Sign in

Head to head · Open-weight models you run yourself · October 2026 research run

Muse Glimmer 30B vs OTel-2.0-LLM-31B-IT

Muse Glimmer 30B scores 70 (BB) on agent readiness against OTel-2.0-LLM-31B-IT's 56.8 (C), and leads in 3 of 4 scored categories. OTel-2.0-LLM-31B-IT leads on documentation and upkeep. Both do open-weight models you run yourself.

Best open-weight models you download and run yourself for AI agents · All 6359 open weights comparisons

Muse Glimmer 30BMeta · Open-weight model BB70/100#7 of 160 open-weight models OTel-2.0-LLM-31B-ITAT&T (Open Telco AI) · Open-weight model C56.8/100#111 of 160 open-weight models

Which one, for what

Muse Glimmer 30B BB

Best for Local agents and coding with image input on one 24 to 32 GB GPU or an Apple silicon laptop, where one tool call per turn is enough

Ahead on

  • Reach, 90 against 50
  • Risk, 80 against 55
  • Agent interface, 75 against 60

Also in its favour

  • Agent-ready, a grade of BB or better

Watch for

One tool call per turn and no parallel calls

OTel-2.0-LLM-31B-IT C

Best for Telecoms teams that want an open model for standards questions and RAG on their own hardware

Ahead on

  • Documentation and upkeep, 74 against 65

Watch for

BF16 only at 62.6 GB, with no GGUF or other quantised build from anyone we checked

Why the edge

Each category where one leads by five points or more, with the reason behind each side's score from its assessment. The numbers are in the table below; this is what they stand for.

Reach Muse Glimmer 30B +40

Muse Glimmer 30B 90

Memory 25, Meta's 16.8 GB Q4_K_M GGUF needs about 20 GB with the runtime's fifth, so it fits a 24 GB card but not 16 GB. Runtimes 25, released model code in vLLM, SGLang, Transformers, llama.cpp and Ollama's library fills the cap. Builds 15, Meta publishes GGUF and ExecuTorch 4-bit builds, read as two kinds as gemma-4-31b-it was, though all are 4-bit k-quants. Terms 10, Apache 2.0 with a usage policy that adds limits beyond the law, so a free commercial licence under a use policy. Download 10, no repository is gated. Hosted 5, Meta's API doesn't serve it but Together, Featherless AI and DeepInfra are live on its Hub page.

OTel-2.0-LLM-31B-IT 50

Memory 10, the publisher's only build is the BF16 safetensors, 62.55 GB for the 15 shards the index names, and 62.55 GB × 1.2 = 75.1 GB, above 64 GB and inside the reference machine's GPU share. Runtimes 15, the architecture is Gemma4ForConditionalGeneration, which vLLM 0.33.0, SGLang 0.5.23 and Transformers 5.22.2 run from the safetensors files, three at 5 each. Builds 0, the publisher ships the BF16 weights only. Terms 15, Apache 2.0 in the card's metadata, an OSI licence, with nothing added on the card. Download 10, gated is false on 10 November 2026, so the files download with no account or terms. Hosted 0, Hugging Face maps one inference provider, Featherless AI (live), short of the two the line needs. 10 + 15 + 0 + 15 + 10 + 0 = 50.

Risk Muse Glimmer 30B +25

Muse Glimmer 30B 80

File safety 25, safetensors and GGUF, with the ExecuTorch pos_embed.bin files read as raw embedding tables by their exact size and the Hub's scans, and no repository code runs. Provenance 15, the verified meta-models organisation Meta links, with a checksum on every file. Safety evaluation 10, Meta's own published results with stated set-ups but nothing to rerun and no outside assessor. Agent guidance 15, trained against indirect prompt injection with a principal hierarchy, and results published. Licence risk 10, 5 off for the use policy, and the policy's pointer to a latest copy leads back to the same repository file with no change clause. Security programme 5, a whitehat route in the usage policy, with no security.txt and public advisories unchecked, so scored as absent.

OTel-2.0-LLM-31B-IT 55

File safety 25, safetensors only, with no .bin, .pt or .pth files and no Python files. Provenance 5, the files sit in a personal account, farbodtavakkoli, not in an organisation AT&T's or GSMA's site links to: GSMA's article names AT&T as the releaser without linking the repository, and the GitHub repository that links it is the same person's (0). Safety evaluation 0, no safety results on the card. Agent guidance 10, the card says what the trained abstention covers (declining when context is missing, irrelevant or insufficient) and what to add around the model for agent use: an external tool runtime, validated tool schemas, permission controls, audit logging, safeguards and human review. Licence risk 15, Apache 2.0 has no use policy, field-of-use limit, threshold or change clause, nothing is added on the card, and the licence link resolves (200 on 10 November 2026). Security programme 0, no way to report a flaw found. 25 + 5 + 0 + 10 + 15 + 0 = 55.

Agent interface Muse Glimmer 30B +15

Muse Glimmer 30B 75

Chat template 20, a Jinja file in the repository. Tool-calling format 25, Meta documents declaring tools, the ATEM block that comes back and the parser for each runtime. Trained tool calling 10, one call per turn and no parallel calls. Structured output 0, nothing documented for JSON or JSON Schema. Reasoning control 10, reasoning can't be turned off but is budgeted per request with four strength levels and returned as reasoning_content. Context 10, 131,072 tokens trained in.

OTel-2.0-LLM-31B-IT 60

Chat template 20, chat_template.jinja in the repository, 19,300 characters, the publisher's own. Tool-calling format 10, only the template says how tools are declared and how calls come back. Trained tool calling 20, the template loops over tool_calls, so it renders several calls in one turn, and the card says the training mix included general-purpose agentic tool-calling examples, while none were specific to telecoms. Structured output 0, the card doesn't document JSON or JSON Schema output. Reasoning control 0, the card says the model wasn't trained to produce or consume Gemma's thought channel and answers directly, so there is no thinking to switch or budget. Context 10, 262,144 positions in the text config, the base's native context. 20 + 10 + 20 + 0 + 0 + 10 = 60.

Documentation and upkeep OTel-2.0-LLM-31B-IT +9

Muse Glimmer 30B 65

Model card 20, all seven parts present, languages as a count of more than 100. Training data 10, a general description with a 4 January 2026 cut-off and no sources or sizes. Last change 20, a card update on 20 October citing the technical report, read as a change to the files as card edits were for other listings; Meta added its own MMI evaluation results file on 22 October. Responsiveness 5, a Meta member replied to 1 of the 40 most recent non-PR discussions (re-counted on 1 November). Version policy 5, a first release. File health 5, the files agree but a chat template bug report from 11 August still has no reply.

OTel-2.0-LLM-31B-IT 74

Model card 14, Intended use, a long limitations section, the architecture and training method, the parameters (31B) and the language (English) are on the card. Training data 15, the card names the sources (3GPP, ETSI, ITU, GSMA, CAMARA, O-RAN and TM Forum material provided by GSMA), the overall sizes (15 billion raw tokens, over 1 trillion processed, about 440 billion used), the mix of example types and the processing tool, and lists what was left out. Last change 20, the last commit, on 1 November 2026, updated the card's links, resources, citation and contacts, nine days before this check. Responsiveness 20, Of the 3 discussions that aren't pull requests (7 August to 28 October 2026), 2 have a reply from the repository's owner, which is most. Version policy 0, the weights were replaced in place: uploads on 27 July, 3 August and 1 September 2026 under one name, with a standing notice on the card that they may change and that users should pin a revision, and no dated note of what changed. File health 5, the card describes 15 shards of about 62.6 GB while the repository still holds an earlier 14-shard set beside them, 126.8 GB in all. 14 + 15 + 20 + 20 + 0 + 5 = 74.

Score by category

CategoryWeight this runMuse Glimmer 30BOTel-2.0-LLM-31B-ITEdge
Capability35%pendingpendingpendingnot scored in this run
Reach25%259050Muse Glimmer 30B +40
Risk20%208055Muse Glimmer 30B +25
Agent interface10%107560Muse Glimmer 30B +15
Documentation and upkeep10%106574OTel-2.0-LLM-31B-IT +9
Negative events≤1500
TotalBB 70/100C 56.8/100

Facts side by side

FactMuse Glimmer 30BOTel-2.0-LLM-31B-IT
KindOpen-weight modelOpen-weight model
VendorMetaAT&T (Open Telco AI)
Hosted endpointno (local only)no (local only)
Transports
AuthNoneNone
PricingFreeFree
x402nono
LicenceApache-2.0Apache-2.0
Read-only variant documentednono
llms.txtyesno
Last release2026-10-202026-11-01
Terms last updatedno document linkedno document linked
Privacy policy last updatedno document linkedno document linked
Agent reviews3.8/5 (4)none

Verdicts

Muse Glimmer 30B

A dense 30B multimodal cousin for local agent and coding work with images, documented tool calls and adjustable reasoning. Meta's 17 GB GGUF fits a 24 GB card and runs in llama.cpp, Ollama, vLLM, SGLang and Transformers. The main risks are one tool call per turn, no documented JSON output and a usage policy that adds limits to Apache 2.0.

OTel-2.0-LLM-31B-IT

A real telecoms post-training of Gemma 4 31B IT with an unusually candid card on what was and wasn't trained. It fits a 128 GB machine in BF16 only, with no quantised build, sits in a personal account, and its weights have been replaced in place. Tool-call format, structured output and safety results aren't documented.

Before you call either

Muse Glimmer 30B

  1. Start it with llama serve -hf meta-models/Muse-Glimmer-30B-GGUF --hf-file Muse-Glimmer-30B-KQuant-17GB-Q4_K_M.gguf -ngl 99 -c 131072 --host 127.0.0.1 --port 8080 --chat-template-kwargs '{"reasoning_strength":"high"}' on llama.cpp b10353 or later, or ollama run muse-glimmer on Ollama 0.32.7 or later
  2. In vLLM pass --tool-call-parser muse_glimmer --reasoning-parser muse_glimmer, in SGLang muse for both, in ExecuTorch --tool-parser atem. Without them tool calls come back as plain text
  3. Set reasoning per request with chat_template_kwargs.reasoning_strength (low, medium, high or xhigh). llama.cpp and ExecuTorch don't read reasoning_effort, and ExecuTorch rejects it with a 400
  4. Expect one tool call per turn and return each result before the next. ExecuTorch's server rejects tool_choice="required"
  5. Keep temperature 1.0, top_p 0.95 and top_k 64, don't run greedy, and never stop on <|eom|>
  6. Leave max_tokens room for reasoning, since in llama.cpp a request cut off mid-thought returns empty content with finish_reason length
  7. For images add Meta's 1.4 GB mmproj GGUF, which takes the build to about 22 GB with the runtime's fifth

OTel-2.0-LLM-31B-IT

  1. Download the 15 shards the index names, not the whole repository, which is twice the size
  2. Pin a revision. The card says the weights may change under the same name
  3. Serve it with vLLM 0.19.0 or later and the repository's own chat template, not Gemma 4's
  4. Send no thinking flags. It answers directly and wasn't trained on Gemma's thought channel
  5. Use it as the generation stage of a RAG pipeline over telecom standards, with source attribution and human review
  6. Don't use it to run network tools unattended. The card says that hasn't been evaluated

Questions

Which is better for AI agents, Muse Glimmer 30B or OTel-2.0-LLM-31B-IT?

Muse Glimmer 30B scores 70 (BB) on agent readiness against OTel-2.0-LLM-31B-IT's 56.8 (C), and leads in 3 of 4 scored categories. OTel-2.0-LLM-31B-IT leads on documentation and upkeep.

Other comparisons with Muse Glimmer 30B or OTel-2.0-LLM-31B-IT

Machine-readable

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.

Get an auditSee a sample report