GLM-4.7-Flash-REAP-23B-A3B GGUF size and VRAM requirements

License: mit ⬇ 32,742 ❤ 255
Parameters23.0B
Context202,752

unsloth/GLM-4.7-Flash-REAP-23B-A3B-GGUF is a large language model with 23.0 billion parameters, built on the deepseek2 architecture. It is released under the mit license and has been downloaded 32,742 times.

To run unsloth/GLM-4.7-Flash-REAP-23B-A3B-GGUF locally at a 4,096-token context, its quantized versions need between 6.96 GB (Q1_0, lowest quality) and 43.72 GB (BF16, highest quality) of memory, weights plus KV cache and a system margin included.

For most users the best balance is IQ1_M, needing about 7.94 GB. That means unsloth/GLM-4.7-Flash-REAP-23B-A3B-GGUF fits entirely in the VRAM of an 8 GB GPU or larger, running fully on the GPU.

→ Guide: How much VRAM do you need?

GGUF file size and memory by quantization

Compare real GGUF weight sizes, estimated KV cache and total memory for Q4, Q5, Q8 and every quantization published in this repository.

Quant.Bits QualityWeights KVTotal Speed~Verdict
Q1_0 2.27 Very low 6.09 GB 0.07 GB 6.96 GB 65.7 t/s Fits in VRAM
IQ1_S 2.51 Very low 6.71 GB 0.07 GB 7.58 GB 59.6 t/s Fits in VRAM
IQ1_M 2.64 Low 7.07 GB 0.07 GB 7.94 GB 56.6 t/s Fits in VRAM
IQ2_XXS 2.87 Low 7.67 GB 0.07 GB 8.55 GB 6.5 t/s Offload
IQ2_M 2.98 Low 7.97 GB 0.07 GB 8.84 GB 6.3 t/s Offload
Q2_K 3.05 Low 8.17 GB 0.07 GB 9.04 GB 6.1 t/s Offload
Q2_K_L 3.08 Low 8.24 GB 0.07 GB 9.11 GB 6.1 t/s Offload
Q2_K_XL 3.14 Low 8.39 GB 0.07 GB 9.27 GB 6.0 t/s Offload
IQ3_XXS 3.49 Fair 9.35 GB 0.07 GB 10.22 GB 5.3 t/s Offload
Q3_K_S 3.58 Fair 9.59 GB 0.07 GB 10.46 GB 5.2 t/s Offload
Q3_K_M 3.92 Fair 10.5 GB 0.07 GB 11.37 GB 4.8 t/s Offload
Q3_K_XL 3.99 Fair 10.67 GB 0.07 GB 11.55 GB 4.7 t/s Offload
IQ4_XS 4.37 Good 11.71 GB 0.07 GB 12.58 GB 4.3 t/s Offload
IQ4_NL 4.61 Good 12.34 GB 0.07 GB 13.22 GB 4.1 t/s Offload
Q4_0 4.62 Good 12.38 GB 0.07 GB 13.25 GB 4.0 t/s Offload
Q4_K_S 4.64 Good 12.41 GB 0.07 GB 13.29 GB 4.0 t/s Offload
Q4_K_M 4.91 Good 13.14 GB 0.07 GB 14.02 GB 3.8 t/s Offload
Q4_K_XL 4.96 Good 13.27 GB 0.07 GB 14.14 GB 3.8 t/s Offload
Q4_1 5.09 Very good 13.62 GB 0.07 GB 14.49 GB 3.7 t/s Offload
Q5_K_S 5.58 Very good 14.94 GB 0.07 GB 15.81 GB 3.3 t/s Offload
Q5_K_M 5.73 Very good 15.35 GB 0.07 GB 16.22 GB 3.3 t/s Offload
Q5_K_XL 5.82 Very good 15.59 GB 0.07 GB 16.46 GB 3.2 t/s Offload
Q6_K 6.61 Excellent 17.69 GB 0.07 GB 18.56 GB 2.8 t/s Offload
Q6_K_XL 7.04 Excellent 18.84 GB 0.07 GB 19.71 GB 2.7 t/s Offload
Q8_0 8.51 Excellent 22.78 GB 0.07 GB 23.65 GB 2.2 t/s Offload
Q8_K_XL 9.58 Excellent 25.64 GB 0.07 GB 26.51 GB Insufficient
BF16 16.01 Excellent 42.85 GB 0.07 GB 43.72 GB Insufficient

KV cache computed from the model's exact architecture. Speed is a rough estimate bounded by memory bandwidth.

Frequently asked questions

How much VRAM do you need to run unsloth/GLM-4.7-Flash-REAP-23B-A3B-GGUF?

You need about 7.94 GB of VRAM to run unsloth/GLM-4.7-Flash-REAP-23B-A3B-GGUF entirely on the GPU using the IQ1_M quantization (at a 4,096-token context). Smaller quantizations lower the requirement at the cost of quality.

Can I run unsloth/GLM-4.7-Flash-REAP-23B-A3B-GGUF on an 8 GB GPU?

Yes. With 8 GB of VRAM you can run unsloth/GLM-4.7-Flash-REAP-23B-A3B-GGUF fully on the GPU using IQ1_M (about 7.94 GB).

Can I run unsloth/GLM-4.7-Flash-REAP-23B-A3B-GGUF on a 16 GB GPU?

Yes. With 16 GB of VRAM you can run unsloth/GLM-4.7-Flash-REAP-23B-A3B-GGUF fully on the GPU using Q5_K_S (about 15.81 GB).

Can I run unsloth/GLM-4.7-Flash-REAP-23B-A3B-GGUF on a 24 GB GPU?

Yes. With 24 GB of VRAM you can run unsloth/GLM-4.7-Flash-REAP-23B-A3B-GGUF fully on the GPU using Q8_0 (about 23.65 GB).

What is the best quantization for unsloth/GLM-4.7-Flash-REAP-23B-A3B-GGUF?

If memory allows, higher bits-per-weight means better quality. A common sweet spot is a Q4_K_M or Q5_K_M quantization, which keeps most of the quality while roughly halving the memory versus 8-bit. Pick the highest quantization that still fits in your VRAM.