 tokens. The cache counts only the layers and heads named in the method on the About page.
Can the Framework Desktop 128GB run GLM-4.7-Flash?: Yes. GLM-4.7-Flash fits on the Framework Desktop 128GB at FP16, with 21.1 GB of headroom. Usable memory is 96.0 GB.
What is the cheapest catalog device that runs GLM-4.7-Flash at Q4?: Radeon RX 7900 XT, list price $899.
How fast is GLM-4.7-Flash on the Framework Desktop 128GB, as a bandwidth estimate?: About 42.7 tok/s at FP16. That is device bandwidth divided by active weight bytes, not a measured run.