# GLM-4.7-Flash vs OTel-2.0-LLM-31B-IT: Specs, License and GPU Cost
Source: https://savrn.com/models/compare/glm-4-7-flash-vs-otel-2-0-llm-31b-it
Markdown alternate of the page above; the site index is https://savrn.com/llms.txt

---

| Field | [GLM-4.7-Flash](https://savrn.com/models/glm-4-7-flash) zai-org/GLM-4.7-Flash | [OTel-2.0-LLM-31B-IT](https://savrn.com/models/otel-2-0-llm-31b-it) farbodtavakkoli/OTel-2.0-LLM-31B-IT |
| --- | --- | --- |
| Publisher | Z.ai | Farbod Tavakkoli |
| Task | Text generation | Text generation |
| Modality | Text | Text |
| Parameters, as reported | 31.2B parameters | 31.3B parameters |
| Architecture | Glm4MoeLiteForCausalLM | Gemma4ForConditionalGeneration |
| Library | transformers | transformers |
| Context length | 202,752 tokens | 262,144 tokens |
| Repository size | 62.5 GB | 126.8 GB |
| Artifact formats | safetensors | safetensors |
| License | mit | apache-2.0 |
| Access | Open weights, no gate | Open weights, no gate |
| Memory at 16-bit (weights and margin) | 74.9 GB | 75.1 GB |
| Cheapest GPUs at 16-bit, per hour | 1x MI300X, $1.85 | 1x MI300X, $1.85 |
| Memory at 4-bit (weights and margin) | 18.7 GB | 18.8 GB |
| Cheapest GPUs at 4-bit, per hour | 1x MI300X, $1.85 | 1x MI300X, $1.85 |
| Revision viewed | 7dd20894a642 | de9c87a5681a |
| Downloads reported by the hub | 1M | 1.2M |
| Last observed | 2026-10-23 | 2026-10-12 |

An evaluation row appears only where at least two of these models report the same benchmark with the same stated configuration, metric, unit and setup. Different evaluators stay named in each cell. Values are shown as reported: no unit conversion, no ranking.

## Other Reported Results

These results are listed for each model on its own, because the conditions needed to compare them are not stated or do not match. Two results that leave a condition blank are not assumed to share it.

### GLM-4.7-Flash

| Benchmark | Conditions | Result | Reported by | Revision | Date |
| --- | --- | --- | --- | --- | --- |
| Idavidrein/gpqa | Task diamondMetric diamondComparison conditions not established | 75.2 | [Model Card](https://huggingface.co/zai-org/GLM-4.7-Flash) Reported by a third party | Evaluated revision not stated | 2026-01-27 |
| SWE-bench/SWE-bench_Verified | Task swe_bench_%_resolvedMetric swe_bench_%_resolvedComparison conditions not established | 59.2 | [Model Card](https://huggingface.co/zai-org/GLM-4.7-Flash) Reported by a third party | Evaluated revision not stated | 2026-03-18 |
| cais/hle | Task hleMetric hleComparison conditions not established | 14.4 | [Model Card](https://huggingface.co/zai-org/GLM-4.7-Flash) Reported by a third party | Evaluated revision not stated | 2026-01-28 |

## SAVRN's Notes on GLM-4.7-Flash

GLM-4.7-Flash is a 30B-A3B mixture-of-experts: 31.2B parameters with about 3B active per token, routed across 64 experts, 4 per token. The full-precision run needs 74.9 GB at 16-bit, 37.5 GB at 8-bit and 18.7 GB at 4-bit — one MI300X at $1.85 an hour carries it at any precision, and at 4-bit it drops to a workstation card. The repo is 48 safetensors shards totalling 62.4 GB, context is 202,752 tokens, and downloads run 1.8M a month.

MIT permits commercial use with no added terms. Reported scores on the page include GPQA diamond 75.2, SWE-bench Verified 59.2 and HLE 14.4, and the card tables it against Qwen3-30B-A3B and GPT-OSS-20B, leading SWE-bench 59.2 to 22.0 and 34.0. Hosted, DeepInfra lists $0.06 in and $0.40 out per million tokens, Novita $0.07 and $0.40 — among the cheapest agentic-class rates we track.

A blockwise FP8 build, glm47-flash-blockwise-fp8, is listed at about half the BF16 size — 30 GiB against 58 — with gsm8k of 0.809 versus 0.819 for BF16: a small, stated quality cost for halved memory. Its card also warns attention tensor parallelism must be 1 or 2. For agentic work at this price, we would benchmark this before any other 30B-class model.

SAVRN Research

## SAVRN's Notes on OTel-2.0-LLM-31B-IT

A 31.3B-parameter model with a 262,144-token context, post-trained from Gemma 4 31B-IT on roughly 440 billion telecom tokens: OTel-2.0-LLM-31B-IT is built for network operations, standards interpretation, configuration help and retrieval-backed answering, which is why the window matters — the input is a standards document, not a ticket. Memory runs 75.1 GB at 16-bit, 37.5 GB at 8-bit, 18.8 GB at 4-bit, and every row fits one MI300X at $1.85 an hour. The Gemma4ForConditionalGeneration architecture records the base.

Apache 2.0 permits commercial deployment, modification and redistribution with notices kept, though the Gemma base's terms deserve their own read. The repository is 39 files and 126.8 GB — about twice the 62.5 GB of 16-bit weights — so confirm what the extra files hold before pulling. The card points evaluators at agentic suites such as SWE-Bench Verified and τ²-Bench with preserved-thinking mode. If your workload is not telecom, the neighboring Qwen3.6-27B offers a more general long-context run.

SAVRN Research

## Questions

### Which is larger, GLM-4.7-Flash or OTel-2.0-LLM-31B-IT?

OTel-2.0-LLM-31B-IT (31.3B parameters) is larger than GLM-4.7-Flash (31.2B parameters), by the parameter counts their publishers report.

### Which is cheaper to run, GLM-4.7-Flash or OTel-2.0-LLM-31B-IT?

At 4-bit, GLM-4.7-Flash fits on 1x MI300X from $1.85 an hour and OTel-2.0-LLM-31B-IT on 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists.

### Can I use GLM-4.7-Flash commercially?

Yes. GLM-4.7-Flash is released under MIT License. The MIT License is a short permissive license. It permits commercial use, modification and redistribution, provided the copyright notice and permission notice are included.

### Can I use OTel-2.0-LLM-31B-IT commercially?

Yes. OTel-2.0-LLM-31B-IT is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors.

## Related Comparisons

- [Fastino-Nemotron-3.5-Lightning-Finance vs OTel-2.0-LLM-31B-IT](https://savrn.com/models/compare/fastino-nemotron-3-5-lightning-finance-vs-otel-2-0-llm-31b-it)
- [NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 vs OTel-2.0-LLM-31B-IT](https://savrn.com/models/compare/nvidia-nemotron-3-nano-30b-a3b-bf16-vs-otel-2-0-llm-31b-it)