IN

ComfyChat InternLM2 1 8b v2 1

InternLMGGUF by mradermacherUpdated 2024-08-03
Download on Hugging Face
Parameters1.89B
Context32K
Layers24
Architectureinternlm2
Smallest quant0.8 GB
Quick answer

ComfyChat InternLM2 1 8b v2 1 needs about 2.5 GB of memory at Q4_K_M (a 1.2 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 15 quants, from 0.8 GB (Q2_K) to 3.8 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 3.2 GB.

ComfyChat InternLM2 1 8b v2 1 is a 1.89B-parameter InternLM model in GGUF format, quantized by mradermacher. Its trained context length is 32K tokens. The repository has 15 quant files, from 0.8 GB (Q2_K) to 3.8 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K0.8 GB 2.1 GB
Fits Get file →
IQ3_XS0.9 GB 2.2 GB
Fits Get file →
IQ3_S0.9 GB 2.2 GB
Fits Get file →
Q3_K_S0.9 GB 2.2 GB
Fits Get file →
IQ3_M0.9 GB 2.2 GB
Fits Get file →
Q3_K_M1.0 GB 2.3 GB
Fits Get file →
Q3_K_L1.0 GB 2.3 GB
Fits Get file →
IQ4_XS1.1 GB 2.4 GB
Fits Get file →
Q4_K_S1.1 GB 2.4 GB
Fits Get file →
Q4_K_M1.2 GB 2.5 GB
Fits Get file →
Q5_K_S1.3 GB 2.6 GB
Fits Get file →
Q5_K_M1.4 GB 2.7 GB
Fits Get file →
Q6_K1.6 GB 2.9 GB
Fits Get file →
Q8_02.0 GB 3.3 GB
Fits Get file →
F163.8 GB 5.1 GB
Fits Get file →

What GPU do you need for ComfyChat InternLM2 1 8b v2 1?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: the best quant that fits is Q8_0 (2.0 GB file, about 3.3 GB in use).
  • 6 GB VRAM: the best quant that fits is F16 (3.8 GB file, about 5.1 GB in use).

Which ComfyChat InternLM2 1 8b v2 1 quant should you choose?

Q4_K_M is the usual starting point for ComfyChat InternLM2 1 8b v2 1: it balances file size and quality well. Here it is a 1.2 GB file.

The Q8_0 file is 2.0 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is Q2_K at 0.8 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureinternlm2
Parameters1.89B
Layers24
Trained context32,768 tokens
KV cache (fp16)96 KB per token

Source

Quantized bymradermacher
FamilyInternLM
Downloads (HF)287
Last updated2024-08-03

Frequently asked questions about ComfyChat InternLM2 1 8b v2 1

How much VRAM does ComfyChat InternLM2 1 8b v2 1 need?

About 2.5 GB at Q4_K_M with an 8K context window. That is the 1.2 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run ComfyChat InternLM2 1 8b v2 1 on an 8 GB GPU?

Yes, with F16: the 3.8 GB file needs about 5.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of ComfyChat InternLM2 1 8b v2 1 GGUF?

It depends on the quant: Q2_K is 0.8 GB, IQ3_XS is 0.9 GB, IQ3_S is 0.9 GB, Q3_K_S is 0.9 GB, IQ3_M is 0.9 GB, Q3_K_M is 1.0 GB and 9 more.

What context length does ComfyChat InternLM2 1 8b v2 1 support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.8 GB at 8K and 3.2 GB at 32K.

Where can I download ComfyChat InternLM2 1 8b v2 1 GGUF?

The files are on Hugging Face in the mradermacher/ComfyChat-InternLM2-1-8b-v2-1-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More InternLM models

All InternLM →

Other tiny models

All tiny models →